CN118235723B - Cow intelligent monitoring platform and device based on wisdom pasture - Google Patents
Cow intelligent monitoring platform and device based on wisdom pasture Download PDFInfo
- Publication number
- CN118235723B CN118235723B CN202410667982.3A CN202410667982A CN118235723B CN 118235723 B CN118235723 B CN 118235723B CN 202410667982 A CN202410667982 A CN 202410667982A CN 118235723 B CN118235723 B CN 118235723B
- Authority
- CN
- China
- Prior art keywords
- pasture
- cow
- management
- data
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 50
- 241000283690 Bos taurus Species 0.000 claims abstract description 123
- 230000002159 abnormal effect Effects 0.000 claims abstract description 69
- 238000012545 processing Methods 0.000 claims abstract description 49
- 238000005457 optimization Methods 0.000 claims abstract description 37
- 230000005856 abnormality Effects 0.000 claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 20
- 238000009395 breeding Methods 0.000 claims abstract description 17
- 230000001488 breeding effect Effects 0.000 claims abstract description 17
- 230000036541 health Effects 0.000 claims abstract description 10
- 230000035790 physiological processes and functions Effects 0.000 claims abstract description 5
- 238000007726 management method Methods 0.000 claims description 143
- 238000000034 method Methods 0.000 claims description 30
- 230000000694 effects Effects 0.000 claims description 21
- 230000036760 body temperature Effects 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000003909 pattern recognition Methods 0.000 claims description 10
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 4
- 238000013501 data transformation Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 5
- 230000006399 behavior Effects 0.000 description 20
- 230000008569 process Effects 0.000 description 9
- 241001465754 Metazoa Species 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000003631 expected effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000009360 aquaculture Methods 0.000 description 3
- 244000144974 aquaculture Species 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011157 data evaluation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000012173 estrus Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 210000004767 rumen Anatomy 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- Animal Husbandry (AREA)
- Theoretical Computer Science (AREA)
- Biodiversity & Conservation Biology (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Marine Sciences & Fisheries (AREA)
- Agronomy & Crop Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cow intelligent monitoring platform and device based on an intelligent pasture, and relates to the technical field of intelligent pastures, wherein the cow intelligent monitoring platform and device are used for acquiring behavior patterns, physiological states and health indexes of cows; determining corresponding target parameters according to the behavior mode of the cow, constructing an abnormality index according to the change of the target parameters, acquiring the concentration of the abnormality processing instructions if the acquired abnormality index exceeds an abnormality threshold, and giving a pasture management strategy according to a pasture management knowledge graph if the concentration of the abnormality processing instructions exceeds an expected value; testing the output management strategy by the pasture management digital twin model, constructing an optimization degree by the state coefficient obtained by the testing, judging whether the current management strategy is effective or not by the optimization degree, and selecting a corresponding processing mode for the management strategy according to a judging result. When the pasture management is abnormal, the abnormal conditions of the pasture can be adjusted and optimized as a whole, and the breeding state of the cows is improved.
Description
Technical Field
The invention relates to the technical field of intelligent pastures, in particular to a cow intelligent monitoring platform and device based on an intelligent pasture.
Background
The intelligent pasture is a novel cultivation mode for intelligently modifying and upgrading the pasture by means of technical means such as modern Internet of things, big data, artificial intelligence and the like. Through installing all kinds of sensors and monitoring facilities, wisdom pasture can collect data such as aquaculture environment, animal growth and health status in real time to through cloud computing and big data analysis, provide scientific decision support for the breeder. Specifically, the intelligent pasture can realize the automation and intelligent management of the cultivation process, including automatic feeding, environmental control, disease monitoring, early warning and the like. It can also build a food safety tracking system to ensure the quality and safety of the product. In addition, the intelligent pasture can also improve the breeding efficiency, reduce the resource consumption and the environmental pollution, and realize sustainable development.
In the Chinese patent of application publication number CN114778787A, an intelligent marine pasture monitoring system based on information and energy simultaneous transmission is disclosed, and the intelligent marine pasture monitoring system comprises a field monitoring sensor, wherein the field monitoring sensor is connected with an information and energy simultaneous transmission AP through a wireless signal receiving and transmitting antenna and an energy receiving antenna, the information and energy simultaneous transmission AP is connected with a display control unit, the display control unit is connected with a master control room, and the master control room is connected with a mobile terminal through a cloud server. According to the invention, an oxygen dissolving sensor, a PH detection sensor, a turbidity sensor, a salinity sensor, an ammonia nitrogen sensor and a COD sensor are arranged to detect the oxygen dissolving amount, the pH value, the turbidity, the salinity ammonia nitrogen content and the water quality of the aquaculture water, so as to monitor whether various indexes of seawater on the aquaculture fish reach standards.
In the Chinese patent of the invention with the application publication number of CN117061562A, the intelligent cow monitoring platform and device based on the intelligent pasture comprise a data acquisition component and a terminal upper computer, wherein the data acquisition component is connected with the terminal upper computer through a wireless transmission module, and the data acquisition component comprises an STM32 chip, a storage module, a GPS positioning sensor, a motion sensor and a temperature sensor.
Combining the contents of the above applications and prior art:
When monitoring the breeding state of cows in pastures, a plurality of groups of sensors or data acquisition devices are usually required to be installed, the cows and the environmental data are acquired, the current breeding state of the cows is evaluated and monitored according to the change of the acquired data, and the current management pasture management strategy is adjusted according to the monitoring and the corresponding analysis results; however, in the existing pasture monitoring platform, whether the breeding state of the cow is abnormal is judged mainly through data analysis and evaluation, and an alarm is given when the cow is abnormal, but a reasonable management strategy is difficult to give, so that emergency treatment can be carried out only on the current abnormal condition, and the pasture management is still lack of improvement on the whole.
Therefore, the invention provides a cow intelligent monitoring platform and device based on an intelligent pasture.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides a cow intelligent monitoring platform and device based on an intelligent pasture, which are characterized in that if the concentration of an abnormal processing instruction exceeds the expected value, a pasture management knowledge graph is used for giving a pasture management strategy; testing the output management strategy by the pasture management digital twin model, constructing an optimization degree by the state coefficient obtained by the testing, judging whether the current management strategy is effective or not by the optimization degree, and selecting a corresponding processing mode for the management strategy according to a judging result. When the pasture management is abnormal, the abnormal conditions of the pasture can be adjusted and optimized as a whole, and the breeding state of the cows is improved. Thereby solving the technical problems in the background technology.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
An intelligent cow monitoring platform based on intelligent pasture comprises,
The data acquisition unit acquires cow breeding data by the sensor group, and constructs state coefficients by the current activity data and body temperature data of the cowsIf the state coefficientThe fluctuation range of the system exceeds the expected range, and an alarm instruction is sent to the outside;
The pattern recognition unit is used for training and obtaining a pattern recognition model, analyzing and recognizing the collected data by using the trained pattern recognition model, and obtaining the behavior pattern, the physiological state and the health index of the cow;
an abnormality analysis unit for determining corresponding target parameters from behavior patterns of the cows and constructing abnormality indexes according to changes of the target parameters If the obtained abnormality indexAn abnormality processing instruction is sent to the outside when the abnormality threshold value is exceeded; wherein, after identifying and acquiring the behavior mode of the cow, calculating and acquiring the fluctuation value of the corresponding representative parameter under the current behavior modeSelecting a fluctuation value from a plurality of representative parametersThe smallest parameter is taken as a target parameter; the method is as follows: the data values of the representative parameters are normalized in the following manner:
Wherein, M, m is the number of representative parameter data values,Is the mean value of the representative parameter data values,The data value of the ith that is a representative parameter;
Policy output unit for acquiring density of exception handling instructions from distribution state of exception handling instructions If the concentration of the exception handling instructions is highGiving a pasture management strategy by a pasture management knowledge graph beyond expectation;
the strategy optimization unit tests the output management strategy by the pasture management digital twin model, and the state coefficient obtained by the test Build optimalityBy degree of optimizationJudging whether the current management strategy is effective or not, and selecting a corresponding processing mode for the management strategy according to a judging result.
Further, a sensor group is arranged on the cow body or in the pasture, the sensor group collects behavior data, physiological data and environmental data of the cow in real time, and the collected data are summarized to construct a pasture running state data set; construction of state coefficients of cowsThe mode is as follows: activity on cropsBody temperaturePerforming linear normalization processing and mapping corresponding data values to intervalsIn the following manner:
Weight coefficient: ， And is also provided with ；，The number of cows; For the activity level of the ith cow, Is the average value of the activity level,Is a qualified standard value of activity; For the body temperature of the ith cow, Is the average value of the body temperature,Is a qualified standard value of body temperature.
Further, after receiving an alarm instruction, marking the sample data by taking data in a pasture running state data set and corresponding historical data as sample data, providing correct category or attribute information, constructing an initial model by a decision tree after preprocessing, feature extraction and data transformation, training the model by using the preprocessed data and marking information, and acquiring a trained mode recognition model after testing and optimizing; confirming the mode index related to the cow behavior mode, and outputting each behavior mode and the corresponding mode index.
Further, a plurality of monitoring nodes are arranged, data values of corresponding target parameters are obtained at the monitoring nodes, and an abnormality index is builtThe mode is as follows:
Wherein, P, p is the collection number of the target parameters,Is the firstThe values of the individual target parameters are chosen,For the corresponding mean value, the weight coefficients:， And (2) and 。
Further, after an exception handling instruction is received, current state data of the cow are identified, and corresponding exception characteristics are obtained; aiming at the abnormal behavior or abnormal state of the cow, acquiring abnormal condition processing schemes of a plurality of pasture cows, summarizing, constructing an abnormal condition processing measure library, and giving the abnormal condition processing scheme for the cow by the abnormal condition processing measure library according to the correspondence between the abnormal characteristics and the processing measures.
Further, the position information of each abnormal processing instruction is recorded, and the density of the abnormal processing instructions is calculatedIf the concentration of the exception handling instructions is highBeyond expectations, policy management instructions are issued externally in the following manner:
Wherein, In order to issue the number of exception handling instructions,Is the distance from the i-th exception handling instruction issue location to the j-th exception handling instruction issue location,Is the distance average of the outgoing locations.
Further, after receiving the policy management instruction, identifying each item of data in the pasture running state data set in a plurality of continuous monitoring periods to obtain corresponding pasture running characteristics; taking pasture management as a target word, and constructing a pasture management knowledge graph; and according to the correspondence between the pasture operation characteristics and the pasture management strategies, the pasture management strategies are given by the pasture management knowledge graphs.
Further, constructing a pasture management digital twin model, and performing simulation execution on the output management strategy by the pasture management digital twin model; after executing the management policy, build the optimalityBy degree of optimizationJudging whether the current management strategy is effective; if the degree of optimizationThe management policy is an effective policy exceeding the threshold of the optimization degree, and the management policy is executed; if not, the management policy is an invalid policy to optimizeAnd (3) taking the condition that the optimization degree threshold is exceeded as an optimization target, and optimizing the management strategy by using a strategy optimization model.
Further, the state coefficient of the observation node is obtainedState coefficients before and after the test execution environment management strategyOne by state coefficientBuild optimalityThe mode is as follows:
Wherein, For the optimality intermediate value at the i-th node,I is the node number for its mean value,N is the number of nodes,AndThe state coefficients at the i-th node before and after the optimization,AndIs the corresponding mean value.
A cow intelligent monitoring device based on an intelligent pasture at least comprises a receiving and transmitting unit, a processing unit, a storage unit and a data interface.
(III) beneficial effects
The invention provides a cow intelligent monitoring platform and device based on an intelligent pasture, which have the following beneficial effects:
1. constructing state coefficients of cows in pasture from activity and body temperature data of each cow The method comprises the steps of comprehensively evaluating the current state in the pasture on the whole environment, confirming whether the breeding state of cows in the pasture is abnormal, and sending an alarm instruction to the outside when the abnormality occurs, so that the comprehensive monitoring of the cows in the pasture is realized, and the occurrence of emergency is avoided.
2. By training and constructing a pattern recognition model, the current behavior pattern of the cow and the representative indexes under the corresponding pattern are rapidly recognized, and by monitoring a plurality of representative pattern indexes, whether the current state of the cow is abnormal or not can be judged according to the change of the pattern indexes.
3. According to abnormality indexThe method can judge whether the cow is abnormal at present, has higher accuracy and relatively smaller volatility when judging whether the cow is abnormal, and can rapidly process the cow to restore the cow to a normal state when confirming that the cow is abnormal to a certain extent by sending an abnormal processing instruction.
4. According to the current abnormal characteristics, an abnormal condition processing scheme is given for the abnormal cow by a pre-constructed abnormal condition processing measure library, and the abnormal condition processing scheme is used as a reference scheme, so that when the abnormal cow actually generates the abnormal condition, the abnormal condition can be rapidly processed, a temporary searching scheme is not needed, the temporary emergency processing efficiency is improved, and the temporary processing risk is reduced.
5. According to the concentration degreeIf the current pasture management is qualified, the current management strategy does not need to be adjusted, if the current pasture management is not qualified, a new management strategy is provided according to the current state of the pasture on the basis of matching with the pasture management knowledge graph, and when the pasture management is abnormal, the abnormal situation of the pasture can be adjusted and optimized as a whole, so that the breeding state of the cows is improved.
6. Constructing a pasture management digital twin model, performing simulation execution on an output management strategy by the pasture management digital twin model, and further constructing the optimization degree by test dataTo optimize degree ofWhether the output management strategy can be judged, and the reliability of the management strategy can be guaranteed through testing and optimizing the management strategy, so that the expected effect can be achieved when the management strategy is used for pasture management, and the efficiency of pasture management is improved.
Drawings
FIG. 1 is a schematic flow chart of the intelligent monitoring method of the cow of the invention;
FIG. 2 is a schematic diagram of the intelligent cow monitoring platform structure of the invention;
fig. 3 is a schematic structural diagram of the intelligent cow monitoring device of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
Referring to fig. 1 and 2, the present invention provides a cow intelligent monitoring platform based on intelligent pasture, comprising:
The data acquisition unit acquires cow breeding data by the sensor group, and constructs state coefficients by the current activity data and body temperature data of the cows If the state coefficientThe fluctuation range of the system exceeds the expected range, and an alarm instruction is sent to the outside;
when applied, the method comprises the following steps:
Step 101, when the health state and the growth state of cows in a farm are required to be monitored, a sensor group is installed on the cows or in pastures, wherein the sensor group comprises an activity monitor, a GPS tracker, a body temperature sensor, a rumen pH sensor and the like, the sensor group is used for collecting behavior data, physiological data, environmental data and the like of the cows in real time, and the collected data are summarized to construct a pasture running state data set;
step 102, combining current activity data and body temperature data of the pasture cows in the pasture running state data set to construct state coefficients of the cows, wherein the mode is as follows: activity on crops Body temperaturePerforming linear normalization processing and mapping corresponding data values to intervalsIn the following manner:
Weight coefficient: ， And is also provided with ；，The number of cows; For the activity level of the ith cow, Is the average value of the activity level,Is a qualified standard value of activity; For the body temperature of the ith cow, Is the average value of the body temperature,Is a qualified standard value of body temperature; obtaining a weight coefficient by a reference analytic hierarchy process;
Setting a monitoring period, for example, each monitoring period is 1 day, and acquiring state coefficients in the current monitoring period Comparing the current state of the pasture with a state coefficient in a previous monitoring period, and if the difference value between the current state of the pasture and the state coefficient is larger than the expected value, namely exceeds a preset difference value threshold value, indicating that the current state of the pasture is abnormal to a certain extent compared with the current state of the pasture, and sending an alarm instruction to the outside;
In use, the contents of steps 101 and 102 are combined:
When the cows in the pasture are managed, firstly, all data in the pasture are collected and arranged, and the state coefficients of the cows in the pasture are constructed according to the activity and body temperature data of all the cows According to state coefficientsThe method comprises the steps of comprehensively evaluating the current state in the pasture on the whole environment, confirming whether the breeding state of cows in the pasture is abnormal, and sending an alarm instruction to the outside when the abnormality occurs, so that the comprehensive monitoring of the cows in the pasture is realized, and the occurrence of emergency is avoided.
When monitoring the breeding state of cows in pastures, a plurality of groups of sensors or data acquisition devices are usually required to be installed, the cows and the environmental data are acquired, the current breeding state of the cows is evaluated and monitored according to the change of the acquired data, and the current management pasture management strategy is adjusted according to the monitoring and the corresponding analysis results; however, in the existing pasture monitoring platform, whether the breeding state of the cow is abnormal is judged mainly through data analysis and evaluation, and an alarm is given when the cow is abnormal, but a reasonable management strategy is difficult to give, so that emergency treatment can be carried out only on the current abnormal condition, and the pasture management is still lack of improvement on the whole.
The pattern recognition unit is used for training and obtaining a pattern recognition model, analyzing and recognizing the collected data by using the trained pattern recognition model, and obtaining the behavior pattern, the physiological state and the health index of the cow;
when applied, the method comprises the following steps:
Step 201, after receiving an alarm instruction, marking the sample data by taking data in a pasture running state data set and corresponding historical data as sample data, providing correct category or attribute information, constructing an initial model by a decision tree after preprocessing, feature extraction and data transformation, training the model by using the preprocessed data and marking information, and acquiring a trained mode recognition model after testing and optimizing;
Step 202, analyzing and identifying the collected data by using the trained pattern identification model, wherein the collected data are behavior patterns, physiological states and health indexes of the cow; behavioral patterns include, for example, feeding, resting, milking frequency, etc., and health conditions including, for example, estrus, pregnancy, illness, etc.; confirming mode indexes related to cow behavior modes through deep retrieval, and outputting all behavior modes and corresponding mode indexes;
In use, the contents of steps 201 and 202 are combined:
The method has the advantages that the activity data of the cows are collected through the sensor group, the current behavior mode of the cows and the representative indexes under the corresponding mode are rapidly identified through training and constructing the mode identification model, so that whether the current state of the cows is abnormal or not can be judged through monitoring a plurality of representative mode indexes according to the change of the mode indexes.
An abnormality analysis unit for determining corresponding target parameters from behavior patterns of the cows and constructing abnormality indexes according to changes of the target parametersIf the obtained abnormality indexAn abnormality processing instruction is sent to the outside when the abnormality threshold value is exceeded;
when applied, the method comprises the following steps:
step 301, after identifying the behavior pattern of the cow, for example, when the cow is in rest, selecting representative parameters, for example, body temperature, respiratory rate or heart rate, in the current behavior pattern, and calculating the fluctuation value of the representative parameters based on the fluctuation of the representative parameters The mode is as follows: the data values of the representative parameters are normalized in the following manner:
Wherein, M, m is the number of representative parameter data values,Is the mean value of the representative parameter data values,The data value of the ith that is a representative parameter;
selecting a fluctuation value from a number of representative parameters The smallest parameter is taken as a target parameter;
Step 302, setting a plurality of monitoring nodes when the cow is in the current behavior mode, and acquiring data values of corresponding target parameters at the monitoring nodes to further construct an abnormality index The mode is as follows:
Wherein, P, p is the collection number of the target parameters,Is the firstThe values of the individual target parameters are chosen,For the corresponding mean value, the weight coefficients:， And (2) and ; The weight coefficient value can be consistent with the previous value;
Setting an abnormal threshold for the target parameter according to the historical data and the health and abnormal behavior management expectation of the cow, if the obtained abnormal index If the abnormal threshold value is exceeded, it is indicated that the cow behavior may be abnormal, and therefore, when the abnormal behavior or health index of the cow is found to be abnormal, an abnormality processing instruction is issued to the outside;
when in use, the abnormality index is constructed based on the screening of the target parameters Thereby according to the abnormality indexThe method can judge whether the cow is abnormal at present, has higher accuracy and relatively smaller volatility when judging whether the cow is abnormal, and can rapidly process the cow to restore the cow to a normal state when confirming that the cow is abnormal to a certain extent by sending an abnormal processing instruction.
Step 303, after receiving the exception handling instruction, setting corresponding exception indexes for each parameter according to the management expectation of the cow; identifying current state data of the cow, including behavior data, physiological data, environmental data and the like, and acquiring corresponding abnormal characteristics; acquiring abnormal condition processing schemes of a plurality of pasture cows according to abnormal behaviors or abnormal states of the cows through offline formulation or online deep search, summarizing, constructing an abnormal condition processing measure library, and giving the abnormal condition processing schemes for the cows according to the correspondence between abnormal characteristics and processing measures by the abnormal condition processing measure library;
in use, the contents of steps 301 to 303 are combined:
When judging that the cow is abnormal currently, providing an abnormal situation processing scheme for the cow generating the abnormality by a pre-constructed abnormal situation processing measure library according to the current abnormal characteristics, and taking the abnormal situation processing scheme as a reference scheme, so that when the cow is abnormal actually, the processing can be performed rapidly, a temporary searching scheme is not needed any more, the temporary emergency processing efficiency is improved, and the temporary processing risk is reduced.
Policy output unit for acquiring density of exception handling instructions from distribution state of exception handling instructionsIf the concentration of the exception handling instructions is highGiving a pasture management strategy by a pasture management knowledge graph beyond expectation;
when applied, the method comprises the following steps:
Step 401, recording position information of each exception handling instruction in a current monitoring period, calculating the density of the exception handling instructions, and obtaining the density of the exception handling instructions The mode is as follows:
Wherein, In order to issue the number of exception handling instructions,Is the distance from the i-th exception handling instruction issue location to the j-th exception handling instruction issue location,Distance average value for the emission location;
Presetting a concentration threshold according to operation management expectation and historical data of pastures; if the concentration of the exception handling instructions is high If the current management strategy is over the expected value, namely the concentration threshold is exceeded, the situation that the cows in the pasture frequently generate abnormal conditions in the breeding and management process is described, management staff possibly have certain shortages on the management strategy of the pasture, the current management strategy needs to be corrected or a new management strategy is given, and at the moment, a strategy management instruction is sent to the outside;
step 402, after receiving a policy management instruction, identifying each item of data in a pasture running state data set in a plurality of continuous monitoring periods, and acquiring corresponding pasture running characteristics after characteristic extraction; taking pasture management as a target word, and constructing a pasture management knowledge graph after deep retrieval and construction of corresponding entity relations;
using the trained matching model, and giving a pasture management strategy by a pasture management knowledge graph according to the correspondence between the pasture operation characteristics and the pasture management strategy;
in use, the contents of steps 401 and 402 are combined:
after frequently receiving the exception handling instruction, evaluating the received intensity and obtaining the corresponding intensity According to the concentration degreeIf the current pasture management is qualified, the current management strategy does not need to be adjusted, if the current pasture management is not qualified, a new management strategy is provided according to the current state of the pasture on the basis of matching with the pasture management knowledge graph, and when the pasture management is abnormal, the abnormal situation of the pasture can be adjusted and optimized as a whole, so that the breeding state of the cows is improved.
The strategy optimization unit tests the output management strategy by the pasture management digital twin model, and the state coefficient obtained by the testBuild optimalityBy degree of optimizationJudging whether the current management strategy is effective or not, and selecting a corresponding processing mode for the management strategy according to a judging result;
when applied, the method comprises the following steps:
Step 501, using various data in a field running state data set and corresponding historical data and the like as sample data, using a convolutional neural network, constructing a pasture management digital twin model after training and optimizing, and performing simulation execution on an output management strategy by the pasture management digital twin model; setting an observation period comprising a plurality of observation nodes, and acquiring state coefficients of the observation nodes after executing a management strategy State coefficients before and after the test execution environment management strategyOne by state coefficientBuild optimalityThe mode is as follows:
Wherein, For the optimality intermediate value at the i-th node,I is the node number for its mean value,N is the number of nodes,AndThe state coefficients at the i-th node before and after the optimization,AndIs the corresponding average value;
step 502, presetting an optimization threshold for the prediction and corresponding historical data of pasture operation optimization management, and using the optimization Judging whether the current management strategy is effective; if the degree of optimizationIf the optimization degree threshold is exceeded, the current management strategy is indicated to have the expected effect, the management strategy is an effective strategy, and the management strategy is executed;
if the optimization degree is not more than the threshold value of the optimization degree, the current management strategy is not capable of playing the expected effect, the management strategy is an invalid strategy, and a strategy optimization model is built by an optimization algorithm to optimize the degree Optimizing the management strategy by using the strategy optimization model until the management strategy achieves the expected execution effect;
in use, the contents of steps 501 and 502 are combined:
After acquiring a new management strategy, in order to verify the feasibility of the management strategy, constructing a pasture management digital twin model, performing simulation execution on the output management strategy by the pasture management digital twin model, and further constructing the optimization degree by test data To optimize degree ofWhether the output management strategy can be judged, and the reliability of the management strategy can be guaranteed through testing and optimizing the management strategy, so that the expected effect can be achieved when the management strategy is used for pasture management, and the efficiency of pasture management is improved.
Referring to fig. 3, the invention provides a cow intelligent monitoring device based on an intelligent pasture, which at least further comprises a receiving and transmitting unit, a processing unit, a storage unit and a data interface.
It should be noted that:
the method for constructing pasture management knowledge graph can follow the following steps:
Explicitly constructing a target: first, it is necessary to specify the construction target of the knowledge graph. Pasture management involves a number of aspects including, but not limited to, employee management, animal health management, supply management, production planning management, safety production management, environmental protection management, and the like. The explicit goal helps to determine the range and depth of the knowledge-graph.
Collecting and arranging pasture management related knowledge: relevant knowledge of pasture management is collected from various sources (e.g., professional books, academic papers, industry reports, practice experiences, etc.). Such knowledge should include theoretical concepts, practical methods, case analysis, and the like.
Entity extraction and relationship definition: entities such as pastures, employees, animals, feeds, etc. are extracted from the collected knowledge and relationships between these entities are defined, such as employee employment relationships with pastures, animal feeding relationships with feeds, etc.
Constructing a knowledge graph frame: and constructing a framework of the knowledge graph based on the extracted entities and the defined relationship. This typically involves determining the hierarchical structure of the atlas, the taxonomy, and the manner of association between entities.
Filling and refining a knowledge graph: and filling the collected specific knowledge into a framework of the knowledge graph, and refining and enriching the entities and the relations. This may be accomplished by adding attributes, instances, descriptions, etc.
Verifying and correcting a knowledge graph: and verifying the constructed knowledge graph to ensure the accuracy and the integrity of the knowledge graph. Verification can be performed by expert review, practice inspection and the like, and necessary correction can be performed according to feedback.
And (5) visualizing and displaying a knowledge graph: and the knowledge graph is displayed in a graphical mode by utilizing the visualization tool, so that the knowledge graph is convenient for a user to browse and understand. Meanwhile, the system can also provide inquiry and navigation functions, and is convenient for a user to acquire the required information.
Through the steps, a comprehensive, accurate and easy-to-use pasture management knowledge graph can be constructed, and powerful knowledge support is provided for pasture management. It should be noted that the construction of the knowledge graph is a continuous process, and needs to be updated and perfected continuously with the development of pasture management practice.
It should be noted that:
The analytic hierarchy process, AHP for short, is one kind of decision making process, and has the core idea of decomposing elements relevant to decision making problem into target, criterion, scheme and other layers and qualitative and quantitative analysis based on the decomposed elements. This method is suitable for handling target systems with hierarchically interleaved evaluation indicators, especially when the target values are difficult to quantitatively describe.
The analytic hierarchy process is widely applied to the fields of decision analysis, syntactic structure analysis and the like. In decision analysis, the problems are decomposed into different composition factors, and the factors are aggregated and combined according to different levels according to the mutual correlation influence among the factors and the membership to form a multi-level analysis structure model, so that the problems are finally classified into the determination of the relative importance weight of the lowest level (scheme for decision, measure and the like) relative to the highest level (total target) or the arrangement of the relative priority order.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the elements is merely a division of some logic functions, and there may be additional divisions in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (8)
1. Cow intelligent monitoring platform based on wisdom pasture, its characterized in that: comprising the steps of (a) a step of,
The data acquisition unit acquires cow breeding data by the sensor group, and constructs state coefficients by the current activity data and body temperature data of the cowsIf the state coefficientThe fluctuation range of the system exceeds the expected range, and an alarm instruction is sent to the outside;
The pattern recognition unit is used for training and obtaining a pattern recognition model, analyzing and recognizing the collected data by using the trained pattern recognition model, and obtaining the behavior pattern, the physiological state and the health index of the cow;
an abnormality analysis unit for determining corresponding target parameters from behavior patterns of the cows and constructing abnormality indexes according to changes of the target parameters If the obtained abnormality indexAn abnormality processing instruction is sent to the outside when the abnormality threshold value is exceeded; wherein, after identifying and acquiring the behavior mode of the cow, calculating and acquiring the fluctuation value of the corresponding representative parameter under the current behavior modeSelecting a fluctuation value from a plurality of representative parametersThe smallest parameter is taken as a target parameter; the method is as follows: the data values of the representative parameters are normalized in the following manner:
Wherein, M, m is the number of representative parameter data values,Is the mean value of the representative parameter data values,The data value of the ith that is a representative parameter;
Policy output unit for acquiring density of exception handling instructions from distribution state of exception handling instructions If the concentration of the exception handling instructions is highGiving a pasture management strategy by a pasture management knowledge graph beyond expectation;
the strategy optimization unit tests the output management strategy by the pasture management digital twin model, and the state coefficient obtained by the test Build optimalityBy degree of optimizationJudging whether the current management strategy is effective or not, and selecting a corresponding processing mode for the management strategy according to a judging result, wherein a pasture management digital twin model is constructed, and the pasture management digital twin model is used for carrying out simulation execution on the output management strategy; after executing the management policy, build the optimalityBy degree of optimizationJudging whether the current management strategy is effective; if the degree of optimizationThe management policy is an effective policy exceeding the threshold of the optimization degree, and the management policy is executed; if not, the management policy is an invalid policy to optimizeThe management strategy is optimized by a strategy optimization model by taking the threshold exceeding the optimization degree as an optimization target;
Acquiring state coefficients of observation nodes State coefficients before and after the test execution environment management strategyOne by state coefficientBuild optimalityThe mode is as follows:
Wherein, For the optimality intermediate value at the i-th node,I is the node number for its mean value,N is the number of nodes,AndThe state coefficients at the i-th node before and after the optimization,AndIs the corresponding mean value.
2. The intelligent cow monitoring platform based on intelligent pasture as set forth in claim 1, wherein:
Installing a sensor group on a cow body or in a pasture, collecting behavior data, physiological data and environmental data of the cow in real time by the sensor group, summarizing the collected data, and constructing a pasture running state data set; construction of state coefficients of cows The mode is as follows: activity on cropsBody temperaturePerforming linear normalization processing and mapping corresponding data values to intervalsIn the following manner:
Weight coefficient: ， And is also provided with ；，The number of cows; For the activity level of the ith cow, Is the average value of the activity level,Is a qualified standard value of activity; For the body temperature of the ith cow, Is the average value of the body temperature,Is a qualified standard value of body temperature.
3. The intelligent cow monitoring platform based on intelligent pasture as set forth in claim 2, wherein:
After an alarm instruction is received, the data in the pasture running state data set and the corresponding historical data are used as sample data, the sample data are marked, correct category or attribute information is provided, an initial model is built by a decision tree after preprocessing, feature extraction and data transformation, the model is trained by using the preprocessed data and marking information, and a trained mode recognition model is obtained after testing and optimizing; confirming the mode index related to the cow behavior mode, and outputting each behavior mode and the corresponding mode index.
4. A cow intelligent monitoring platform based on intelligent pasture as set forth in claim 3, wherein:
Setting a plurality of monitoring nodes, acquiring data values of corresponding target parameters at the monitoring nodes, and further constructing an abnormality index The mode is as follows:
Wherein, P, p is the collection number of the target parameters,Is the firstThe values of the individual target parameters are chosen,For the corresponding mean value, the weight coefficients:， And (2) and 。
5. The intelligent cow monitoring platform based on intelligent pasture as set forth in claim 4, wherein:
After an exception handling instruction is received, identifying current state data of the cow, and acquiring corresponding exception characteristics; aiming at the abnormal behavior or abnormal state of the cow, acquiring abnormal condition processing schemes of a plurality of pasture cows, summarizing, constructing an abnormal condition processing measure library, and giving the abnormal condition processing scheme for the cow by the abnormal condition processing measure library according to the correspondence between the abnormal characteristics and the processing measures.
6. The intelligent cow monitoring platform based on intelligent pasture as set forth in claim 1, wherein:
recording position information of each exception handling instruction, and calculating the concentration of the exception handling instructions If the concentration of the exception handling instructions is highBeyond expectations, policy management instructions are issued externally in the following manner:
Wherein, In order to issue the number of exception handling instructions,Is the distance from the i-th exception handling instruction issue location to the j-th exception handling instruction issue location,Is the distance average of the outgoing locations.
7. The intelligent cow monitoring platform based on intelligent pasture as set forth in claim 6, wherein:
After receiving the strategy management instruction, identifying various data in a pasture running state data set in a plurality of continuous monitoring periods to obtain corresponding pasture running characteristics; taking pasture management as a target word, and constructing a pasture management knowledge graph; and according to the correspondence between the pasture operation characteristics and the pasture management strategies, the pasture management strategies are given by the pasture management knowledge graphs.
8. A cow intelligent monitoring device based on intelligent pasture for executing the platform according to any one of claims 1-7, characterized in that: the device at least comprises a receiving and transmitting unit, a processing unit, a storage unit and a data interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667982.3A CN118235723B (en) | 2024-05-28 | 2024-05-28 | Cow intelligent monitoring platform and device based on wisdom pasture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410667982.3A CN118235723B (en) | 2024-05-28 | 2024-05-28 | Cow intelligent monitoring platform and device based on wisdom pasture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118235723A CN118235723A (en) | 2024-06-25 |
| CN118235723B true CN118235723B (en) | 2024-07-19 |
Family
ID=91564024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410667982.3A Active CN118235723B (en) | 2024-05-28 | 2024-05-28 | Cow intelligent monitoring platform and device based on wisdom pasture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118235723B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118614413B (en) * | 2024-08-13 | 2024-11-08 | 四川农业大学 | Sensing device of grazing mother-son machine and abnormal livestock monitoring method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920719A (en) * | 2018-07-30 | 2018-11-30 | 合肥康之恒机械科技有限公司 | A kind of raising pets health omnibearing management method and system |
| CN117541291A (en) * | 2023-11-22 | 2024-02-09 | 贵州电力交易中心有限责任公司 | Electricity price prediction method and system based on EMD decomposition and SSA-SVM model |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170032153A (en) * | 2015-09-14 | 2017-03-22 | (주)빌리언이십일 | Control method and apparatus of The ecological environment of the fish farm |
| CN118070053A (en) * | 2024-03-01 | 2024-05-24 | 江西欧易科技有限公司 | Remote management device and method for rotational molding machine supporting multi-user cooperation |
-
2024
- 2024-05-28 CN CN202410667982.3A patent/CN118235723B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920719A (en) * | 2018-07-30 | 2018-11-30 | 合肥康之恒机械科技有限公司 | A kind of raising pets health omnibearing management method and system |
| CN117541291A (en) * | 2023-11-22 | 2024-02-09 | 贵州电力交易中心有限责任公司 | Electricity price prediction method and system based on EMD decomposition and SSA-SVM model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118235723A (en) | 2024-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3939418B1 (en) | Automated livestock management system | |
| CN109145032A (en) | A kind of bee raising intelligent monitoring method and system | |
| CN109840549A (en) | A kind of pest and disease damage recognition methods and device | |
| CN118235723B (en) | Cow intelligent monitoring platform and device based on wisdom pasture | |
| Feiyang et al. | Monitoring behavior of poultry based on RFID radio frequency network | |
| CN116934088B (en) | Intelligent pigeon breeding management method and system based on analysis model | |
| Othman et al. | Automated water quality monitoring system development via LabVIEW for aquaculture industry (Tilapia) in Malaysia | |
| CN115660291A (en) | Plant disease occurrence and potential occurrence identification and evaluation method and system | |
| Syarif et al. | Health monitoring and early diseases detection on dairy cow based on internet of things and intelligent system | |
| CN118211810B (en) | Intelligent farm operation management alarm system and method | |
| CN117473446B (en) | Anomaly detection and processing method and system based on deep learning | |
| CN116843529A (en) | Method and system for monitoring and evaluating health of wetland ecosystem based on remote sensing data | |
| CN115147000A (en) | Method for evaluating environment suitability of laying hen house based on variable selection optimization and AHP | |
| CN115359050A (en) | Method and device for detecting abnormal feed intake of livestock | |
| CN114428810B (en) | Animal survival state early warning method, system and equipment | |
| CN118131844B (en) | Animal greenhouse management system based on internet of things data identification | |
| CN118887033A (en) | Monitoring data processing system for cultivation equipment | |
| Cassimiro et al. | Milk weighing scale based on machine learning | |
| CN117764760A (en) | Biological asset intelligent monitoring and protecting management system for livestock in animal husbandry | |
| KR102590406B1 (en) | Biometric authentication apparatus based on livestock growth | |
| Chen et al. | A prediction model for piggery ammonia concentration based on least squares support vector regression using fruit fly optimisation algorithm | |
| Samantaray et al. | Efficient Smart Farm System Using Machine Learning | |
| CN116487028A (en) | Livestock health state monitoring method, device, storage medium and system | |
| CN118901610A (en) | Electronic ear tag monitoring method and system for livestock | |
| CN118177095A (en) | Livestock electronic ear tag with low energy consumption and using method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |