CN118521043B

CN118521043B - Water ecology investigation and evaluation method, device, equipment and storage medium

Info

Publication number: CN118521043B
Application number: CN202410969857.8A
Authority: CN
Inventors: 来楷迪; 朱栋; 陈亚; 卢莎莎; 翁世辰; 方誉锟
Original assignee: Guizhou Environmental Engineering Assessment Center; Guizhou Lvxing Qingyuan Environmental Protection Co ltd; Guizhou University
Current assignee: Guizhou Environmental Engineering Assessment Center; Guizhou Lvxing Qingyuan Environmental Protection Co ltd; Guizhou University
Priority date: 2024-07-19
Filing date: 2024-07-19
Publication date: 2024-10-18
Anticipated expiration: 2044-07-19
Also published as: CN118521043A

Abstract

The invention discloses a water ecology investigation and evaluation method, a device, equipment and a storage medium, and belongs to the technical field of environmental data analysis and processing. The method can efficiently integrate and analyze the multisource monitoring data, can deeply mine the ecology law after the data are back, and can accurately identify and track the key ecology indexes through the vector mapping and focusing technology. Meanwhile, importance of time-space domain analysis is emphasized, a global assessment framework is constructed through linkage monitoring index association, and the comprehensiveness and accuracy of assessment are greatly improved. Finally, based on the output of the commonality weight operation, more scientific and accurate decision support can be provided for the ecological quality management of the water area.

Description

Water ecology investigation and evaluation method, device, equipment and storage medium

Technical Field

The invention belongs to the technical field of environmental data analysis and processing, and particularly relates to a water ecology investigation and evaluation method, a device, equipment and a storage medium.

Background

In the current water area ecological environment protection and management, accurately and efficiently evaluating the water area ecological quality is the basis for making scientific decisions. However, the conventional method often depends on limited monitoring data and experience judgment, and is difficult to comprehensively and deeply reflect the complex condition of the ecological environment of the water area and the dynamic change thereof. Particularly, when a large amount of multi-dimensional monitoring data is faced, an effective means for deep mining and comprehensive analysis is lacked, so that the accuracy and timeliness of an evaluation result are insufficient. In addition, the importance of time-space domain features is often ignored in the evaluation process, and the inherent relation between the evaluation early warning auxiliary decision information and the real-time monitoring data further limits the effectiveness and the guidance of the evaluation.

Disclosure of Invention

The invention provides a water ecology investigation and evaluation method, a device, equipment and a storage medium, which can solve or partially solve the technical problems related to the background technology.

The embodiment of the invention provides a water ecology investigation and evaluation method which is applied to water ecology investigation and evaluation equipment, and comprises the following steps: acquiring ecological environment monitoring data and corresponding evaluation early warning auxiliary decision information of a target water area; performing environment monitoring index vector identification according to the ecological environment monitoring data of the target water area to obtain an environment monitoring index vector; performing dense vector mapping on the evaluation early warning auxiliary decision information to obtain an auxiliary decision dense vector, performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and performing time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic ecological time-space domain index vector; performing linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector to obtain a global water ecological time-space domain index vector, and performing linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain a global environment monitoring index vector; carrying out commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector to obtain target commonality weight, and determining a target water ecology quality evaluation viewpoint corresponding to ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information

The embodiment of the invention provides a water ecological investigation and evaluation device which is used for: acquiring ecological environment monitoring data and corresponding evaluation early warning auxiliary decision information of a target water area; performing environment monitoring index vector identification according to the ecological environment monitoring data of the target water area to obtain an environment monitoring index vector; performing dense vector mapping on the evaluation early warning auxiliary decision information to obtain an auxiliary decision dense vector, performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and performing time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic ecological time-space domain index vector; performing linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector to obtain a global water ecological time-space domain index vector, and performing linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain a global environment monitoring index vector; and carrying out commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector to obtain target commonality weight, and determining a target water ecology quality evaluation viewpoint corresponding to the ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information.

The embodiment of the invention provides water ecology investigation and evaluation equipment, which comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored by the memory, causing the at least one processor to perform the method described above.

Embodiments of the present invention provide a readable storage medium having stored thereon a program or instructions which, when executed by a processor, perform the steps of the above-described method.

In the embodiment of the invention, not only can the multi-source monitoring data be integrated and analyzed efficiently, but also the ecology law after the data back can be deeply mined, and the accurate identification and tracking of the key ecology index can be realized through the vector mapping and focusing technology. Meanwhile, importance of time-space domain analysis is emphasized, a global assessment framework is constructed through linkage monitoring index association, and the comprehensiveness and accuracy of assessment are greatly improved. Finally, based on the output of the commonality weight operation, more scientific and accurate decision support can be provided for the ecological quality management of the water area.

Drawings

FIG. 1 is a flow chart of a water ecology investigation and evaluation method provided by an embodiment of the invention.

Fig. 2 is a schematic structural diagram of an apparatus for investigation and evaluation of water ecology according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The terms "first," "second," and the like in this specification are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present invention may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. In addition, "and/or" in the present invention means at least one of the connected objects, and the character "/" generally means a relationship in which the associated objects are one kind of "or".

Fig. 1 shows a water ecology investigation and evaluation method applied to a water ecology investigation and evaluation apparatus, the method comprising the following steps 110 to 150.

And 110, acquiring ecological environment monitoring data of the target water area and corresponding evaluation early warning auxiliary decision information.

And 120, identifying an environment monitoring index vector according to the ecological environment monitoring data of the target water area to obtain the environment monitoring index vector.

And 130, performing dense vector mapping on the evaluation early warning auxiliary decision information to obtain an auxiliary decision dense vector, performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and performing time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic ecological time-space domain index vector.

And 140, carrying out linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector to obtain a global water ecological time-space domain index vector, and carrying out linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain the global environment monitoring index vector.

And 150, carrying out commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector to obtain target commonality weight, and determining a target water ecology quality evaluation view corresponding to the ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information.

In modern water ecological management, accurate and comprehensive monitoring and assessment of the ecological environment of a water area is of great importance. In order to achieve the aim, the water ecology investigation and evaluation equipment provided by the embodiment of the invention integrates various high-tech monitoring technologies and data analysis algorithms, and can comprehensively monitor and evaluate the ecological environment of the water area. Hereinafter, how the water ecological investigation and evaluation apparatus performs steps 110 to 150 will be described in detail by way of a specific application scenario example.

The water ecology survey evaluation apparatus is first deployed in a target water area, which may be a lake, river, reservoir or the like. After the equipment is started, the ecological environment monitoring data of the target water area are collected in real time through integrated various sensors, such as a water quality sensor, a meteorological sensor, a biological sensor and the like. The ecological environment monitoring data include, but are not limited to, water temperature, pH, dissolved oxygen, turbidity, ammonia nitrogen content, phosphorus content, plankton type and number, and the like. Meanwhile, the water ecology investigation evaluation equipment is also connected to a data center through a wireless network, and evaluation early warning auxiliary decision information related to the target water area is acquired from the data center. The evaluation early warning auxiliary decision information is comprehensively obtained based on various data such as historical monitoring data, scientific research, policy regulations and the like and is used for assisting in evaluating and early warning of current monitoring data.

After the monitoring data and the auxiliary decision information are acquired, the water ecology investigation and evaluation equipment starts to execute the task of environment monitoring index vector identification. The purpose of this step is to convert the raw monitoring data into a structured form, namely an environmental monitoring index vector. The environment monitoring index vector contains values of all monitoring indexes, such as water temperature, pH value and the like, and each index corresponds to one dimension in the vector. To achieve this conversion, a set of data processing algorithms is built into the water ecological survey assessment apparatus. The set of algorithm firstly carries out preprocessing on the original data, such as removing noise, filling missing values and the like, and then organizes the processed data into an environment monitoring index vector according to a preset format.

Next, the water ecology investigation evaluation device performs dense vector mapping on the evaluation early warning auxiliary decision information. The purpose of this step is to convert the auxiliary decision information into a form compatible with the environmental monitoring index vector for subsequent joint analysis. Dense vector mapping is a technique that converts sparse or high-dimensional data into dense low-dimensional vectors, which can help improve the efficiency and accuracy of data analysis. After the dense vector mapping is completed, the water ecology investigation and evaluation equipment performs dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector. The purpose of this step is to highlight the part of the auxiliary decision information that is most relevant to the current monitoring situation in the target water area. Jiao Dianhua is implemented by computing the similarity between the environmental monitoring index vector and the decision-aid dense vector, the higher the similarity the greater the weight that the higher the similarity gets in the focused vector. And then, the water ecology investigation and evaluation equipment performs time-space domain vector mining according to the auxiliary decision vector after the focusing. Time-space domain vector mining is a technique that analyzes the distribution and trend of data in time and space. Through the step, the water ecology investigation and evaluation equipment can extract key indexes on a time-space domain related to the ecological environment of the target water area from a large amount of monitoring data, such as seasonal change of water quality, pollution conditions of a specific area and the like. The key indexes are organized into an aqueous ecological time-space domain index vector.

After the water ecology time-space domain index vector is obtained, the water ecology investigation and evaluation equipment carries out linkage monitoring index association on the water ecology time-space domain index vector through the environment monitoring index vector. The method aims at connecting key indexes on a time-space domain with current monitoring conditions to form a global water ecological time-space domain index vector. The global water ecological time-space domain index vector not only contains key indexes on a time-space domain, but also contains the association information between the indexes and the current monitoring condition. Meanwhile, the water ecology investigation and evaluation equipment also carries out linkage monitoring index association on the environment monitoring index vector through the water ecology time-space domain index vector to obtain a global environment monitoring index vector. The method aims at combining the current monitoring condition with key indexes on a time-space domain to form a comprehensive and deep global environment monitoring index vector. The global environment monitoring index vector not only contains current monitoring data, but also contains background and trend information of the data on a time-space domain.

And finally, the water ecology investigation and evaluation equipment performs commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector. The aim of this step is to find the index that is common to both vectors and has the greatest impact on the quality of the target waters ecology environment, and to calculate the weights of these indices. Commonality weight operation is a multi-criterion decision analysis method that can help determine factors and weights thereof that are commonly important under multiple criteria. After the commonality weight operation is completed, the water ecology investigation and evaluation equipment determines a target water ecology quality evaluation viewpoint corresponding to the ecology environment monitoring data of the target water area according to the obtained target commonality weight and evaluation early warning auxiliary decision information. The purpose of this step is to convert complex monitoring data and auxiliary decision information into a compact, clear assessment view, such as "current water quality in the target water is good, but there is a risk of seasonal eutrophication".

Through the steps, the water ecological investigation and evaluation equipment can comprehensively and accurately acquire the ecological environment monitoring data of the target water area, and can carry out deep analysis and evaluation by combining evaluation early warning auxiliary decision information. The method not only improves the efficiency and accuracy of water ecological management, but also provides powerful data support for formulating scientific and reasonable ecological protection measures.

In detail, the environmental monitoring index vector, the assistant decision density vector, the assistant decision attention vector, the water ecological time-space domain index vector, the global water ecological time-space domain index vector, and the global environmental monitoring index vector in the above steps 110-150 are important technical features related to the core invention point mentioned in the embodiments of the present invention, and the following description will be given for exemplary development of these vectors.

The environmental monitoring index vector is key information extracted from original monitoring data acquired from a target water area by water ecological investigation and evaluation equipment, and represents the current ecological environment condition of the water area in a structured form. The environmental monitoring index vector comprises a plurality of dimensions, and each dimension corresponds to a specific monitoring index. Taking a monitoring example, the environmental monitoring index vector may be as follows: [ Water temperature: 22.5 ℃, pH value: 7.8, dissolved oxygen: 8.5mg/L, turbidity: 12NTU, ammonia nitrogen content: 0.5mg/L, phosphorus content: 0.1mg/L, plankton species: 5, plankton number: 1000/L ]. The environmental monitoring index vector comprises 8 dimensions, and each dimension is a specific monitoring index such as water temperature, pH value and the like. The values of these indicators reflect the current ecological environment conditions of the target water area.

The auxiliary decision dense vector is a result obtained by performing dense vector mapping on the evaluation early warning auxiliary decision information. The assistant decision dense vector contains a plurality of assistant decision information related to the ecological environment of the target water area, and the information is converted into a form compatible with the environment monitoring index vector. Taking a certain auxiliary decision as an example, the auxiliary decision dense vector can be as follows: [ historical Water quality status: 0.8, seasonal variation pattern: 0.6, policy regulatory influence: 0.4, ecological protection target: 0.7, peripheral human activity effects: 0.5]. The auxiliary decision dense vector contains 5 dimensions, each dimension being a specific auxiliary decision information such as historical water quality conditions, seasonal variation patterns, etc. The values of these information are converted into values between 0 and 1, representing their importance in the current decision.

The auxiliary decision attention vector is a result obtained by carrying out dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector. The auxiliary decision attention vector highlights auxiliary decision information most relevant to the current monitoring condition of the target water area. Taking a certain focus as an example, the auxiliary decision-making attention vector may be as follows: [ historical Water quality status: 0.9, seasonal variation pattern: 0.8, policy regulatory impact: 0.3, ecological protection target: 0.6, peripheral human activity effects: 0.4]. The dimensions associated with the historical water quality conditions and seasonal patterns of variation are weighted higher in the focused vector because they are more relevant to the current monitoring conditions in the target water area.

The water ecological time-space domain index vector is a result obtained by mining the time-space domain vector and comprises key indexes of the ecological environment of the target water area on the time-space domain. Taking a time-space domain vector mining for example, the water ecological time-space domain index vector can be as follows: [ spring Water quality Condition: 0.7, summer water quality status: 0.6, autumn water quality condition: 0.8, winter water quality status: 0.9, upstream zone contamination status: 0.5, downstream zone contamination status: 0.4]. The water ecology time-space domain index vector comprises 6 dimensions, and each dimension is a specific time-space domain index, such as spring water quality condition, upstream area pollution condition and the like. The values of these indicators reflect the ecological environment conditions of the target waters in the time-space domain.

The global water ecology time-space domain index vector is a result obtained by carrying out linkage monitoring index association on the water ecology time-space domain index vector through the environment monitoring index vector. The global water ecology time-space domain index vector not only comprises key indexes on a time-space domain, but also comprises association information between the indexes and the current monitoring condition. Taking a certain linkage monitoring index association as an example, the global water ecology time-space domain index vector can be as follows: [ spring Water quality Condition: 0.75, summer water quality status: 0.65, autumn water quality status: 0.85, winter water quality status: 0.95, upstream zone contamination status: 0.55, downstream zone contamination status: 0.45, association with current monitoring: 0.8]. Compared with the water ecological time-space domain index vector, the global water ecological time-space domain index vector is increased by a dimension of the correlation degree with the current monitoring, and the dimension represents the correlation degree between the time-space domain index and the current monitoring condition.

The global environment monitoring index vector is a result obtained by carrying out linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector. The global environment monitoring index vector not only contains current monitoring data, but also contains background and trend information of the data on a time-space domain. Taking a certain linkage monitoring index association as an example, the global environment monitoring index vector can be as follows: [ Water temperature: 22.5 ℃, pH value: 7.8, dissolved oxygen: 8.5mg/L, turbidity: 12NTU, ammonia nitrogen content: 0.5mg/L, phosphorus content: 0.1mg/L, plankton species: 5, plankton number: 1000/L, time-space domain background information: 0.7, trend information: 0.6].

Compared with the global water ecology time-space domain index vector, the global environment monitoring index vector is increased by two dimensions: time-space domain background information and trend information. These two dimensions provide background and trend information about the current monitored data over the time-space domain, helping to more fully understand the ecological environment conditions of the target waters.

Further, the steps 130 and 140 are core invention points of the embodiments of the present invention, and the steps 130 and 140 convert the original monitoring data and the auxiliary decision information into vector representations with deep insight into the ecological environment of the target water area through complex data processing and algorithm analysis, so as to support more accurate water ecological quality assessment. The following is a detailed description of these two steps.

Step 130 involves dense vector mapping, focusing, and time-space domain vector mining.

(1) Dense vector mapping

The dense vector mapping is the first step of step 130, whose purpose is to convert the evaluation early warning assistant decision information into a dense vector form compatible with the environmental monitoring index vector. The evaluation early warning auxiliary decision information comprises various data such as historical data, policy regulations, ecological protection targets, human activity influence and the like, and the information can be unstructured or semi-structured data such as texts, charts and the like.

To implement the dense vector mapping, the water ecology survey assessment apparatus employs a series of Natural Language Processing (NLP) and machine learning techniques. Firstly, the equipment performs word segmentation, part-of-speech tagging, named entity recognition and other processes on text data through an NLP technology, and extracts key information. The extracted keywords are then converted into dense vectors in high-dimensional space using word embedding (Word Embedding) techniques. For non-text data such as charts, the device then converts it to structured data via image recognition techniques and further to dense vectors.

Finally, the evaluation early warning assistant decision information is converted into one or more dense vectors, each element in the vectors represents a feature or concept in the original information, and the relative positional relationship among the elements reflects the inherent relationship among the features or concepts.

For example, the evaluation early warning auxiliary decision information contains a policy rule that states that the ammonia nitrogen content of the target water area must not exceed 0.5 mg/L. Through NLP processing and word embedding techniques, the policy rule may be converted into a dense vector, such as [0.1,0.2, -0.3, 0.5], where the last element (0.5) of the vector directly corresponds to the threshold of ammonia nitrogen content, while other elements reflect the characteristics of other related concepts in the policy rule.

(2) Dense vector focalization

The dense vector Jiao Dianhua is the second step of step 130, whose purpose is to filter and weight the auxiliary decision dense vector by the environmental monitoring index vector, highlighting the auxiliary decision information most relevant to the current monitoring situation in the target water area. The core of the step is to calculate the similarity or correlation between the environment monitoring index vector and the assistant decision dense vector, and weight the elements in the assistant decision dense vector according to the size of the similarity or correlation.

To implement the dense vector Jiao Dianhua, the water ecology survey assessment apparatus employs an attention mechanism (Attention Mechanism). The attention mechanism is a deep learning technique that simulates the human visual attention process and allows models to pay more attention to important parts in processing information. In this step, the device takes the environmental monitoring index vector as a Query (Query), takes the aid decision dense vector as a Key-Value pair (Key-Value), and assigns an attention weight to each element in the Key-Value pair by calculating a similarity score between the Query and the Key-Value pair.

Finally, each element in the auxiliary decision dense vector is weighted according to the attention weight of the element, so that a focused auxiliary decision attention vector is obtained. The element values in the vector not only reflect the importance degree of the original auxiliary decision information, but also reflect the association degree between the element values and the current monitoring condition of the target water area.

Continuing with the previous policy regulations as an example. The environmental monitoring index vector shows that the ammonia nitrogen content of the current target water area is 0.45mg/L, and is close to but not exceeding a specified threshold (0.5 mg/L). In the process of focusing the dense vector, the equipment calculates a similarity score between the environment monitoring index vector and the auxiliary decision dense vector containing the ammonia nitrogen content threshold value, and distributes higher attention weight to elements related to the ammonia nitrogen content in the auxiliary decision dense vector. Therefore, in the focused auxiliary decision-making attention vector, the element value related to the ammonia nitrogen content is relatively larger, which indicates that the importance of the information under the current monitoring condition is higher.

(3) Time-space domain vector mining

The time-space domain vector mining is the last step of step 130, and aims to perform deep analysis on a time-space domain according to the focused auxiliary decision-making attention vector and extract key indexes of the ecological environment of the target water area on the time-space domain. The step integrates a plurality of technical methods such as time sequence analysis, space statistics analysis, data mining and the like.

In the aspect of time sequence analysis, the device performs trend analysis, periodic analysis, anomaly detection and other operations on the historical monitoring data so as to identify the change rule of the ecological environment of the target water area in the time dimension. In the aspect of space statistical analysis, the device utilizes a Geographic Information System (GIS) technology to perform operations such as space interpolation, space clustering and the like on the monitored data so as to reveal the distribution characteristics and heterogeneity of the ecological environment of the target water area in the space dimension. In addition, the device also adopts a data mining technology to extract hidden modes and knowledge rules from a large amount of monitoring data, and provides powerful support for subsequent evaluation and early warning.

Finally, the equipment obtains an aquatic ecology time-space domain index vector through time-space domain vector mining. The vector contains key index values in multiple dimensions and change trend information of the key index values in time and space. These index values reflect not only the current condition of the target water ecological environment but also the possible future changes thereof.

The water ecological time-space domain index vector obtained after the time-space domain vector is excavated comprises water quality condition index values in four seasons of spring, summer, autumn and winter and pollution condition index values in an upstream area and a downstream area. These index values may show a relatively good spring water quality but a tendency to decline in summer; while the contamination of the upstream area is more severe and the downstream area is relatively light but at risk of diffusion. The information has important guiding significance for formulating targeted ecological protection measures.

Step 140 involves linking the monitor index association with the global vector construction.

(1) Linkage monitoring index association

Linkage monitoring index association is the first step of step 140 and is also one of the core steps. The method aims to establish a linkage monitoring index association model through the interaction relation between the environment monitoring index vector and the water ecology time-space domain index vector so as to obtain a global water ecology time-space domain index vector and a global environment monitoring index vector.

In this step the device first analyzes the internal relationship between the environmental monitoring index vector and the water ecology time-space domain index vector for common points and complementarity between them. And then the equipment adopts advanced data processing technologies such as a Graph Neural Network (GNN) and tensor decomposition (Tensor Factorization) to construct a linkage monitoring index association model. The model can capture complex relations among different monitoring indexes and integrate the complex relations into a unified framework for comprehensive analysis.

Finally, the global water ecology time-space domain index vector and the global environment monitoring index vector are obtained through the linkage monitoring index association model equipment. The two vectors not only contain the original monitoring data and the time-space domain index value, but also reflect the internal relation and the interaction relation between the two vectors, so that a more comprehensive and deep understanding of the ecological environment of the target water area is formed.

The environment monitoring index vector contains a plurality of water quality index values such as water temperature, pH value, dissolved oxygen and the like, and the water ecology time-space domain index vector contains water quality condition index values in different seasons such as spring, summer and different areas such as upstream, downstream and the like. The device analyzes the interaction relationship between these index values, such as the increase of water temperature, in the linkage monitoring index association process may lead to the decrease of dissolved oxygen, while the pollution condition of the upstream area may affect the water quality condition of the downstream area, etc. The complex interaction relations can be integrated into a unified frame for comprehensive analysis by constructing the linkage monitoring index association model equipment, so that the global water ecology time-space domain index vector and the global environment monitoring index vector are obtained. Each element in these vectors represents an important aspect of the target waters ecological environment and the relative positional relationship between the elements reflects the inherent and interactive relationship between them.

(2) Global vector construction

Global vector construction is the last step of step 140 and is also the climax part of the overall solution. In the step, the equipment integrates and optimizes the global water ecology time-space domain index vector and the global environment monitoring index vector to form a comprehensive evaluation result which is more comprehensive, accurate and has guiding significance.

To implement the global vector construction device first performs a normalization process on the two global vectors to ensure comparability between them. And then the equipment adopts data analysis technologies such as multi-criterion decision analysis (MCDA), principal Component Analysis (PCA) and the like to extract key indexes and weight information in the comprehensive evaluation result. These key indicators and weight information not only reflect the overall condition of the target waters ecology environment but also indicate major problems and potential risks present therein.

The end device presents the composite assessment results in a visual form to present the current status, historical trend of change, and possible future risks and challenges of the target water ecological environment to the user, for example, in the form of dashboards, thermodynamic diagrams, or reports. The information has important significance for making scientific and reasonable ecological protection measures and optimizing water resource management decisions.

The comprehensive evaluation result obtained after the global vector construction shows that the current water quality condition of the target water area is generally good but the seasonal eutrophication risk exists, and the pollution condition of the upstream area has a significant influence on the water quality condition of the downstream area. Such information will be presented in visual form on the dashboard, e.g. by means of different colored lights or numbers to indicate the water quality status and pollution level of different seasons and areas, etc. Users can formulate targeted ecological protection measures such as enhancing seasonal eutrophication monitoring and early warning, optimizing pollution source treatment schemes in upstream areas, and the like according to the information so as to ensure long-term stability and green development of the ecological environment of the target water area.

The embodiment of the invention obviously improves the accuracy and efficiency of monitoring and evaluating the ecological environment of the target water area by comprehensively applying advanced data processing and machine learning technologies. Specifically, the embodiment of the invention can acquire comprehensive ecological environment monitoring data and corresponding evaluation early warning auxiliary decision information thereof, so as to identify key environment monitoring index vectors and lay a foundation for accurate analysis. By converting the evaluation early warning auxiliary decision information into a dense vector and carrying out focusing treatment, the embodiment of the invention effectively digs key ecological indexes in the space-time domain and realizes deep understanding of the ecological environment of the water area. Further, through linkage monitoring index association, the embodiment of the invention constructs global water ecology time-space domain index vector and environment monitoring index vector, and provides a comprehensive view angle for comprehensive evaluation. Finally, based on the commonality weight operation, the ecological quality evaluation viewpoint of the target water area can be accurately output, and a powerful scientific basis is provided for ecological protection and management decision, so that the green development of the ecological environment of the water area is assisted.

In some optional embodiments, the identifying the environmental monitoring index vector according to the ecological environment monitoring data of the target water area to obtain the environmental monitoring index vector includes: dividing each ecological environment monitoring data segment from the ecological environment monitoring data of the target water area, and respectively carrying out dense vector mapping on each ecological environment monitoring data segment to obtain each local environment monitoring dense vector; carrying out time-space domain vector mining on the local environment monitoring dense vectors to obtain local time-space domain index vectors; and splicing the local time-space domain index vectors based on the investigation evaluation task to obtain the environment monitoring index vector.

In practical application of the water ecology investigation and evaluation device, detailed and scientific analysis of the ecological environment monitoring data of the target water area is of great importance. In the following, a specific example will be described in detail how the water ecology investigation and evaluation device performs the recognition of the environmental monitoring index vector according to the ecology environment monitoring data of the target water area, and finally obtains the environmental monitoring index vector for comprehensive evaluation.

Firstly, the water ecology investigation and evaluation equipment divides each ecological environment monitoring data segment from the ecological environment monitoring data of the target water area. The purpose of this step is to break down the original, monitored data, which may contain a lot of redundancy and noise, into smaller, more easily handled data segments. Each data segment may correspond to a different monitoring time point, a different monitoring location or a different monitoring index, such segmentation facilitating the pertinence and accuracy of the subsequent analysis.

Next, the device maps the dense vector of each ecological environment monitoring data segment to obtain each local environment monitoring dense vector. Dense vector mapping is a technique that converts high-dimensional sparse data into low-dimensional dense data that enables the data to be more compact and easy to compute while preserving the primary characteristics of the original data. In this step, the device performs feature extraction and vector conversion on each data segment using advanced machine learning algorithms, such as a deep learning network, to obtain a dense vector that reflects the primary ecological environment features of the data segment.

After obtaining the dense vectors of each local environment monitoring, the device further performs time-space domain vector mining on the vectors to obtain each local time-space domain index vector. Time-space domain vector mining is a data analysis method considering time and space factors, and can reveal the change rule of data on different time and space scales. In the step, the device performs depth analysis on the dense vector by using a time-space domain mining algorithm, such as space-time clustering, space-time association rule mining and the like, so as to extract an index vector capable of reflecting the space-time characteristics of the ecological environment of the target water area.

And finally, the equipment performs the splicing based on the investigation evaluation task on each local time-space domain index vector to obtain a final environment monitoring index vector. The purpose of this step is to integrate the local vectors obtained previously into a comprehensive vector that can reflect the overall ecological environment conditions of the target water area. The manner of stitching may be determined based on specific survey assessment tasks, such as stitching may be performed in chronological order, spatial layout, or importance. By means of the splicing, the device can obtain an environment monitoring index vector which contains rich ecological environment information and has clear physical meaning, and a solid foundation is provided for subsequent comprehensive evaluation.

In the whole process, the dense vector mapping and the time-space domain vector mining play key roles. The dense vector mapping enables the original high-dimensional sparse data to be more compact and easier to process, and improves the efficiency of data analysis; and the time-space domain vector mining considers the factors of time and space, so that the analysis result is more comprehensive and deeper.

Therefore, the water ecology investigation and evaluation equipment has obvious beneficial effects in the aspect of environment monitoring index vector identification according to the ecological environment monitoring data of the target water area. Firstly, by dividing the ecological environment monitoring data segment and performing dense vector mapping, the device can effectively extract main features in the data, remove redundancy and noise, and enable subsequent analysis to be more accurate and efficient. This step not only improves the efficiency of data processing, but also provides a high quality input for subsequent deep analysis. And secondly, through time-space domain vector mining, the equipment can reveal the change rules of the ecological environment of the target water area on different time and space scales, so that the analysis result is more comprehensive and deeper. The space-time characteristics of the ecological environment data are considered in the step, so that the obtained environment monitoring index vector is more representative and explanatory. Finally, by splicing based on investigation evaluation tasks, the device can integrate each local time-space domain index vector into a comprehensive environment monitoring index vector, and a solid foundation is provided for subsequent comprehensive evaluation. The step enables the analysis result to better meet the requirements of practical application, and improves the accuracy and reliability of evaluation. In summary, the water ecology investigation and evaluation device realizes comprehensive, deep and accurate analysis of the ecological environment data by dividing the data segments, mapping the dense vectors, mining the time-space vectors, splicing the task-based data and the like in the aspect of carrying out environment monitoring index vector recognition according to the ecological environment monitoring data of the target water area. The method not only improves the efficiency and quality of data analysis, but also provides powerful support for subsequent ecological environment assessment and decision-making. Therefore, the technical scheme has wide application prospect and important practical value in the field of water ecological investigation and evaluation.

In other optional embodiments, the performing, by the environmental monitoring index vector, dense vector focusing on the auxiliary decision dense vector to obtain an auxiliary decision attention vector includes: carrying out residual connection processing on the environment monitoring index vector to obtain environment monitoring residual characteristics; and integrating the environment monitoring residual characteristics with the auxiliary decision dense vector to obtain the auxiliary decision attention vector.

In practice, the apparatus performs a complex and elaborate series of data processing and analysis steps in order to more accurately mine and interpret the ecological conditions of the target water area. The process of performing the dense vector Jiao Dianhua on the auxiliary decision dense vector through the environment monitoring index vector to obtain the auxiliary decision attention vector is an important embodiment of the core function of the device. Details of the implementation of this process will be set forth in detail below.

Firstly, the equipment performs residual connection processing on the environment monitoring index vector to obtain environment monitoring residual characteristics. Residual connection is a widely used technique in the field of deep learning, which helps the network learn the difference between the input and the output, i.e. the residual, by adding the input to the output of a layer. This approach can enhance the feature extraction capabilities of the network, enabling the network to focus more on subtle changes in the input data. In the application scene of the water ecology investigation and evaluation equipment, the environment monitoring index vector contains rich ecological environment information of a target water area, key characteristics in the information, namely environment monitoring residual characteristics, can be extracted by the equipment through residual connection processing, and the characteristics reflect the uniqueness and the variability of the ecological environment of the water area.

Next, the device integrates the environmental monitoring residual feature with the auxiliary decision dense vector to obtain an auxiliary decision attention vector. The auxiliary decision dense vector is obtained by the equipment after dense vector mapping according to the evaluation early warning auxiliary decision information, and contains key information for auxiliary decision. However, the vector may not exactly match the current ecological environment conditions of the target waters. Thus, the device needs to integrate the environmental monitoring residual features with it in order to make corrections and adjustments to the auxiliary decision dense vector. The way of integration may be simple vector addition, stitching or more complex deep learning fusion methods. Through integration, the device can obtain an auxiliary decision-making attention vector which is closer to the current ecological environment condition of the target water area. The vector not only contains key information for assisting decision making, but also integrates real-time data of environment monitoring, so that the vector has higher accuracy and reliability.

In a specific implementation, the water ecology survey and evaluation device utilizes advanced machine learning algorithms and deep learning models to perform the above steps. For example, the device may use a deep learning model such as a Convolutional Neural Network (CNN) or a Recurrent Neural Network (RNN) to perform feature extraction and residual connection processing on the environmental monitoring index vector. Meanwhile, the device can effectively integrate the environment monitoring residual characteristics with the auxiliary decision dense vector by using advanced technologies such as an attention mechanism and the like so as to obtain a more accurate auxiliary decision attention vector.

Thus, the water ecology investigation and evaluation device has obvious technical advantages and practical application value in the aspect of carrying out dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector. Firstly, through residual connection processing, the equipment can extract key features in the environment monitoring index vector, namely environment monitoring residual features. These features reflect the uniqueness and variability of the water ecological environment and provide more accurate and comprehensive information for subsequent auxiliary decisions. And secondly, by integrating the environment monitoring residual characteristics with the auxiliary decision dense vector, the device can obtain an auxiliary decision attention vector which is closer to the current ecological environment condition of the target water area. The vector not only contains key information for assisting decision making, but also integrates real-time data of environment monitoring, so that the vector has higher accuracy and reliability. This provides a powerful support for subsequent ecological assessment and decision making. Finally, by performing the above steps using advanced machine learning algorithms and deep learning models, the water ecological investigation and evaluation apparatus achieves comprehensive, deep and accurate analysis of the ecological environment data. The method not only improves the efficiency and quality of data analysis, but also provides powerful technical support for the protection of biological environment and the development of green.

In summary, in the aspect of carrying out the dense vector Jiao Dianhua on the auxiliary decision dense vector through the environment monitoring index vector, the water ecological investigation and evaluation device realizes the accurate analysis and auxiliary decision support on the ecological environment data through the steps of residual connection processing, integrating the environment monitoring residual characteristics with the auxiliary decision dense vector and the like, and improves the accuracy and reliability of ecological environment evaluation and decision.

Under a preferred design thought, the performing linkage monitoring index association on the water ecology time-space domain index vector through the environment monitoring index vector to obtain a global water ecology time-space domain index vector comprises the following steps: performing characteristic focusing coefficient operation according to the water ecological time-space domain index vector and the environment monitoring index vector to obtain a characteristic focusing coefficient; performing characteristic reinforcement on the environment monitoring index vector through the characteristic focusing coefficient to obtain a first environment monitoring focusing vector; and combining the first environment monitoring focusing vector and the water ecology time-space domain index vector to obtain the global water ecology time-space domain index vector.

Under the design thought, the process of carrying out linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector so as to obtain the global water ecological time-space domain index vector is an important embodiment of the core invention point of the embodiment of the invention.

Firstly, the equipment performs characteristic focusing coefficient operation according to the water ecological time-space domain index vector and the environment monitoring index vector, so as to obtain the characteristic focusing coefficient. The feature focusing factor is an index that measures the degree of association between two vectors and the importance of the feature. In the context of water ecology survey assessments, the coefficients can reflect which features in the environmental monitoring index vector are most relevant or important to features in the water ecology time-space domain index vector. To calculate the coefficients, the device may employ a complex series of mathematical operations including, but not limited to, vector dot product, cosine similarity calculation, or more advanced machine learning algorithms. Through the operations, the device can quantify the association degree between each feature in the environment monitoring index vector and the water ecology time-space domain index vector, and further obtain the feature focusing coefficient.

And then, the device performs characteristic reinforcement on the environment monitoring index vector through the characteristic focusing coefficient to obtain a first environment monitoring focusing vector. Feature enhancement is a process of adjusting the weights of features in a vector based on the feature focusing coefficients. In this process, the device increases the weights of those features that are highly correlated to the water ecological time-space domain indicator vector, while decreasing the weights of those features that are less correlated. Thus, the first environmental monitoring focusing vector focuses more on the features which are most important to the water ecological time-space domain index vector. This method of feature enhancement helps to improve the accuracy and effectiveness of subsequent analysis, as it ensures that those features that are most important are of greater concern in subsequent analysis.

Finally, the device combines the first environment monitoring focusing vector and the water ecology time-space domain index vector to obtain a global water ecology time-space domain index vector. The combining process may be a simple vector addition, stitching or more complex fusion method, depending on the technology and algorithm employed by the device. Through the process, the equipment can integrate the key characteristic information in the first environment monitoring focusing vector into the water ecology time-space domain index vector, so that a global water ecology time-space domain index vector which is more comprehensive and accurate and contains rich information is obtained. The vector not only contains the original information of the water ecological time-space domain index vector, but also integrates the key characteristics in the environment monitoring index vector, so that the ecological environment condition of the target water area can be reflected more comprehensively.

In an implementation, the water ecology survey assessment apparatus may utilize advanced machine learning algorithms and deep learning models to perform the above steps. For example, the device may use a neural network model to perform the computation of the feature focusing coefficients and the feature enhancement process. Meanwhile, the equipment can also adopt some optimization algorithms to ensure the calculation efficiency and accuracy of the whole process.

Therefore, the water ecology investigation and evaluation equipment has obvious technical advantages and practical application value in the aspect of carrying out linkage monitoring index association on the water ecology time-space domain index vector through the environment monitoring index vector. Firstly, through calculation of the characteristic focusing coefficient, the equipment can accurately quantify the association degree between the environment monitoring index vector and the water ecology time-space domain index vector, so that the most important characteristic is identified. This provides powerful support for subsequent analysis and decision making. Second, by the feature enhancement process, the device can ensure that those features that are most important are of greater concern in subsequent analysis. This helps to increase the accuracy and effectiveness of the analysis, as the device can focus more on those features that are most important for the water ecological time-space domain index vector. Finally, by combining the first environment monitoring focusing vector and the water ecology time-space domain index vector, the device can obtain a global water ecology time-space domain index vector which is more comprehensive and accurate and contains rich information. The vector not only contains the original information of the water ecological time-space domain index vector, but also integrates the key characteristics in the environment monitoring index vector. This provides a powerful technical support for the overall assessment and development of ecological environments.

Therefore, the water ecology investigation and evaluation equipment realizes comprehensive, deep and accurate analysis of the ecological environment data through the steps of calculation of the characteristic focusing coefficient, characteristic reinforcement, vector combination and the like in the aspect of carrying out linkage monitoring index association on the water ecology time-space domain index vector through the environment monitoring index vector. This not only improves the accuracy and reliability of ecological environment assessment and decision making, but also makes an important contribution to the protection and development of the ecological environment. Therefore, the technical scheme has wide application prospect and important practical value in the field of water ecological investigation and evaluation.

Under other preferred design ideas, the performing linkage monitoring index association on the environmental monitoring index vector through the water ecological time-space domain index vector to obtain a global environmental monitoring index vector comprises: performing characteristic focusing coefficient operation according to the water ecological time-space domain index vector and the environment monitoring index vector to obtain a characteristic focusing coefficient; carrying out characteristic reinforcement on the water ecological time-space domain index vector through the characteristic focusing coefficient to obtain a second environment monitoring focusing vector; and combining the second environment monitoring focusing vector and the environment monitoring index vector to obtain the global environment monitoring index vector.

When the embodiment of the water ecology investigation and evaluation equipment is thoroughly discussed, firstly, the equipment aims to comprehensively and accurately monitor and evaluate the health condition of the water ecology system, and provides scientific basis for environmental protection and water resource management. In the following, how to realize the construction of the global environment monitoring index vector through the linkage of the water ecological time-space domain index vector and the environment monitoring index vector, thereby improving the accuracy and the comprehensiveness of monitoring and evaluation.

Firstly, the water ecology investigation and evaluation equipment collects a large amount of water ecology time-space domain index vector data which cover various ecology parameters of the water body under different time and space dimensions, such as water temperature, pH value, dissolved oxygen content, plankton types and quantity and the like. Meanwhile, the equipment can also collect environment monitoring index vectors in real time, wherein the environment monitoring index vectors comprise basic information such as water quality pollutant concentration, water flow speed, water depth and the like. In order to realize the effective linkage of the two, an advanced characteristic focusing coefficient operation algorithm is embedded in the device. The algorithm is characterized in that the internal relation between the water ecology time-space domain index vector and the environment monitoring index vector is analyzed through a mathematical model, and the ecological parameters which have obvious influence on the environment monitoring index, namely 'characteristic focusing' is identified. This process is analogous to finding key features in complex datasets to more accurately predict or interpret target variables. The characteristic focusing factor is an index for quantifying the influence degree, and the higher the value is, the greater the influence of the ecological parameter on the environment monitoring index is.

After the characteristic focusing coefficients are obtained, the water ecology investigation and evaluation equipment uses the coefficients to carry out characteristic strengthening treatment on the water ecology time-space domain index vector. In particular, the device increases the weights in the data analysis for those ecological parameters that have high characteristic focusing coefficients, while relatively decreasing the weights for other parameters, thereby generating a second environmental monitoring focus vector. The step is equivalent to carrying out focusing treatment on the data, so that the ecological parameters which have important influence on the environmental monitoring index are more prominent, and the subsequent analysis and decision are facilitated.

Finally, the water ecology investigation and evaluation equipment combines the second environment monitoring focusing vector with the original environment monitoring index vector, and forms a global environment monitoring index vector through a series of complex data fusion and processing technologies. The process not only keeps all information of the environment monitoring index vector, but also enhances the importance of the monitoring index closely related to the water ecological time-space domain in a characteristic focusing mode, so that the global environment monitoring index vector can more comprehensively and accurately reflect the actual condition of the water ecological system.

Through the design, key factors which have important influence on environmental monitoring indexes in the water ecological system can be more accurately identified through the characteristic focusing coefficient operation and the characteristic strengthening treatment, so that the accuracy of monitoring data and the reliability of analysis results are improved. The construction of the global environment monitoring index vector not only comprises the traditional environment monitoring index, but also integrates the water ecological time-space domain information subjected to characteristic focusing treatment, so that the monitoring and evaluation work can cover wider water ecological parameters and more comprehensively reflect the health condition of the water ecological system. The introduction of the characteristic focusing coefficient makes the data processing process more efficient, avoids the condition of blindly searching key information in a large amount of data, and effectively improves the efficiency of data analysis and decision support. Based on the monitoring evaluation result of the global environment monitoring index vector, a more scientific and comprehensive basis can be provided for water ecological management, thereby being beneficial to formulating more accurate and effective protection measures and management strategies and promoting the development of a water ecological system. Therefore, by optimizing the linkage monitoring mechanism of the water ecology time-space domain index vector and the environment monitoring index vector, the water ecology investigation and evaluation equipment not only improves the accuracy and the comprehensiveness of monitoring and evaluation, but also remarkably improves the data processing efficiency, provides powerful technical support for water ecology management, and has important significance for promoting the continuous utilization of water resources and the protection of ecological environment.

In the next step, the step of performing a commonality weight operation according to the global environmental monitoring index vector and the global water ecology time-space domain index vector to obtain a target commonality weight, and determining a target water ecology quality evaluation viewpoint corresponding to the ecological environmental monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information comprises the following steps: based on the global environment monitoring index vector and the global water ecology time-space domain index vector, obtaining a commonality identification feature; and performing interval weight conversion on the commonality identification features to obtain the target commonality weight, and taking the water ecological quality evaluation viewpoint corresponding to the evaluation early warning auxiliary decision information as the target water ecological quality evaluation viewpoint corresponding to the ecological environment monitoring data of the target water area when the target commonality weight is greater than the set commonality weight.

The above embodiment focuses on how the device performs the commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector, and finally determines the target water ecology quality evaluation view corresponding to the ecological environment monitoring data of the target water area. The process not only embodies the advanced data processing capability of the device, but also highlights the practical value of the device in complex water ecological system evaluation.

In detail, the water ecology investigation and evaluation equipment firstly extracts the commonality recognition characteristics after obtaining the global environment monitoring index vector and the global water ecology time-space domain index vector. The core of this step is to identify key features of the water ecosystem state that are commonly represented in the two sets of vectors. The commonality-identifying features may include, but are not limited to, a prevalent concentration level of a particular contaminant in the body of water, a distribution and abundance of key species in the water ecosystem, a pattern of consistency of the response of the water ecosystem under particular space-time conditions, and the like. The process of extracting common identification features involves complex data mining and pattern recognition techniques. The device uses an algorithm to analyze the data points in the two sets of vectors and find features that exhibit similar trends or states at different environmental monitoring indicators and water ecology time-space domain indicators. For example, if the water temperature, pH and dissolved oxygen content of an area all exhibit seasonal variation rules at multiple monitoring points, and such rules are closely related to certain water ecology time-space domain indicators (e.g., seasonal changes, rainfall), then these characteristics may be identified as commonality identification characteristics.

Once the commonality identifying features are extracted, the water ecology survey evaluation apparatus subjects these features to interval weight conversion to generate target commonality weights. Interval weight conversion is a process of quantifying the relative importance of commonality identifying features into specific values. The process involves mapping the eigenvalues into a predetermined weight interval, where higher eigenvalues correspond to higher weights, and vice versa. The target commonality weight is a single numerical value obtained by comprehensively considering the global environment monitoring index and the global water ecology time-space domain index, and reflects the degree of agreement between the current water ecology system state and the commonality identification characteristic. The higher the weight, the more the current state of the water ecosystem will be indicative of those features that are considered critical or commonality, suggesting a particular problem or trend that the water ecosystem may face.

Finally, the water ecological investigation and evaluation equipment compares the target commonality weight with a preset setting commonality weight to determine a target water ecological quality evaluation viewpoint corresponding to the ecological environment monitoring data of the target water area. The commonality weight is set as a threshold value for judging whether the current state of the water ecological system is enough to significantly represent the commonality identification feature, so that attention is required or corresponding measures are required. If the target commonality weight is greater than the set commonality weight, the equipment takes the water ecological quality evaluation viewpoint in the evaluation early warning auxiliary decision information associated with the target commonality weight as a final target water ecological quality evaluation viewpoint. This means that based on comprehensive environmental monitoring and water ecology time-space analysis, the device has identified key commonality features in the water ecosystem, and these features indicate that the water ecosystem may be in a particular state or facing a particular challenge. Thus, the evaluation viewpoint provided by the device is used as an important basis for decision support to guide relevant institutions or personnel to take appropriate ecological protection or management measures.

In this way, firstly, through the extraction of the commonality identification features and the interval weight conversion, the device can reveal key features which are ubiquitous across space-time and index in the complex water ecological system in a systematic and quantitative mode. This not only enhances the interpretation of the monitored data, but also provides a more solid basis for subsequent evaluation and decision making. And secondly, the introduction of the target commonality weight provides a comprehensive and comparable measurement standard for the state of the water ecological system. The standard not only considers the change of a single monitoring index, but also integrates the multidimensional information of the water ecology time-space domain, thereby improving the accuracy and the comprehensiveness of the evaluation. Furthermore, by combining the evaluation early warning auxiliary decision information with the target commonality weight, the device can directly provide targeted evaluation views and management suggestions while identifying potential problems or trends of the water ecological system. The instant and accurate decision support has important significance for timely coping with water ecological crisis, protecting water resources and ecological environment. Therefore, the water ecology investigation and evaluation equipment not only improves the technical level of monitoring and evaluation of the water ecology system, but also provides a more scientific and efficient tool for protecting and managing the ecological environment through the determination of the commonality weight operation and the target water ecology quality evaluation viewpoint. Therefore, the method is hopeful to promote the deep development of protection work of the water ecological system, and provides powerful support for realizing continuous utilization of water resources and long-term stabilization of ecological environment.

In some examples, the evaluation early warning assistance decision information includes at least two, the method further comprising: performing dense vector mapping on the at least two evaluation early warning auxiliary decision information to obtain at least two auxiliary decision dense vectors, and performing dense vector Jiao Dianhua on the at least two auxiliary decision dense vectors through the environment monitoring index vector to obtain at least two auxiliary decision attention vectors, and performing time-space domain vector mining on the at least two auxiliary decision attention vectors to obtain at least two water ecological time-space domain index vectors; the environment monitoring index vectors are respectively used for carrying out linkage monitoring index association on the at least two water ecology time-space domain index vectors to obtain at least two global water ecology time-space domain index vectors, and the environment monitoring index vectors are respectively used for carrying out linkage monitoring index association on the at least two water ecology time-space domain index vectors to obtain at least two global environment monitoring index vectors; and carrying out common weight operation on the at least two global water ecology time-space domain index vectors and the corresponding global environment monitoring index vectors in the at least two global environment monitoring index vectors respectively to obtain target common weights of the at least two evaluation early warning auxiliary decision information and the ecological environment monitoring data of the target water area respectively, and determining the current water ecology quality evaluation viewpoint corresponding to the ecological environment monitoring data of the target water area according to the target common weights and the at least two evaluation early warning auxiliary decision information.

In the application scenario of the water ecology investigation and evaluation device, the evaluation early warning auxiliary decision information can comprise multiple aspects, such as water pollution early warning, ecological diversity protection suggestion, water flow dynamic change analysis and the like. In order to integrate these information effectively, the device first performs dense vector mapping on these evaluation early warning assistant decision information.

Dense vector mapping is a technique that converts text or discrete data into dense vectors in a continuous vector space. The purpose of this step is to convert the key content and semantics in the evaluation pre-warning aid decision information into a numerical form that can be processed by the device algorithm. Through dense vector mapping, each evaluation early warning assistant decision information is converted into an assistant decision dense vector, and the vectors preserve the semantics and the context relation of the original information in a vector space. Next, the device performs dense vector focalization on the auxiliary decision dense vector using the environmental monitoring index vector. This process is similar to the application of attention mechanisms in deep learning, which allows the device to "focus" on those parts of the auxiliary decision information that are closely related to the environmental monitoring metrics. By focusing, the device is able to generate auxiliary decision attention vectors that are more focused on key auxiliary decision information under the current environmental monitoring indicators.

After the auxiliary decision attention vectors are obtained, the water ecology investigation and evaluation equipment further performs time-space domain vector mining on the vectors. Time-space domain vector mining is a technique that analyzes data distribution and pattern of variation in both time and space dimensions. Through the step, the equipment can extract key characteristics of the water ecological time-space domain, such as seasonal variation, geographic distribution, long-term trend and the like, from the auxiliary decision-making attention vector. The mined time-space domain features are used to generate water ecological time-space domain index vectors reflecting the key performance of the evaluation early warning auxiliary decision information on the time-space domain. And then, the equipment obtains the global water ecology time-space domain index vector through the linkage monitoring index association of the environment monitoring index vector and the water ecology time-space domain index vector. The process realizes the deep fusion of the environment monitoring index and the time-space domain characteristics, so that the global vector more comprehensively reflects the actual condition of the water ecological system. Meanwhile, the equipment also utilizes the water ecological time-space domain index vector to carry out linkage monitoring index association on the environment monitoring index vector so as to obtain a global environment monitoring index vector. The step further enhances the time-space domain characteristics of the environment monitoring index vector, so that the global vector integrates the key information of the time-space domain while retaining the original monitoring information.

And finally, the water ecology investigation and evaluation equipment performs commonality weight operation on the global water ecology time-space domain index vector and the corresponding global environment monitoring index vector. The commonality weight operation is a method of quantifying commonality and variability between two sets of vectors. Through the operation, the equipment can obtain the target commonality weight between each evaluation early warning auxiliary decision information and the target water ecological environment monitoring data. The target commonality weight reflects the degree of agreement between the evaluation early warning auxiliary decision information and the current water ecological system state. The higher the weight is, the more the assessment early warning auxiliary decision information can accurately reflect the key characteristics and potential problems of the current water ecological system. According to the target commonality weight and the evaluation early warning auxiliary decision information, the water ecology investigation evaluation equipment can determine the current water ecology quality evaluation view corresponding to the ecological environment monitoring data of the target water area. The view is obtained by integrating a plurality of evaluation early warning auxiliary decision information and environment monitoring indexes, so that the actual condition of the water ecological system is reflected more comprehensively and accurately.

So designed, first, through dense vector mapping and dense vector focusing, the device can effectively integrate and process multiple assessment early warning auxiliary decision information, so that the information can more fully play a role in subsequent analysis and decision. And secondly, the time-space domain vector is mined and the global vector is constructed, so that the equipment can comprehensively and deeply analyze the condition of the water ecological system in two dimensions of time and space, and the accuracy and the comprehensiveness of monitoring and evaluation are improved. Finally, through the common weight operation and the determination of the target water ecological quality evaluation viewpoint, the device can provide a comprehensive and quantitative evaluation result, and the result not only reflects the actual condition of the current water ecological system, but also provides scientific and effective decision support for subsequent ecological protection and management. Therefore, the embodiment of the water ecology investigation evaluation device in the aspect of processing a plurality of evaluation early warning auxiliary decision information not only improves the technical level and application capacity of the device, but also provides more comprehensive and accurate support for the protection and management of the water ecology system.

In an alternative embodiment, the method further comprises: the ecological environment monitoring data of the target water area and corresponding evaluation early warning auxiliary decision information are input into a target water ecological investigation evaluation algorithm, and environment monitoring index vector identification is carried out on the ecological environment monitoring data of the target water area through the target water ecological investigation evaluation algorithm, so that environment monitoring index vectors are obtained; performing dense vector mapping on the evaluation early warning auxiliary decision information through the target water ecology investigation evaluation algorithm to obtain an auxiliary decision dense vector, performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and performing time-space domain vector mining according to the auxiliary decision attention vector to obtain a water ecology time-space domain index vector; performing linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector by the target water ecological investigation evaluation algorithm to obtain a global water ecological time-space domain index vector, and performing linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain a global environment monitoring index vector; and carrying out commonality weight operation on the global environment monitoring index vector and the global water ecology time-space domain index vector through the target water ecology investigation evaluation algorithm to obtain target commonality weight, and determining a target water ecology quality evaluation view corresponding to the ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information.

In this embodiment, first, the water ecology survey evaluation apparatus enters ecology environment monitoring data of a target water area into a target water ecology survey evaluation algorithm. Such monitoring data may include real-time or historical data for various aspects of water temperature, water quality, dissolved oxygen content, water flow rate, etc. Then, the target water ecology investigation and evaluation algorithm can perform environment monitoring index vector identification on the ecological environment monitoring data. The purpose of this step is to convert the raw monitoring data into a numerical vector form that can be efficiently processed by the algorithm, i.e., an environmental monitoring index vector. Each element corresponds to a specific environment monitoring index in the vector, and key characteristics and variation trend of the original data are reserved.

Meanwhile, the water ecology investigation evaluation equipment also inputs corresponding evaluation early warning auxiliary decision information into a target water ecology investigation evaluation algorithm. Such information may include expert advice, analysis of historical cases, predictive results of models, etc. to aid in assessing the condition of the hydro-ecosystem. The algorithm will map the dense vector of these evaluation early warning aid decision information. Dense vector mapping is a technique that converts text or discrete data into continuous vectors in a high-dimensional space. Through this step, each evaluation early warning assistant decision information is converted into an assistant decision dense vector which preserves the semantics and context of the original information in vector space. The algorithm then uses the previously obtained environmental monitoring index vector to focus the decision-aid dense vector. Focusing is a mechanism of attention that allows algorithms to "focus" on those parts of the auxiliary decision information that are closely related to environmental monitoring metrics. Through Jiao Dianhua, the algorithm can generate auxiliary decision attention vectors that are more focused on critical auxiliary decision information under the current environmental monitoring metrics.

After the auxiliary decision-making attention vectors are obtained, the target water ecology investigation and evaluation algorithm of the water ecology investigation and evaluation equipment can further conduct time-space domain vector mining on the vectors. Time-space domain vector mining is a technique that analyzes data distribution and pattern of variation in both time and space dimensions. Through the step, the algorithm can extract key characteristics of the water ecological time-space domain, such as seasonal variation, geographic distribution, long-term trend and the like, from the auxiliary decision-making attention vector. The mined time-space domain features are used to generate water ecological time-space domain index vectors reflecting the key performance of the evaluation early warning auxiliary decision information on the time-space domain. Then, the algorithm obtains the global water ecology time-space domain index vector through the linkage monitoring index association of the environment monitoring index vector and the water ecology time-space domain index vector. The process realizes the deep fusion of the environment monitoring index and the time-space domain characteristics, so that the global vector more comprehensively reflects the actual condition of the water ecological system. Meanwhile, the algorithm also utilizes the water ecological time-space domain index vector to carry out linkage monitoring index association on the environment monitoring index vector so as to obtain a global environment monitoring index vector. The step further enhances the time-space domain characteristics of the environment monitoring index vector, so that the global vector integrates the key information of the time-space domain while retaining the original monitoring information.

Finally, the target water ecology investigation and evaluation algorithm of the water ecology investigation and evaluation equipment can carry out commonality weight operation on the global environment monitoring index vector and the global water ecology time-space domain index vector. The commonality weight operation is a method of quantifying commonality and variability between two sets of vectors. Through the operation, the algorithm can obtain the target commonality weight between the evaluation early warning auxiliary decision information and the target water area ecological environment monitoring data. The target commonality weight reflects the degree of agreement between the evaluation early warning auxiliary decision information and the current water ecological system state. The higher the weight is, the more the assessment early warning auxiliary decision information can accurately reflect the key characteristics and potential problems of the current water ecological system. According to the target commonality weight and the evaluation early warning auxiliary decision information, the water ecology investigation evaluation equipment can determine a target water ecology quality evaluation viewpoint corresponding to the ecology environment monitoring data of the target water area. The view is obtained by integrating a plurality of evaluation early warning auxiliary decision information and environment monitoring indexes, so that the actual condition of the water ecological system is reflected more comprehensively and accurately.

By means of the design, firstly, through application of the target water ecology investigation evaluation algorithm, the device can effectively integrate and process ecological environment monitoring data of a target water area and corresponding evaluation early warning auxiliary decision information, and therefore the information can fully play a role in subsequent analysis and decision. This not only improves the efficiency of data processing, but also enhances the accuracy and comprehensiveness of the evaluation result. Secondly, through a series of steps of dense vector mapping, dense vector Jiao Dianhua, time-space domain vector mining, global vector construction, etc., the device can deeply analyze and mine the condition of the water ecosystem from multiple dimensions and layers. The method not only enables the evaluation result to be finer and more accurate, but also provides more comprehensive and scientific data support for subsequent ecological protection and management. Finally, the device can provide a comprehensive and quantized evaluation result through common weight operation and determination of the target water ecological quality evaluation viewpoint. The result not only reflects the actual condition of the current water ecological system, but also provides clear and effective decision basis for subsequent ecological protection and management. The method has important significance for promoting the further development of the protection work of the water ecological system, realizing the continuous utilization of water resources and maintaining the long-term stability of the ecological environment.

In other alternative embodiments, the target water ecological investigation and evaluation algorithm comprises an environmental monitoring index mining branch, an auxiliary decision mining branch, a linkage monitoring index association branch and a commonality weight operation branch; the recording of the ecological environment monitoring data of the target water area and the corresponding evaluation early warning auxiliary decision information into a target water ecological investigation evaluation algorithm comprises the following steps: recording the ecological environment monitoring data of the target water area into the environment monitoring index mining branch to identify environment monitoring index vectors, so as to obtain environment monitoring index vectors; recording the evaluation early warning auxiliary decision information into the auxiliary decision mining branch for dense vector mapping to obtain an auxiliary decision dense vector, carrying out dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and carrying out time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic ecological time-space domain index vector; the environment monitoring index vector and the water ecological time-space domain index vector are input into the linkage monitoring index association branch, the water ecological time-space domain index vector is subjected to linkage monitoring index association through the environment monitoring index vector by the linkage monitoring index association branch to obtain a global water ecological time-space domain index vector, and the environment monitoring index vector is subjected to linkage monitoring index association through the water ecological time-space domain index vector to obtain a global environment monitoring index vector; and recording the global environment monitoring index vector and the global water ecology time-space domain index vector into the commonality weight operation branch to perform commonality weight operation, so as to obtain target commonality weight, and determining a target water ecology quality evaluation view corresponding to the ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information.

In this embodiment, the target water ecology investigation evaluation algorithm employed by the water ecology investigation evaluation device is innovatively designed to include four core branches: an environment monitoring index mining branch, an auxiliary decision mining branch, a linkage monitoring index association branch and a commonality weight operation branch. The four branches work cooperatively to complete the deep analysis and comprehensive evaluation of the ecological environment monitoring data and the corresponding evaluation early warning auxiliary decision information of the target water area.

Firstly, the water ecology investigation and evaluation equipment inputs ecological environment monitoring data of a target water area into an environment monitoring index mining branch. The purpose of this step is to perform depth mining and feature extraction on the original monitoring data, and convert it into a numerical vector form that can be effectively processed by the algorithm, i.e. an environmental monitoring index vector. Each element corresponds to a specific environmental monitoring index such as water temperature, water quality, dissolved oxygen content and the like in the vector, and key characteristics and variation trend of the original data are reserved. The conversion process not only improves the processing efficiency of the data, but also provides a more accurate and comprehensive data basis for subsequent analysis and decision.

Meanwhile, the water ecological investigation evaluation equipment also inputs corresponding evaluation early warning auxiliary decision information into an auxiliary decision mining branch. Such information may include expert advice, analysis of historical cases, predictive results of models, etc., which have important reference value for aiding in assessing the condition of the water ecosystem. In the auxiliary decision mining branch, the algorithm performs dense vector mapping on the evaluation early warning auxiliary decision information. Dense vector mapping is an advanced natural language processing technique that is capable of converting text or discrete data into continuous vectors in high-dimensional space. Through the step, each evaluation early warning assistant decision information is converted into an assistant decision dense vector, the vectors keep the semantics and the context relation of the original information in a vector space, and a richer information basis is provided for subsequent analysis and decision.

Next, the water ecology survey evaluation apparatus performs dense vector focusing on the auxiliary decision dense vector using the environmental monitoring index vector obtained previously. Focusing is a mechanism of attention that allows algorithms to "focus" on those parts of the auxiliary decision information that are closely related to environmental monitoring metrics. Through Jiao Dianhua, the algorithm can generate auxiliary decision attention vectors which are focused on key auxiliary decision information under the current environment monitoring index, so that the accuracy and pertinence of subsequent analysis are improved.

After the auxiliary decision-making attention vectors are obtained, the target water ecology investigation and evaluation algorithm of the water ecology investigation and evaluation device can further conduct time-space domain vector mining on the vectors. Time-space domain vector mining is an advanced data analysis technique that is capable of analyzing the distribution and variation patterns of data in both time and space dimensions. Through the step, the algorithm can extract key characteristics of the water ecological time-space domain, such as seasonal variation, geographic distribution, long-term trend and the like, from the auxiliary decision-making attention vector. These features have important reference values for a comprehensive understanding of the condition of the water ecosystem and its trend of variation.

The mined time-space domain features are used to generate water ecological time-space domain index vectors reflecting the key performance of the evaluation early warning auxiliary decision information on the time-space domain. Then, the water ecology investigation and evaluation equipment inputs the environment monitoring index vector and the water ecology time-space domain index vector into the linkage monitoring index association branch. The aim of the branch is to realize the deep fusion of the environment monitoring index and the time-space domain characteristics, so that the global vector more comprehensively reflects the actual condition of the water ecological system. Through the processing of the linkage monitoring index association branch, the algorithm can obtain the global water ecological time-space domain index vector and the global environment monitoring index vector. The two global vectors not only keep key characteristics of original monitoring information and auxiliary decision information, but also integrate important information of a time-space domain, and provide a more comprehensive and accurate data basis for subsequent comprehensive evaluation and decision.

Finally, the water ecology investigation and evaluation equipment inputs the global environment monitoring index vector and the global water ecology time-space domain index vector into a common weight operation branch to perform common weight operation. The commonality weight operation is a method of quantifying commonality and variability between two sets of vectors. Through the operation, the algorithm can obtain the target commonality weight between the evaluation early warning auxiliary decision information and the target water area ecological environment monitoring data. The target commonality weight reflects the degree of agreement between the evaluation early warning auxiliary decision information and the current water ecological system state. The higher the weight is, the more the assessment early warning auxiliary decision information can accurately reflect the key characteristics and potential problems of the current water ecological system.

According to the target commonality weight and the evaluation early warning auxiliary decision information, the water ecology investigation evaluation equipment can determine a target water ecology quality evaluation viewpoint corresponding to the ecology environment monitoring data of the target water area. The view is obtained by integrating a plurality of evaluation early warning auxiliary decision information and environment monitoring indexes, so that the actual condition of the water ecological system is reflected more comprehensively and accurately. Meanwhile, the view is obtained based on common weight operation, so that the view has higher objectivity and accuracy, and can provide powerful data support and decision basis for subsequent ecological protection and management.

Therefore, the aquatic ecology investigation and evaluation equipment can effectively integrate and process ecological environment monitoring data of a target water area and corresponding evaluation early warning auxiliary decision information thereof by adopting a target aquatic ecology investigation and evaluation algorithm comprising an environment monitoring index mining branch, an auxiliary decision mining branch, a linkage monitoring index association branch and a commonality weight operation branch. The method not only improves the efficiency and quality of data processing, but also provides more comprehensive and scientific data support and decision basis for subsequent ecological protection and management. The method has important significance for promoting the further development of the protection work of the water ecological system, realizing the continuous utilization of water resources and maintaining the long-term stability of the ecological environment.

In some example embodiments, the auxiliary decision mining branch includes a dense vector mapping module, a dense vector focalization module, and a time-space domain vector mining module; the step of inputting the evaluation early warning auxiliary decision information into the auxiliary decision mining branch to carry out dense vector mapping to obtain an auxiliary decision dense vector, carrying out dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, carrying out time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic attitude time-space domain index vector, and comprising the following steps: inputting the evaluation early warning auxiliary decision information into the dense vector mapping module to carry out dense vector mapping to obtain the auxiliary decision dense vector; performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector by the dense vector Jiao Dianhua module to obtain the auxiliary decision attention vector; and inputting the auxiliary decision-making attention vector into the time-space domain vector mining module to perform time-space domain vector mining to obtain the water ecological time-space domain index vector.

Based on this embodiment, the auxiliary decision mining branch employed by the water ecological survey assessment apparatus is designed to contain three core modules: the device comprises a dense vector mapping module, a dense vector focusing module and a time-space domain vector mining module. The three modules work cooperatively to finish the deep analysis and processing of the evaluation early warning auxiliary decision information together so as to extract key characteristics and potential problems of the water ecological system.

Firstly, the water ecology investigation evaluation equipment inputs evaluation early warning auxiliary decision information into the dense vector mapping module. The purpose of this step is to convert the original evaluation early warning assistant decision information, such as expert advice, analysis of historical cases, prediction results of models, etc., into a numerical vector form that can be effectively processed by the algorithm, i.e. an assistant decision dense vector. Dense vector mapping is an advanced natural language processing technique that is capable of converting text or discrete data into continuous vectors in high-dimensional space. Through the conversion, each evaluation early warning assistant decision information is converted into an assistant decision dense vector, the vectors keep the semantics and the context relation of the original information in a vector space, and a richer information basis is provided for subsequent analysis and decision.

Next, the water ecology survey evaluation apparatus performs dense vector focusing on the auxiliary decision dense vector using the environmental monitoring index vector obtained previously. This step is achieved by a dense vector focalization module. Focusing is a mechanism of attention that allows algorithms to "focus" on those parts of the auxiliary decision information that are closely related to environmental monitoring metrics. Specifically, the algorithm calculates the similarity or correlation between the environment monitoring index vector and the assistant decision dense vector, and weights the assistant decision dense vector according to the similarity or correlation. Through Jiao Dianhua, the algorithm can generate auxiliary decision attention vectors which are focused on key auxiliary decision information under the current environment monitoring index, so that the accuracy and pertinence of subsequent analysis are improved.

After the auxiliary decision-making attention vectors are obtained, the water ecology investigation and evaluation equipment aims at inputting the vectors into a time-space domain vector mining module for time-space domain vector mining. Time-space domain vector mining is an advanced data analysis technique that is capable of analyzing the distribution and variation patterns of data in both time and space dimensions. Through the step, the algorithm can extract key characteristics of the water ecological time-space domain, such as seasonal variation, geographic distribution, long-term trend and the like, from the auxiliary decision-making attention vector. These features have important reference values for a comprehensive understanding of the condition of the water ecosystem and its trend of variation.

In the time-space domain vector mining process, the algorithm considers the change of the auxiliary decision-making attention vector in the time dimension, such as the auxiliary decision-making information difference of different seasons and different years; meanwhile, the algorithm also considers information in space dimension, such as auxiliary decision information characteristics of different geographic positions and different water areas. By comprehensively considering the information of time and space dimensions, the algorithm can more accurately mine the time-space domain characteristics of the water ecological system and generate the water ecological time-space domain index vector. The vectors reflect the key performance of the evaluation early warning auxiliary decision information on the time-space domain, and a more comprehensive and accurate data basis is provided for subsequent comprehensive evaluation and decision.

In this way, by adopting the auxiliary decision mining branch including the dense vector mapping module, the dense vector focusing module, and the time-space domain vector mining module, the water ecology investigation evaluation apparatus can effectively process and analyze and evaluate the early warning auxiliary decision information. The processing flow not only improves the processing efficiency and quality of the data, but also provides more comprehensive and scientific data support and decision basis for subsequent ecological protection and management. Specifically, the dense vector mapping module converts the original evaluation early warning auxiliary decision information into a numerical vector form, and provides a richer information basis for subsequent analysis and decision; the dense vector Jiao Dianhua module extracts key auxiliary decision information closely related to the environmental monitoring index through an attention mechanism, so that the accuracy and pertinence of subsequent analysis are improved; the time-space domain vector mining module comprehensively considers the information of time and space dimensions, and mines the time-space domain characteristics of the water ecological system, so that more comprehensive and accurate data support is provided for comprehensive evaluation and decision.

In other alternative embodiments, the tuning of the target water ecology survey evaluation algorithm comprises the steps of: acquiring an ecological environment monitoring data sample, an evaluation early warning auxiliary decision sample and an aquatic ecological quality priori view; inputting the ecological environment monitoring data sample and the evaluation early warning auxiliary decision sample into a basic water ecological investigation evaluation algorithm, and carrying out environment monitoring index vector identification on the ecological environment monitoring data sample through the basic water ecological investigation evaluation algorithm to obtain a debugging environment monitoring index vector; performing dense vector mapping on the evaluation early warning auxiliary decision sample through the basic water ecology investigation evaluation algorithm to obtain a debugging auxiliary decision dense vector, performing dense vector focusing on the debugging auxiliary decision dense vector through the debugging environment monitoring index vector to obtain a debugging auxiliary decision attention vector, and performing time-space domain vector mining according to the debugging auxiliary decision attention vector to obtain a debugging water ecology time-space domain index vector; performing linkage monitoring index association on the debugging water ecology time-space domain index vector through the debugging environment monitoring index vector by the basic water ecology investigation evaluation algorithm to obtain a target debugging water ecology time-space domain index vector, and performing linkage monitoring index association on the debugging environment monitoring index vector through the debugging water ecology time-space domain index vector to obtain a target debugging environment monitoring index vector; carrying out commonality weight operation on the target debugging environment monitoring index vector and the target debugging water ecological time-space domain index vector through the basic water ecological investigation evaluation algorithm to obtain a debugging target commonality weight, and determining a debugging water ecological quality evaluation view corresponding to the ecological environment monitoring data sample according to the debugging target commonality weight and the evaluation early warning auxiliary decision sample; and carrying out quality evaluation error operation according to the debugging water ecological quality evaluation viewpoint and the water ecological quality priori viewpoint to obtain algorithm error data, optimizing the basic water ecological investigation evaluation algorithm according to the algorithm error data, and then jumping to the step of obtaining an ecological environment monitoring data sample, a corresponding evaluation early warning auxiliary decision sample and the water ecological quality priori viewpoint for cyclic implementation until meeting the debugging standard-reaching requirement, thereby obtaining the target water ecological investigation evaluation algorithm.

The debugging process of the target water ecology investigation and evaluation algorithm related in the embodiment is an iterative optimization process, and depends on the comprehensive application of the ecological environment monitoring data sample, the evaluation early warning auxiliary decision sample and the water ecology quality priori point of view.

Firstly, the water ecology investigation and evaluation equipment acquires a group of ecological environment monitoring data samples which are derived from a long-term water quality monitoring station, remote sensing satellite images, unmanned aerial vehicle inspection and other multi-element monitoring means, and comprise a series of environment monitoring indexes such as water temperature, pH value, dissolved oxygen, turbidity, nutrient salt content and the like. Meanwhile, the equipment can acquire evaluation early warning auxiliary decision-making examples corresponding to the ecological environment monitoring data examples, wherein the examples can comprise an ecological protection policy in a historical period, an evaluation report of an expert, a past ecological restoration case and the like, and the evaluation early warning auxiliary decision-making examples provide important references and bases for the evaluation of the quality of the water ecology. In addition, in order to measure the debugging effect of the algorithm, the device can acquire a set of water ecological quality priori views, and the views represent a current common cognition of water ecological quality based on long-term ecological monitoring and scientific research.

And the aquatic ecology investigation and evaluation equipment inputs the ecological environment monitoring data sample and the evaluation early warning auxiliary decision sample into a basic aquatic ecology investigation and evaluation algorithm. The basic water ecology investigation and evaluation algorithm is a pre-constructed mathematical model or machine learning model, and can perform deep analysis and processing on input ecological environment monitoring data. In this step, the algorithm first identifies the environmental monitoring index vector for the sample of the ecological environmental monitoring data. The process involves converting raw monitoring data into a numerical vector form that can be efficiently processed by an algorithm, i.e., a debug environment monitoring index vector. The vectors preserve the characteristics and the relations of the original data in a vector space, and provide a richer information basis for subsequent analysis and decision.

Then, the basic water ecology investigation evaluation algorithm can carry out dense vector mapping on the evaluation early warning auxiliary decision-making sample. Dense vector mapping is an advanced natural language processing technique that is capable of converting text or discrete data into continuous vectors in high-dimensional space. Through the conversion, each evaluation early warning assistant decision sample is converted into a debugging assistant decision dense vector. The vectors preserve the semantics and context of the original information in the vector space, providing a richer information basis for subsequent analysis and decision making.

After obtaining the debug aid decision dense vectors, the algorithm uses the previously obtained debug environment monitoring index vectors to focus the dense vectors. Focusing is a mechanism of attention that allows algorithms to "focus" on those parts of the auxiliary decision information that are closely related to environmental monitoring metrics. Specifically, the algorithm calculates the similarity or correlation between the debug environment monitoring index vector and the debug auxiliary decision dense vector, and performs weighting processing on the debug auxiliary decision dense vector according to the similarity or correlation. Through Jiao Dianhua, the algorithm can generate debugging auxiliary decision attention vectors which are focused on key auxiliary decision information under the current environment monitoring index, so that the accuracy and pertinence of subsequent analysis are improved.

Next, the algorithm performs time-space domain vector mining according to the debug aid decision attention vector. Time-space domain vector mining is an advanced data analysis technique that is capable of analyzing the distribution and variation patterns of data in both time and space dimensions. Through the step, the algorithm can extract key characteristics of the water ecological time-space domain, such as seasonal variation, geographic distribution, long-term trend and the like, from the debugging auxiliary decision-making attention vector. These features have important reference values for a comprehensive understanding of the condition of the water ecosystem and its trend of variation.

After the index vector of the debugging water ecology time-space domain is obtained, the algorithm can carry out linkage monitoring index association. This step involves correlating and mapping the debug environment monitor index vector with the debug water ecology time-space domain index vector. Specifically, the algorithm analyzes the inherent links and laws between the two, such as whether a change in certain environmental monitoring metrics would result in the appearance or disappearance of a particular time-space domain feature. Through the step, the algorithm can obtain the target debugging water ecology time-space domain index vector and the target debugging environment monitoring index vector, and the two vectors reflect the actual condition and the change trend of the water ecology system more accurately.

And finally, the algorithm carries out common weight operation on the target debugging environment monitoring index vector and the target debugging water ecology time-space domain index vector. This step involves calculating the degree of commonality or similarity between the two vectors, i.e. the debug target commonality weight. This weight represents a comprehensive decision of the current algorithm for water ecological quality assessment. According to the weight and the evaluation early warning auxiliary decision-making sample, the algorithm can determine the debugging water ecological quality evaluation viewpoint corresponding to the ecological environment monitoring data sample.

After obtaining the adjusted water ecological quality evaluation viewpoint, the algorithm performs quality evaluation error operation with the water ecological quality priori viewpoint. This step involves calculating the difference or error between the two, i.e., the algorithm error data. This data reflects the accuracy and reliability of the current algorithm in assessing water ecological quality. According to the error data, the algorithm can optimize and adjust the basic water ecology investigation evaluation algorithm so as to improve the accuracy and reliability of the evaluation.

Then, the algorithm jumps to the step of circularly implementing the steps of acquiring the ecological environment monitoring data sample, the corresponding evaluation early warning auxiliary decision sample and the water ecological quality priori view. The process is continuously iterated and optimized until the evaluation result of the algorithm meets the debugging standard-reaching requirement, and a final target water ecology investigation evaluation algorithm is obtained.

Thus, the water ecology investigation and evaluation equipment can realize accurate and reliable evaluation of the water ecology quality. The method not only improves the accuracy and reliability of the water ecology evaluation, but also provides more scientific and effective data support and decision basis for the subsequent ecological protection and management. In detail, the accuracy and the reliability of the water ecological assessment are improved, so that the ecological protection and management are more scientific and effective; the method provides richer and comprehensive water ecological information and provides more comprehensive data support for ecological protection and management; deep excavation and analysis of time-space domain characteristics of the water ecosystem are realized, and important reference value is provided for understanding the condition and the change trend of the water ecosystem; through iterative optimization and debugging, the evaluation accuracy and reliability of the algorithm are continuously improved, and powerful technical support is provided for long-term protection and continuous development of the water ecological system.

In some independent embodiments, the method further comprises: and carrying out water ecological maintenance treatment on the target water area according to the target water ecological quality evaluation viewpoint. In detail, the water ecological maintenance treatment for the target water area according to the target water ecological quality evaluation viewpoint comprises the following steps: analyzing the target water ecological quality evaluation viewpoint, and identifying key ecological problems, causes, influence ranges and potential risks facing the target water area; determining a maintenance target of water ecological maintenance based on the identified key ecological problems, and formulating rule features of a maintenance scheme; customizing maintenance measures according to the determined maintenance targets and rule characteristics, wherein the maintenance measures comprise: pollution source control measures, ecological restoration engineering and environmental supervision mechanisms; an implementation plan is established for maintenance measures, wherein the implementation plan comprises a responsibility department, a fund source, personnel configuration, material preparation, and a time node and a staged target are set; and establishing a periodic assessment mechanism, tracking, monitoring and assessing the maintenance effect, and timely adjusting maintenance measures and plans according to the assessment result so as to ensure the realization of a maintenance target. Through the steps, the method can generate a set of scientific, reasonable and creative water ecological maintenance scheme text according to the target water ecological quality evaluation viewpoint, and provides powerful support for water ecological protection and management of the target water area.

It can be understood that the above-mentioned water ecology investigation and evaluation device is not limited to the evaluation of the ecology quality of a water area, but also performs maintenance treatment of the water ecology of a target water area further from the evaluation viewpoint. The expanding application greatly enhances the practicability and comprehensive benefits of the equipment, so that the equipment becomes an important tool for protecting and managing the ecology of the water area.

In detail, the process of performing water ecological maintenance treatment on the target water area according to the target water ecological quality evaluation viewpoint specifically comprises the following key steps: first, the water ecology investigation and evaluation device analyzes a target water ecology quality evaluation viewpoint. This step involves in-depth analysis and interpretation of the assessment data to identify critical ecological problems faced by the target waters. These problems may include water eutrophication, heavy metal pollution, reduced biodiversity, foreign species invasion, increased water and soil loss, etc. The equipment can accurately identify the cause, the influence range and the potential ecological risk of the problems through advanced algorithms and models. For example, the equipment can find that the eutrophication problem of a certain water area is mainly caused by chemical fertilizers in surrounding farmlands and disordered discharge of domestic sewage of residents, and the problem has caused mass propagation of algae in the water body, which seriously affects the transparency and oxygen content of the water body. Next, based on the identified key ecological issue, the device determines a maintenance objective for the water ecological maintenance and formulates a rule feature for the maintenance scheme. Maintenance objectives include restoring self-cleaning ability of the water body, improving biodiversity, controlling pollution source emission, protecting key ecological areas, and the like. The rule features refer to basic principles and constraint conditions to be followed by the maintenance scheme, such as coordination unification of ecological protection and economic and social development, and consideration of long-term benefit and short-term effect. In the step, the equipment comprehensively considers factors such as ecological environment, socioeconomic status, policy and regulations and the like of the water area, and a scientific and feasible maintenance scheme is prepared. The device then customizes the maintenance measures based on the determined maintenance objectives and rule features. These maintenance measures may include pollution source control measures, ecological restoration projects, environmental regulatory mechanisms, and the like. For example, for the eutrophication problem, the equipment can provide specific measures such as establishing a guiding system for farmland fertilizer use, building a domestic sewage treatment facility, implementing dredging engineering of water bottom mud and the like. At the same time, the device also considers how to establish an effective environmental supervision mechanism to ensure that these measures can be effectively executed and supervised. After the maintenance measures are formulated, the apparatus makes detailed implementation plans for these measures. The implementation plan comprises key elements such as responsibility departments, fund sources, personnel configuration, material preparation and the like, and definite time nodes and stage targets are set. This step ensures that the maintenance scheme can be advanced in order and efficiently. For example, the equipment can determine that a certain sediment dredging project is responsible for implementation by a local environmental protection department, funds come from budgets and environmental protection funds, the funds need to be completed in the next six months, and specific dredging amount and water quality improvement targets are set as staged targets. Finally, the device also establishes a periodic assessment mechanism to track, monitor and assess the maintenance effect. The mechanism comprises regular water quality monitoring, ecological condition investigation, inspection of maintenance measure execution and the like. The device timely adjusts maintenance measures and plans according to the evaluation result so as to ensure the realization of maintenance targets. For example, if the device finds that the operation effect of a certain domestic sewage treatment facility is poor, and the nitrogen and phosphorus content in the water body is still higher, the device can make adjustment suggestions such as increasing the scale of the treatment facility, optimizing the treatment process or enhancing the operation management of the facility. Through the steps, a set of scientific, reasonable and creative water ecological maintenance scheme text can be generated according to the target water ecological quality evaluation viewpoint. The water ecology maintenance scheme text not only comprises detailed maintenance measures and implementation plans, but also considers the feasibility and long-term benefits of the scheme, and provides powerful support for the water ecology protection and management of the target water area.

In other independent embodiments, the method further comprises: and carrying out association labeling storage processing on the ecological environment monitoring data of the target water area and the target water ecological quality evaluation viewpoint.

The water ecological investigation and evaluation equipment in the embodiment of the invention is not only limited to the ecological quality evaluation and subsequent maintenance processing of the water area, but also further realizes the function of carrying out the association labeling storage processing on the ecological environment monitoring data of the target water area and the ecological quality evaluation viewpoint of the target water. The expansion application not only enhances the data processing capability of the equipment, but also provides richer and more accurate data support for the ecological protection and management of the water area.

In detail, the process of performing association labeling storage processing on the ecological environment monitoring data of the target water area and the target water ecological quality evaluation viewpoint specifically comprises the following key steps: first, the water ecology investigation and evaluation device collects the ecological environment monitoring data of the target water area. The data can include water quality parameters such as temperature, pH value, dissolved oxygen content, turbidity, nutrient salt concentration and the like of the water body, and ecological parameters such as the types, the numbers, the distribution and the like of the aquatic organisms. The device can accurately acquire the data in real time through advanced sensor and monitoring technology and store the data in an internal database. Next, the device pre-processes the collected ecological environment monitoring data. This step involves the cleaning, denoising, conversion, etc. of the data to ensure accuracy and consistency of the data. For example, the device may remove outliers due to sensor failures or data transmission errors, or convert data from different sources into a uniform format and unit. After the data preprocessing is completed, the device correlates the preprocessed ecological environment monitoring data with the target water ecological quality evaluation viewpoint. This step is the core of the overall process and it enables an organic combination of data and evaluation perspectives. In particular, the device correlates relevant monitoring data with the key ecological problems, causes, impact ranges and the like mentioned in the evaluation point of view. For example, if the evaluation point indicates that there is an eutrophication problem in a certain water area, the apparatus will relate water quality parameters (e.g., nutrient salt concentration) and ecological parameters (e.g., the type and quantity of aquatic organisms) related to the eutrophication to the point. After the association is completed, the device marks the association data. The content of the annotation may include information about the source of the data, the time of acquisition, the location, the degree of association with the evaluation viewpoint, etc. This step facilitates subsequent data analysis and utilization, enabling the user to more quickly find the desired data and understand the relationship between the data and the evaluation perspective. And finally, the device stores the marked associated data in an internal database and performs effective management and maintenance. These databases may take the form of relational databases or non-relational databases, depending on the structure of the data and the query requirements. The device provides a convenient data query and access interface so that a user can conveniently acquire and utilize such data. Through the steps, the water ecology investigation and evaluation equipment provided by the embodiment of the invention realizes the associated labeling storage processing of the ecological environment monitoring data of the target water area and the target water ecology quality evaluation viewpoint. The function not only enhances the data processing capacity of the equipment, but also provides richer and more accurate data support for water ecological protection and management. Users can know the ecological condition of the water area more deeply by inquiring the data, evaluate the basis of the views and the association relation between the two, thereby providing powerful support for formulating more scientific ecological protection and management strategies.

Therefore, the application of the water ecological investigation and evaluation equipment in the ecological environment monitoring data and target water ecological quality evaluation viewpoint association label storage processing brings remarkable beneficial effects. Firstly, the device accurately collects the ecological environment monitoring data of the target water area in real time, and performs pretreatment and associated labeling storage treatment on the ecological environment monitoring data, so that richer and more accurate data support is provided for the ecological protection and management of the water area. The data not only comprises basic information such as water quality parameters and ecological parameters, but also is organically combined with the evaluation viewpoint, so that a user can know the ecological condition of the water area and the relationship between the ecological condition and the evaluation viewpoint more deeply. Second, the convenient data query and access interface provided by the device enables the user to conveniently acquire and utilize such data. The user can inquire specific data or data sets according to the needs to further analyze and process, so that powerful support is provided for formulating more scientific ecological protection and management strategies. The function not only improves the efficiency of data processing and utilization, but also reduces the threshold for the user to acquire and use data. In addition, the device provided by the embodiment of the invention also realizes long-term accumulation and continuous updating of the data by carrying out association labeling storage processing on the ecological environment monitoring data and the target water ecological quality evaluation viewpoint. Over time, the device continuously collects new monitoring data and associates and labels it with existing assessment views. Therefore, the user can acquire the data change information on the time sequence, so that the development trend and the change rule of the ecological condition of the water area can be better known.

In other independent embodiments, the processing of associating the ecological environment monitoring data of the target water area with the target water ecological quality assessment viewpoint for labeling and storing includes: determining an initial structural semantic feature map corresponding to the associated storage object binary group according to the associated annotation indication feature; the initial structural semantic feature map is used for representing the key word semantic thermodynamic diagram of ecological environment monitoring data and a target water ecological quality evaluation view in the associated storage object binary group; determining a semantic logic link vector of the associated storage object binary group according to the initial structural semantic feature map and the associated storage object binary group; the semantic logic link vector is used for representing semantic derivative identification coefficients of each segmented data set, each segmented data set comprises a part of the ecological environment monitoring data and a part of the target water ecological quality evaluation viewpoint, and overlapping exists among the segmented data sets; updating the initial structure semantic feature map according to the semantic logic link vector to obtain an updated structure semantic feature map; and carrying out association labeling on the association storage object binary groups according to the update structure semantic feature diagram, and storing the association storage object binary groups into a target database through a structured storage strategy.

In this embodiment, first, the water ecology investigation evaluation device determines an initial structural semantic feature map corresponding to the associated storage object binary group according to the associated annotation indicating feature. The associated annotation indicating feature is a specific instruction or mark used for indicating the equipment to carry out associated annotation processing on the associated storage object binary group. The associated storage object binary group is a pair of two elements consisting of ecological environment monitoring data and a target water ecological quality evaluation viewpoint, and is a basic unit of associated annotation. The initial structure semantic feature map is a graphical representation for representing the relationship between ecological environment monitoring data and a target water ecological quality evaluation viewpoint in the associated storage object binary group, wherein the graphical representation comprises a keyword semantic thermodynamic diagram and is used for intuitively displaying the semantic association degree between the two.

Specifically, the device first identifies keywords in the associated storage object tuples, which may include water quality parameters, ecological problems, causes, impact ranges, etc. The device then calculates semantic similarity between the keywords and generates a semantic thermodynamic diagram based on the magnitude of the similarity. In the thermodynamic diagram, keywords with higher similarity will be labeled as hotter colors, and keywords with lower similarity will be labeled as colder colors. In this way, the user can intuitively understand the semantic association condition between the ecological environment monitoring data and the target water ecological quality assessment viewpoint by observing the thermodynamic diagram.

Next, the device determines a semantic logical link vector for the associated storage object tuple from the initial structural semantic feature map and the associated storage object tuple. The semantic logical link vector is a vector of semantically derived recognition coefficients for characterizing each segmented dataset, reflecting semantically derived relationships between the ecological environment monitoring data in the segmented dataset and the target water ecological quality assessment perspective. Each segmented data set contains partial ecological environment monitoring data and partial target water ecological quality evaluation viewpoints, and overlapping exists among the segmented data sets so as to ensure continuity and integrity of the data.

The device calculates the semantically derived recognition coefficients of each segmented dataset through complex algorithms and models and combines these coefficients into a semantic logical link vector. This vector not only contains semantic association information between segmented datasets, but also reflects their importance and contribution in the water ecological survey assessment. Through the semantic logic link vector, the device can more accurately understand the semantic relation between the ecological environment monitoring data in the associated storage object binary group and the target water ecological quality evaluation viewpoint, and provides powerful support for subsequent associated labeling and storage processing.

And then, the device updates the initial structure semantic feature map according to the semantic logic link vector to obtain an updated structure semantic feature map. The step is a core link of the association labeling process, and the optimization and adjustment of the initial structure semantic feature map are realized. And the device performs weighting processing on the keyword semantic thermodynamic diagram in the initial structural semantic feature diagram according to the semantic derived recognition coefficient provided in the semantic logical link vector. In particular, for segmented datasets with high semantic derived recognition coefficients, the device enhances its representation strength in thermodynamic diagrams; for segmented datasets with low semantic derived recognition coefficients, the device may then weaken its representation in the thermodynamic diagram. Therefore, the updated structural semantic feature map can more accurately reflect the semantic relation between the ecological environment monitoring data and the target water ecological quality evaluation viewpoint.

And finally, the device carries out association labeling on the associated storage object binary groups according to the updated structural semantic feature map, and stores the association labeling in a target database through a structured storage strategy. In the step, the device uses the information in the updated structural semantic feature map to make detailed association labeling for the associated storage object tuples. The marked content can comprise information such as the source of the data, the acquisition time, the location, the degree of association with the target water ecological quality assessment viewpoint and the like. Meanwhile, the device also adopts a structured storage strategy to store the data after the association labeling into a target database. Structured storage policies are an efficient way of data storage that can organize data into structured forms so that users can more conveniently query and utilize the data.

Through the steps, the water ecology investigation and evaluation equipment provided by the embodiment of the invention realizes the associated labeling storage processing of the ecological environment monitoring data of the target water area and the target water ecology quality evaluation viewpoint. The realization of the function not only enhances the data processing capacity of the equipment, but also provides richer and more accurate data support for the ecological protection and management of the water area. Users can know the ecology condition of the water area and the relation between the ecology condition and the target water ecology quality evaluation view more deeply by inquiring the data, so that powerful support is provided for formulating a more scientific ecology protection and management strategy.

Further, fig. 2 is a schematic structural diagram of an apparatus 200 for investigation and evaluation of water ecology according to an embodiment of the present invention. The water ecology survey evaluation apparatus 200 as shown in fig. 2 comprises a processor 210, from which the processor 210 may call and run a computer program to implement the method in an embodiment of the invention.

Optionally, as shown in fig. 2, the water ecology survey evaluation apparatus 200 may also include a memory 230. Wherein the processor 210 may call and run a computer program from the memory 230 to implement the method in an embodiment of the invention. Wherein the memory 230 may be a separate device from the processor 210 or may be integrated into the processor 210.

Optionally, as shown in fig. 2, the water ecological survey and assessment device 200 may further include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices, and in particular, may send information or data to other devices, or receive information or data sent by other devices.

Optionally, the water ecological investigation and evaluation device 200 may implement the storage engine or a component (such as a processing module) in the storage engine or a corresponding flow corresponding to a device in which the storage engine is deployed in each method of the embodiments of the present invention, which is not described herein for brevity. It should be appreciated that the processor of an embodiment of the present invention may be an integrated circuit chip having signal processing capabilities.

It will be appreciated that the memory in embodiments of the invention may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, a suitable type of memory.

On the basis of the above, there is provided an aquatic ecology investigation and evaluation device for: acquiring ecological environment monitoring data and corresponding evaluation early warning auxiliary decision information of a target water area; performing environment monitoring index vector identification according to the ecological environment monitoring data of the target water area to obtain an environment monitoring index vector; performing dense vector mapping on the evaluation early warning auxiliary decision information to obtain an auxiliary decision dense vector, performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and performing time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic ecological time-space domain index vector; performing linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector to obtain a global water ecological time-space domain index vector, and performing linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain a global environment monitoring index vector; and carrying out commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector to obtain target commonality weight, and determining a target water ecology quality evaluation viewpoint corresponding to the ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information.

On the basis of the above, a readable storage medium is provided, on which a program or instructions are stored which, when executed by a processor, implement the steps of the above method.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present invention is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention. The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative, not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit and scope of the present invention.

Claims

1. A water ecology survey evaluation method, the method being applied to a water ecology survey evaluation apparatus, the method comprising:

acquiring ecological environment monitoring data and corresponding evaluation early warning auxiliary decision information of a target water area;

Performing environment monitoring index vector identification according to the ecological environment monitoring data of the target water area to obtain an environment monitoring index vector;

performing dense vector mapping on the evaluation early warning auxiliary decision information to obtain an auxiliary decision dense vector, performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and performing time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic ecological time-space domain index vector;

Performing linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector to obtain a global water ecological time-space domain index vector, and performing linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain a global environment monitoring index vector;

carrying out commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector to obtain target commonality weight, and determining a target water ecology quality evaluation viewpoint corresponding to ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information;

Performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, wherein the method comprises the following steps of:

carrying out residual connection processing on the environment monitoring index vector to obtain environment monitoring residual characteristics;

integrating the environment monitoring residual characteristics with the auxiliary decision dense vector to obtain the auxiliary decision attention vector;

the step of carrying out linkage monitoring index association on the water ecology time-space domain index vector through the environment monitoring index vector to obtain a global water ecology time-space domain index vector comprises the following steps:

Performing characteristic focusing coefficient operation according to the water ecological time-space domain index vector and the environment monitoring index vector to obtain a characteristic focusing coefficient;

Performing characteristic reinforcement on the environment monitoring index vector through the characteristic focusing coefficient to obtain a first environment monitoring focusing vector;

combining the first environment monitoring focusing vector and the water ecology time-space domain index vector to obtain the global water ecology time-space domain index vector;

The step of carrying out linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain a global environment monitoring index vector comprises the following steps:

carrying out characteristic reinforcement on the water ecological time-space domain index vector through the characteristic focusing coefficient to obtain a second environment monitoring focusing vector;

combining the second environment monitoring focus vector and the environment monitoring index vector to obtain the global environment monitoring index vector;

The step of carrying out commonality weight operation according to the global environment monitoring index vector and the global water ecology time-space domain index vector to obtain target commonality weight, and determining a target water ecology quality evaluation viewpoint corresponding to ecology environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information comprises the following steps:

Based on the global environment monitoring index vector and the global water ecology time-space domain index vector, obtaining a commonality identification feature;

And performing interval weight conversion on the commonality identification features to obtain the target commonality weight, and taking the water ecological quality evaluation viewpoint corresponding to the evaluation early warning auxiliary decision information as the target water ecological quality evaluation viewpoint corresponding to the ecological environment monitoring data of the target water area when the target commonality weight is greater than the set commonality weight.

2. The method of claim 1, wherein the performing environmental monitoring index vector identification based on the ecological environment monitoring data of the target water area to obtain an environmental monitoring index vector comprises:

Dividing each ecological environment monitoring data segment from the ecological environment monitoring data of the target water area, and respectively carrying out dense vector mapping on each ecological environment monitoring data segment to obtain each local environment monitoring dense vector;

Carrying out time-space domain vector mining on the local environment monitoring dense vectors to obtain local time-space domain index vectors;

and splicing the local time-space domain index vectors based on the investigation evaluation task to obtain the environment monitoring index vector.

3. The method of claim 1, wherein the evaluation early warning assistance decision information comprises at least two; the method further comprises the steps of:

Performing dense vector mapping on the at least two evaluation early warning auxiliary decision information to obtain at least two auxiliary decision dense vectors, and performing dense vector Jiao Dianhua on the at least two auxiliary decision dense vectors through the environment monitoring index vector to obtain at least two auxiliary decision attention vectors, and performing time-space domain vector mining on the at least two auxiliary decision attention vectors to obtain at least two water ecological time-space domain index vectors;

The environment monitoring index vectors are respectively used for carrying out linkage monitoring index association on the at least two water ecology time-space domain index vectors to obtain at least two global water ecology time-space domain index vectors, and the environment monitoring index vectors are respectively used for carrying out linkage monitoring index association on the at least two water ecology time-space domain index vectors to obtain at least two global environment monitoring index vectors;

And carrying out common weight operation on the at least two global water ecology time-space domain index vectors and the corresponding global environment monitoring index vectors in the at least two global environment monitoring index vectors respectively to obtain target common weights of the at least two evaluation early warning auxiliary decision information and the ecological environment monitoring data of the target water area respectively, and determining the current water ecology quality evaluation viewpoint corresponding to the ecological environment monitoring data of the target water area according to the target common weights and the at least two evaluation early warning auxiliary decision information.

4. The method of claim 1, wherein the method further comprises:

The ecological environment monitoring data of the target water area and corresponding evaluation early warning auxiliary decision information are input into a target water ecological investigation evaluation algorithm, and environment monitoring index vector identification is carried out on the ecological environment monitoring data of the target water area through the target water ecological investigation evaluation algorithm, so that environment monitoring index vectors are obtained;

Performing dense vector mapping on the evaluation early warning auxiliary decision information through the target water ecology investigation evaluation algorithm to obtain an auxiliary decision dense vector, performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and performing time-space domain vector mining according to the auxiliary decision attention vector to obtain a water ecology time-space domain index vector;

Performing linkage monitoring index association on the water ecological time-space domain index vector through the environment monitoring index vector by the target water ecological investigation evaluation algorithm to obtain a global water ecological time-space domain index vector, and performing linkage monitoring index association on the environment monitoring index vector through the water ecological time-space domain index vector to obtain a global environment monitoring index vector;

and carrying out commonality weight operation on the global environment monitoring index vector and the global water ecology time-space domain index vector through the target water ecology investigation evaluation algorithm to obtain target commonality weight, and determining a target water ecology quality evaluation view corresponding to the ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information.

5. The method of claim 4, wherein the target water ecological survey evaluation algorithm comprises an environmental monitoring index mining branch, an auxiliary decision mining branch, a linkage monitoring index association branch and a commonality weight operation branch; the recording of the ecological environment monitoring data of the target water area and the corresponding evaluation early warning auxiliary decision information into a target water ecological investigation evaluation algorithm comprises the following steps:

Recording the ecological environment monitoring data of the target water area into the environment monitoring index mining branch to identify environment monitoring index vectors, so as to obtain environment monitoring index vectors;

Recording the evaluation early warning auxiliary decision information into the auxiliary decision mining branch for dense vector mapping to obtain an auxiliary decision dense vector, carrying out dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, and carrying out time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic ecological time-space domain index vector;

The environment monitoring index vector and the water ecological time-space domain index vector are input into the linkage monitoring index association branch, the water ecological time-space domain index vector is subjected to linkage monitoring index association through the environment monitoring index vector by the linkage monitoring index association branch to obtain a global water ecological time-space domain index vector, and the environment monitoring index vector is subjected to linkage monitoring index association through the water ecological time-space domain index vector to obtain a global environment monitoring index vector;

Recording the global environment monitoring index vector and the global water ecology time-space domain index vector into the commonality weight operation branch to perform commonality weight operation, so as to obtain target commonality weight, and determining a target water ecology quality evaluation view corresponding to the ecological environment monitoring data of the target water area according to the target commonality weight and the evaluation early warning auxiliary decision information;

The auxiliary decision mining branch comprises a dense vector mapping module, a dense vector focusing module and a time-space domain vector mining module; the step of inputting the evaluation early warning auxiliary decision information into the auxiliary decision mining branch to carry out dense vector mapping to obtain an auxiliary decision dense vector, carrying out dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector to obtain an auxiliary decision attention vector, carrying out time-space domain vector mining according to the auxiliary decision attention vector to obtain an aquatic attitude time-space domain index vector, and comprising the following steps:

Inputting the evaluation early warning auxiliary decision information into the dense vector mapping module to carry out dense vector mapping to obtain the auxiliary decision dense vector;

performing dense vector focusing on the auxiliary decision dense vector through the environment monitoring index vector by the dense vector Jiao Dianhua module to obtain the auxiliary decision attention vector;

Inputting the auxiliary decision-making attention vector into the time-space domain vector mining module for time-space domain vector mining to obtain the water ecological time-space domain index vector;

the debugging of the target water ecology investigation evaluation algorithm comprises the following steps:

Acquiring an ecological environment monitoring data sample, an evaluation early warning auxiliary decision sample and an aquatic ecological quality priori view;

Inputting the ecological environment monitoring data sample and the evaluation early warning auxiliary decision sample into a basic water ecological investigation evaluation algorithm, and carrying out environment monitoring index vector identification on the ecological environment monitoring data sample through the basic water ecological investigation evaluation algorithm to obtain a debugging environment monitoring index vector;

Performing dense vector mapping on the evaluation early warning auxiliary decision sample through the basic water ecology investigation evaluation algorithm to obtain a debugging auxiliary decision dense vector, performing dense vector focusing on the debugging auxiliary decision dense vector through the debugging environment monitoring index vector to obtain a debugging auxiliary decision attention vector, and performing time-space domain vector mining according to the debugging auxiliary decision attention vector to obtain a debugging water ecology time-space domain index vector;

Performing linkage monitoring index association on the debugging water ecology time-space domain index vector through the debugging environment monitoring index vector by the basic water ecology investigation evaluation algorithm to obtain a target debugging water ecology time-space domain index vector, and performing linkage monitoring index association on the debugging environment monitoring index vector through the debugging water ecology time-space domain index vector to obtain a target debugging environment monitoring index vector;

carrying out commonality weight operation on the target debugging environment monitoring index vector and the target debugging water ecological time-space domain index vector through the basic water ecological investigation evaluation algorithm to obtain a debugging target commonality weight, and determining a debugging water ecological quality evaluation view corresponding to the ecological environment monitoring data sample according to the debugging target commonality weight and the evaluation early warning auxiliary decision sample;

And carrying out quality evaluation error operation according to the debugging water ecological quality evaluation viewpoint and the water ecological quality priori viewpoint to obtain algorithm error data, optimizing the basic water ecological investigation evaluation algorithm according to the algorithm error data, and then jumping to the step of obtaining an ecological environment monitoring data sample, a corresponding evaluation early warning auxiliary decision sample and the water ecological quality priori viewpoint for cyclic implementation until meeting the debugging standard-reaching requirement, thereby obtaining the target water ecological investigation evaluation algorithm.

6. An apparatus for investigation and evaluation of water ecology, characterized in that the apparatus is used for:

7. An apparatus for water ecological investigation and assessment, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executing computer-executable instructions stored in the memory causes the at least one processor to perform the method of any one of claims 1-5.

8. A readable storage medium, characterized in that it stores thereon a program or instructions, which when executed by a processor, implements the method of any of claims 1-5.