CN110209839A - Agricultural knowledge map construction device, method and computer readable storage medium - Google Patents
Agricultural knowledge map construction device, method and computer readable storage medium Download PDFInfo
- Publication number
- CN110209839A CN110209839A CN201910528268.5A CN201910528268A CN110209839A CN 110209839 A CN110209839 A CN 110209839A CN 201910528268 A CN201910528268 A CN 201910528268A CN 110209839 A CN110209839 A CN 110209839A
- Authority
- CN
- China
- Prior art keywords
- agriculture
- corpus
- entity
- knowledge map
- agricultural knowledge
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of agricultural knowledge map construction method, comprising: obtain the agriculture field data of a target area, and the agriculture field data based on acquisition construct corpus；It carries out participle to the corpus in the corpus to handle with part-of-speech tagging, to identify multiple entitative concepts；The entitative concept identified is screened according to default screening rule to obtain multiple agriculture entities；Parsing is carried out to the corpus in the corpus to extract with relationship, obtains the incidence relation between multiple agriculture entities；And according to the incidence relation between each agriculture entity and each agriculture entity, establish agricultural knowledge map.The present invention also provides a kind of agricultural knowledge map construction device and computer readable storage mediums.Above-mentioned agricultural knowledge map construction device, method and computer readable storage medium are, it can be achieved that construct agricultural knowledge map, the convenience that promotion agriculture field data management efficiency and data use for agriculture field.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of agricultural knowledge map construction devices, method and meter
Calculation machine readable storage medium storing program for executing.
Background technique
Knowledge mapping has powerful data descriptive power, provides technical foundation for intelligent information application, passes through
Implementation of inference conceptual retrieval, while structural knowledge can be presented to user in a manner of patterned.Knowledge mapping is in multiple necks
Domain has application, such as medical treatment, finance, education, investment etc. to have industry existing for relationship.But not yet there is mature agriculture at present
Industry knowledge mapping building mode.
Summary of the invention
In view of this, it is necessary to provide a kind of agricultural knowledge map construction device, method and computer readable storage medium,
It, which can be realized, constructs agricultural knowledge map for agriculture field, and it is convenient that promotion agriculture field data management efficiency and data use
Property.
An embodiment of the present invention provides a kind of agricultural knowledge map construction method, which comprises obtains a target
The agriculture field data in region, and the agriculture field data based on acquisition construct corpus；To the corpus in the corpus into
Row participle is handled with part-of-speech tagging, to identify multiple entitative concepts；According to default screening rule to the entitative concept identified
It is screened to obtain multiple agriculture entities；Parsing is carried out to the corpus in the corpus to extract with relationship, is obtained multiple described
Incidence relation between agriculture entity；It is closed according to the association between each agriculture entity and each agriculture entity
System, establishes agricultural knowledge map；It swashes from network the encyclopaedia information obtained to each agriculture entity；It is advised based on default extraction
Then the encyclopaedia content of pages crawled is extracted, and be added to the corpus and/or institute for obtained content is extracted
State agricultural knowledge map；Similarity analysis is carried out to the encyclopaedia content of pages crawled, obtains each agriculture entity
Classification information；And the classification information of each agriculture entity is added to the agricultural knowledge map；
Wherein, the step of described pair of encyclopaedia content of pages crawled carries out similarity analysis includes: to extract each institute
State multiple specific characteristics in encyclopaedia content of pages；It is calculated between any two encyclopaedia content of pages using KNN algorithm
The similarity of each feature group；And the similarity for the multiple feature groups being calculated is weighted to obtain described any two
The comprehensive similarity of a encyclopaedia content of pages.
Preferably, the agriculture field data include non-structured agriculture field data and semi-structured agriculture field
Data.
Preferably, the corpus in the corpus carries out participle and part-of-speech tagging processing, to identify multiple realities
The step of body concept includes:
Participle is carried out to the corpus in the corpus using default lexical analysis tool to handle with part-of-speech tagging；And
Entity recognition is named to the result of part-of-speech tagging, to identify multiple entitative concepts.
Preferably, the corpus in the corpus carries out parsing and relationship extraction, and it is real to obtain multiple agriculturals
Incidence relation between body:
Corpus in the corpus is parsed to obtain morphological information, syntactic information and semantic information；And
Obtained morphological information, syntactic information and the semantic information that parse is input to relationship extraction mould trained in advance
Type obtains the incidence relation between multiple agriculture entities.
Preferably, the incidence relation according between each agriculture entity and each agriculture entity, builds
The step of vertical agricultural knowledge map includes:
Incidence relation between the name identification of each agriculture entity and each agriculture entity is directed into
Preset pattern database, and carry out visualization and be converted to the agricultural knowledge map.
An embodiment of the present invention provides a kind of agricultural knowledge map construction device, the agricultural knowledge map construction device
Including processor and memory, several computer programs are stored on the memory, the processor is for executing memory
The step of above-mentioned agricultural knowledge map construction method is realized when the computer program of middle storage.
An embodiment of the present invention also provides a kind of computer readable storage medium, and the computer readable storage medium is deposited
A plurality of instruction is contained, a plurality of described instruction can be executed by one or more processor, to realize above-mentioned agricultural knowledge map
The step of construction method.
Compared with prior art, above-mentioned agricultural knowledge map construction device, method and computer readable storage medium, can be with
It realizes the agricultural knowledge map in one specified region of building, promotes the convenience that agriculture field data management efficiency and data use,
Peasant can be assisted to carry out crop production, enterprise procurement, for public science popularization agricultural knowledge.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the agricultural knowledge map construction device of an embodiment of the present invention.
Fig. 2 is the functional block diagram of the agricultural knowledge map construction system of an embodiment of the present invention.
Fig. 3 is the functional block diagram of the agricultural knowledge map construction system of another embodiment of the present invention.
Fig. 4 is that the feature that the agriculture entity of an embodiment of the present invention is the encyclopaedia content of pages of pea divides schematic diagram.
Fig. 5 is the reasoning schematic diagram of the agricultural knowledge question and answer of an embodiment of the present invention.
Fig. 6 is the flow chart of the agricultural knowledge map construction method of an embodiment of the present invention.
Main element symbol description
The present invention that the following detailed description will be further explained with reference to the above drawings.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
Explanation is needed further exist for, herein, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that process, method, article or device including a series of elements are not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or device
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or device including the element.
Referring to Fig. 1, being the schematic diagram of agricultural knowledge map construction device preferred embodiment of the present invention.
The agricultural knowledge map construction device 100 is including memory 10, processor 20 and is stored in the memory
In 10 and the computer program 30 that can be run on the processor 20, such as agricultural knowledge map construction program.The processing
Device 20 realizes the step in agricultural knowledge map construction embodiment of the method when executing the computer program 30, such as shown in Fig. 6
Step S600~S608.Alternatively, the processor 20 realizes agricultural knowledge map construction when executing the computer program 30
The function of each module in system embodiment, such as the module 101~105 in Fig. 2 or the module in Fig. 3 101~107.
The computer program 30 can be divided into one or more modules, and one or more of modules are stored
It is executed in the memory 10, and by the processor 20, to complete the present invention.One or more of modules can be energy
The series of computation machine program instruction section of specific function is enough completed, described instruction section is for describing the computer program 30 in institute
State the implementation procedure in agricultural knowledge map construction device 100.For example, the computer program 30 can be divided into Fig. 2
Acquisition module 101, processing module 102, screening module 103, parsing module 104 and establish module 105, or be divided into figure
Acquisition module 101, processing module 102, screening module 103 in 3, establish module 105, categorization module 106 at parsing module 104
And adding module 107.Each module concrete function referring to each module in agricultural knowledge map construction system embodiment function.
The agricultural knowledge map construction device 100 can be computer, server etc. and calculate equipment.Those skilled in the art
It is appreciated that the schematic diagram is only the example of agricultural knowledge map construction device 100, do not constitute to agricultural knowledge map structure
The restriction for building device 100 may include perhaps combining certain components or different portions than illustrating more or fewer components
Part, such as the agricultural knowledge map construction device 100 can also include input-output equipment, network access equipment, bus etc..
Alleged processor 20 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor 20 is also possible to any conventional processing
Device etc., the processor 20 can use the various pieces of various interfaces and connection agricultural knowledge map construction device 100.
The memory 10 can be used for storing the computer program 30 and/or module, and the processor 20 passes through operation
Or the computer program and/or module being stored in the memory 10 are executed, and call the number being stored in memory 10
According to realizing the various functions of the agricultural knowledge map construction device 100.The memory 10 may include high random access
Memory can also include nonvolatile memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart
Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), at least one disk
Memory device, flush memory device or other volatile solid-state parts.
Fig. 2 is the functional block diagram of agricultural knowledge map construction system preferred embodiment of the present invention.
As shown in fig.2, agricultural knowledge map construction system 40 may include obtaining module 101, processing module 102, sieve
Modeling block 103, parsing module 104 and establish module 105.In one embodiment, above-mentioned module can be to be stored in described deposit
In reservoir 10 and the programmable software instruction executed can be called by the processor 20.It is understood that in other implementations
In mode, above-mentioned module can also be to solidify program instruction or firmware (firmware) in the processor 20.
The agriculture field data for obtaining module 101 and being used to obtain a target area, and the agriculture field based on acquisition
Data construct corpus.
In one embodiment, the target area can be set according to actual use demand, than if necessary
The agricultural knowledge map in a specified city is established, then the agriculture field data of the target area can be the agriculture field in the specified city
If desired data establish the agricultural knowledge map in a specified county, then it is specified to can be this for the agriculture field data of the target area
The agriculture field data in county.The agriculture field data can be unstructured data, semi-structured data, described unstructured
Data such as can be agricultural product picture, audio, video, and it includes agricultural data that the semi-structured data, which such as can be,
XML, JSON include the agriculture encyclopaedia page of agricultural data.The agriculture field data include but is not limited to vegetables data, water
Fruit data, seed data, herding data, poultry data, aquatic products data, chemical fertilizer data, feed data, weather data, natural calamity
Evil data etc..
In one embodiment, the mode for obtaining the acquisition agriculture field data of module 101 includes but is not limited to pass through
Web crawlers technology accesses the agriculture commercial data base bought, industry research report, uses open agricultural data collection, uses
Search engine etc..After the acquisition module 101 acquires the agriculture field data of target area, to the agricultural acquired
FIELD Data is pre-processed to construct corpus.The pretreatment such as refers to unstructured data and semi-structured data
It is handled to obtain corpus, then collects the corpus that processing obtains to construct the corpus.
The processing module 102 is used to carry out the corpus in the corpus participle and handles with part-of-speech tagging, with identification
Multiple entitative concepts out.
In one embodiment, the processing module 102 can use default lexical analysis tool in the corpus
Corpus carry out participle and handled with part-of-speech tagging, then Entity recognition is named to the result of part-of-speech tagging, it is multiple to identify
Entitative concept.
For example, the processing module 102 is using Thulac Chinese lexical analysis kit in the corpus
Corpus carries out participle and handles with part-of-speech tagging, when being identified as name entity, is marked out by default come non-when being identified as
Entity is named, without mark.
The screening module 103 is used to be screened to obtain to the entitative concept identified according to default screening rule multiple
Agriculture entity.
In one embodiment, the agriculture entity can be the entity for belonging to agriculture field, for example, the agricultural entity
It can be vegetables entity, fruit entity, kind fructification, herding entity, poultry entity, aquatic products entity etc..Since multiple entities are general
It may include non-agricultural entity in thought, the screening module 103 is also according to default screening rule to the entitative concept identified
It is screened to obtain multiple agriculture entities.The default screening rule can be set according to actual use demand, for example, institute
Stating default screening rule can be keyword screening, or scan obtained entity using default word combination and part-of-speech rule
Concept, and then to filter out the part for not being agriculture entity.The part-of-speech rule is such as: if verb, then assert it is not agriculture
Industry entity.
The parsing module 104 is used to carry out the corpus in the corpus parsing and extracts with relationship, obtains multiple institutes
State the incidence relation between agriculture entity.
In one embodiment, the parsing module 104 can parse the progress sentence of the corpus in the corpus
To morphological information, syntactic information and semantic information, recycle relationship trained in advance extract model to the morphological information being resolved to,
Syntactic information and semantic information are analyzed, to obtain the incidence relation between multiple agriculture entities.
In one embodiment, when parsing to a corpus, the parsing module 104 can be by generating the corpus
Parsing tree obtain the morphological information and syntactic information of the corpus, can be analyzed to obtain by the structure to corpus
The semantic information of the corpus.
In one embodiment, it can be obtained by the way of remote supervisory for training the relationship to extract model
Training sample data, for example existing knowledge can be corresponded in unstructured corpus, to generate a large amount of training sample
Data are then based on training sample data and machine learning algorithm to train to obtain the relationship and extract model, the engineering
Practising algorithm can be neural network algorithm, inductive algorithm.The source of those knowledge can be artificial mark, existing knowledge base or
Specific sentence structure.For example, it may be considered a kind of specified, such as specified " A is B " structure for specific sentence structure
For subclass relation, then A- subclass relation-B.Such as " banana is a kind of tropical fruit (tree) ", it is obtained by particular statement structure elucidation:
Banana-subclass relation-tropical fruit (tree).
The module 105 of establishing is for according to the association between each agriculture entity and each agriculture entity
Relationship establishes agricultural knowledge map.
In one embodiment, described to establish module after the incidence relation between each agriculture entity is established
105 can establish to obtain the agricultural according to the incidence relation between each agriculture entity and each agriculture entity
Knowledge mapping.
It in one embodiment, include vegetables entity, fruit entity, herding entity, aquatic products entity with the agriculture entity
And for chemical fertilizer entity, the building agricultural knowledge map can be accomplished by the following way in the module 105 of establishing: described
It establishes module 105 and obtains the name identification of vegetables entity, fruit entity, herding entity, aquatic products entity and chemical fertilizer entity, and be based on
The vegetables entity of acquisition, fruit entity, herding entity, aquatic products entity and chemical fertilizer entity name identification construct agricultural knowledge map
Frame, then the incidence relation between each agriculture entity is filled to the agricultural knowledge map frame, it obtains the agricultural and knows
Know map.
In one embodiment, it is described establish module 105 can also by the name identification of each agriculture entity and
Incidence relation between each agriculture entity is directed into preset pattern database, and by the preset pattern data can
The agricultural knowledge map is converted to depending on changing.For example, the preset pattern database can be Noe4j graphic data base, institute
It states and establishes module 105 and lead the incidence relation between the name identification of each agriculture entity and each agriculture entity
Enter to Noe4j graphic data base and visualized, the agricultural knowledge map can be generated.
Please refer to Fig. 3, compared with Fig. 2, the agricultural knowledge map construction system 40 further include categorization module 106 and
Adding module 107.
The categorization module 106 is used to swash from network the encyclopaedia information obtained to each agriculture entity, and to climbing
The encyclopaedia content of pages obtained carries out similarity analysis, obtains the classification information of each agriculture entity.
In one embodiment, for being identified as the entry of agriculture entity, the categorization module 106 can be in interaction hundred
It is crawled to obtain the encyclopaedia information of each agriculture entity in encyclopaedia website disclosed in section/Baidupedia etc., abandons and do not deposit
The page or mistake the page, then similarity analysis is carried out to the encyclopaedia content of pages that crawls, obtained each described
The classification information of agriculture entity.
In one embodiment, the categorization module 106 can be extracted to obtain each encyclopaedia page according to encyclopaedia content of pages
Multiple specific characteristics of face content, recycling are closed on algorithm (KNN algorithm) and are calculated between any two encyclopaedia content of pages
Each feature group similarity, and the similarity for the multiple feature groups being calculated is weighted to obtain described any
The comprehensive similarity of two encyclopaedia content of pages is to get to the comprehensive of two corresponding with two encyclopaedia content of pages agriculture entities
Similarity is closed, realizes the classification for going out agriculture entity B by the category inferences of agriculture entity A.For example, each encyclopaedia content of pages
In include first to third specific characteristic, the similarity of each feature group can be the first specified spy of two encyclopaedia content of pages
The similarity between similarity, the second specific characteristic between sign, the similarity between third specific characteristic.
It is assumed that agriculture entity is pea, Fig. 4 illustrates the encyclopaedia content of pages of pea.The hundred of the pea
Section's content of pages includes four specific characteristics, wherein the first specific characteristic is title, the second specific characteristic is open classification, third
Specific characteristic is brief introduction, the 4th specific characteristic is essential information.The categorization module 106 calculates two by KNN algorithm
The mode of similarity between encyclopaedia content of pages may is that the cosine of the term vector between a) two groups of calculating of " titles " is similar
Degree；B) calculates the cosine similarity of the term vector between two groups " open classification "；C) is calculated in two groups " essential informations " and is repeated
The number of item, to obtain a similarity；D) calculates the coincidence factor of two groups " brief introduction "；E) is by the operation result of above-mentioned a-d
It is weighted to obtain the comprehensive similarity between two encyclopaedia content of pages.
It is understood that can corresponding weight coefficient be arranged in advance for first to fourth specific characteristic, and then can be with
It is similar to the operation result of a-d to be weighted to obtain the synthesis between two encyclopaedia content of pages according to weight coefficient
Degree.
The adding module 107 is used to the classification information of each agriculture entity being added to the agricultural knowledge figure
Spectrum.
In one embodiment, the classification information of each agriculture entity can be added to by the adding module 107
The agricultural knowledge map, and then agricultural knowledge general view function and agriculture entity classification tree function may be implemented.
In one embodiment, the adding module 107 is also based on default extracting rule to the encyclopaedia crawled
Content of pages extracts, and is added to the corpus for obtained content is extracted.The default extracting rule can be needle
The specified region content of the encyclopaedia page is extracted.In other embodiments of the invention, the adding module 107 may be used also
To extract based on default extracting rule to the encyclopaedia content of pages crawled, and institute is added to by obtained content is extracted
State agricultural knowledge map.
In one embodiment, in order to ensure the accuracy of the agricultural knowledge map, default update can be set and advised
Then the agricultural knowledge map is updated.The presupposed information updates rule can be set according to actual use demand
It is fixed, for example it may include monthly updating the primary agricultural knowledge map that the presupposed information, which updates rule,.
In one embodiment, it can use the obtained agricultural knowledge map of establishing and realize following functions:
1) agricultural Entity recognition function may be implemented to identify agriculture entity and its agriculture in non-structured text
Type.For example, a certain non-structured text content are as follows: " chemical fertilizer abbreviation chemical fertilizer.It is made of chemistry and (or) physical method
The nutrient needed containing one or more of crop growths fertilizer, also referred to as inorganic fertilizer, including ammonia fertilizer, phosphate fertilizer, potassium
Fertile, micro- fertilizer, composite chemical fertilizer etc..Pass through the available recognition result of agricultural knowledge map are as follows:Chemical fertilizerReferred to asChemical fertilizer。
Contain one or more made of chemistry and (or) physical methodCropsWhat growth neededNutrient'sFertilizer, also referred to asNothing Machine fertilizer, includingAmmonia fertilizer、Phosphate fertilizer、Potash fertilizer、Micro- fertilizer、Composite chemical fertilizerDeng.Wherein, scribing line content is the entity of identification.
2) agricultural entity encyclopaedia function can show the information such as essential information, the type of farming of agriculture entity.For example it looks into
The agriculture entity of inquiry be " pea ", the agricultural knowledge map can show encyclopaedia entry " https: //
Pea/822636 baike.baidu.com/item/? part/full content shown by fr=aladdin ".
3) agricultural knowledge general view function may be implemented to sort out agricultural knowledge.For example, fruit is returned
Class.
Classification special topic: fruit
Higher level's classification: the edible plant of food agricultural-
Junior's classification:
Types of fruits
In one embodiment, classification can also be carried out with fruit title initial to show.Such as:
4) agriculture entity class is organized into tree and is shown by agricultural entity classification tree function, realization.Citing and
Speech is that root node carries out tree displaying with agricultural, can be obtained:
Agricultural
5) associated entity query function, input entity can be inquired to obtain entity and relation information associated therewith.It lifts
For example, the agriculture entity of input is banana, and following information can be obtained:
| Entity 1 | Relationship | Entity 2 |
| Banana | Subclass relation | Berry |
| Banana | Subclass relation | Fruit |
| Banana | Subclass relation | Fruit tree in many tropical and subtropical countries |
| Banana | It is different from | Plantain |
| Banana | Color | Yellow |
| Banana | Color | Brown |
| Banana | Color | It is red |
| Banana | Color | Green |
| Banana | The natural product of taxon | Musa |
| Banana | The natural product of taxon | Fruitlet open country any of several broadleaf plants hybridizes wild any of several broadleaf plants |
| …… | …… | …… |
6) the agricultural knowledge problem of input is answered in agricultural knowledge question and answer function, realization.For example, problem is
" suitable kind of Fuyang City Taihe County what? " reasoning foundation according to figure 5, available answer is: beech walnut broad-leaved
Set Mongolian oak liana Acer.
Fig. 6 is the flow chart of agriculture knowledge mapping construction method in an embodiment of the present invention.Institute according to different requirements,
The sequence for stating step in flow chart can change, and certain steps can be omitted.
Step S600 obtains the agriculture field data of a target area, and the agriculture field data based on acquisition construct language
Expect library.
Step S602 carries out participle to the corpus in the corpus and handles with part-of-speech tagging, to identify multiple entities
Concept.
Step S604 screens the entitative concept identified according to default screening rule to obtain multiple agriculture entities.
Step S606 carries out parsing to the corpus in the corpus and extracts with relationship, obtains multiple agriculture entities
Between incidence relation.
Step S608 is established according to the incidence relation between each agriculture entity and each agriculture entity
Agricultural knowledge map.
It is specified that building one may be implemented in above-mentioned agricultural knowledge map construction device, method and computer readable storage medium
The agricultural knowledge map in region promotes the convenience that agriculture field data management efficiency and data use, can assist peasant into
Row crop production, enterprise procurement, for public science popularization agricultural knowledge.
It will be apparent to those skilled in the art that the reality of production can be combined with scheme of the invention according to the present invention and inventive concept
Border needs to make other and is altered or modified accordingly, and these change and adjustment all should belong to range disclosed in this invention.
Claims (7)
1. a kind of agricultural knowledge map construction method, which is characterized in that the described method includes:
The agriculture field data of a target area are obtained, and the agriculture field data based on acquisition construct corpus；
It carries out participle to the corpus in the corpus to handle with part-of-speech tagging, to identify multiple entitative concepts；
The entitative concept identified is screened according to default screening rule to obtain multiple agriculture entities；
It carries out parsing to the corpus in the corpus to extract with relationship, the association obtained between multiple agriculture entities is closed
System；
According to the incidence relation between each agriculture entity and each agriculture entity, agricultural knowledge map is established；
It swashes from network the encyclopaedia information obtained to each agriculture entity；
The encyclopaedia content of pages crawled is extracted based on default extracting rule, and is added to obtained content is extracted
The corpus and/or the agricultural knowledge map；
Similarity analysis is carried out to the encyclopaedia content of pages crawled, obtains the classification information of each agriculture entity；And
The classification information of each agriculture entity is added to the agricultural knowledge map；
Wherein, the step of described pair of encyclopaedia content of pages that crawls carries out similarity analysis include:
Extract multiple specific characteristics in each encyclopaedia content of pages；
The similarity of each feature group between any two encyclopaedia content of pages is calculated using KNN algorithm；And
The similarity for the multiple feature groups being calculated is weighted to obtain any two encyclopaedia content of pages
Comprehensive similarity.
2. the method as described in claim 1, which is characterized in that the agriculture field data include non-structured agriculture field
Data and semi-structured agriculture field data.
3. method according to claim 1 or 2, which is characterized in that the corpus in the corpus carry out participle with
Part-of-speech tagging processing, to identify multiple entitative concepts the step of include:
Participle is carried out to the corpus in the corpus using default lexical analysis tool to handle with part-of-speech tagging；And
Entity recognition is named to the result of part-of-speech tagging, to identify multiple entitative concepts.
4. the method as described in claim 1, which is characterized in that the corpus in the corpus carries out parsing and relationship
The step of extracting, obtaining the incidence relation between multiple agriculture entities include:
Corpus in the corpus is parsed to obtain morphological information, syntactic information and semantic information；And
Obtained morphological information, syntactic information and the semantic information that parse is input to relationship extraction model trained in advance,
Obtain the incidence relation between multiple agriculture entities.
5. the method as described in claim 1, which is characterized in that described according to each agriculture entity and each agriculture
Incidence relation between industry entity, the step of establishing agricultural knowledge map include:
Incidence relation between the name identification of each agriculture entity and each agriculture entity is directed into default
Graphic data base, and carry out visualization and be converted to the agricultural knowledge map.
6. a kind of agricultural knowledge map construction device, described device includes processor and memory, is stored on the memory
Several computer programs, which is characterized in that realized such as when the processor is for executing the computer program stored in memory
The step of claim 1-5 described in any item agricultural knowledge map construction methods.
7. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has a plurality of instruction,
A plurality of described instruction can be executed by one or more processor, to realize that agricultural as described in any one in claim 1-5 is known
The step of knowing map construction method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910528268.5A CN110209839B (en) | 2019-06-18 | 2019-06-18 | Agricultural knowledge graph construction device and method and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910528268.5A CN110209839B (en) | 2019-06-18 | 2019-06-18 | Agricultural knowledge graph construction device and method and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110209839A true CN110209839A (en) | 2019-09-06 |
| CN110209839B CN110209839B (en) | 2021-07-27 |
Family
ID=67793313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910528268.5A Active CN110209839B (en) | 2019-06-18 | 2019-06-18 | Agricultural knowledge graph construction device and method and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110209839B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488741A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Tax knowledge data semantic annotation method and related device |
| CN111507758A (en) * | 2020-04-09 | 2020-08-07 | 深圳传世智慧科技有限公司 | Semantic analysis-based investigation method, device, system and server |
| CN112199508A (en) * | 2020-08-10 | 2021-01-08 | 淮阴工学院 | Parameter adaptive agricultural knowledge graph recommendation method based on remote supervision |
| CN112329468A (en) * | 2020-11-03 | 2021-02-05 | 中国平安财产保险股份有限公司 | Method and device for constructing heterogeneous relation network, computer equipment and storage medium |
| CN112465287A (en) * | 2019-09-09 | 2021-03-09 | 国际商业机器公司 | Improving farm farming quality |
| CN113010529A (en) * | 2019-12-19 | 2021-06-22 | 广州极飞科技股份有限公司 | Crop management method and device based on knowledge graph |
| CN113220827A (en) * | 2021-04-23 | 2021-08-06 | 哈尔滨工业大学 | Construction method and device of agricultural corpus |
| CN113761971A (en) * | 2020-06-02 | 2021-12-07 | 中国人民解放军战略支援部队信息工程大学 | Method and device for constructing target knowledge graph of remote sensing image |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484461A (en) * | 2014-12-29 | 2015-04-01 | 北京奇虎科技有限公司 | Method and system based on encyclopedia data for classifying entities |
| CN106250412A (en) * | 2016-07-22 | 2016-12-21 | 浙江大学 | The knowledge mapping construction method merged based on many source entities |
| CN106776711A (en) * | 2016-11-14 | 2017-05-31 | 浙江大学 | A kind of Chinese medical knowledge mapping construction method based on deep learning |
| CN106815293A (en) * | 2016-12-08 | 2017-06-09 | 中国电子科技集团公司第三十二研究所 | System and method for constructing knowledge graph for information analysis |
| US20180025008A1 (en) * | 2016-07-20 | 2018-01-25 | Baidu Usa Llc | Systems and methods for homogeneous entity grouping |
| CN108804521A (en) * | 2018-04-27 | 2018-11-13 | 南京柯基数据科技有限公司 | A kind of answering method and agricultural encyclopaedia question answering system of knowledge based collection of illustrative plates |
| CN108984661A (en) * | 2018-06-28 | 2018-12-11 | 上海海乂知信息科技有限公司 | Entity alignment schemes and device in a kind of knowledge mapping |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
-
2019
- 2019-06-18 CN CN201910528268.5A patent/CN110209839B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484461A (en) * | 2014-12-29 | 2015-04-01 | 北京奇虎科技有限公司 | Method and system based on encyclopedia data for classifying entities |
| US20180025008A1 (en) * | 2016-07-20 | 2018-01-25 | Baidu Usa Llc | Systems and methods for homogeneous entity grouping |
| CN106250412A (en) * | 2016-07-22 | 2016-12-21 | 浙江大学 | The knowledge mapping construction method merged based on many source entities |
| CN106776711A (en) * | 2016-11-14 | 2017-05-31 | 浙江大学 | A kind of Chinese medical knowledge mapping construction method based on deep learning |
| CN106815293A (en) * | 2016-12-08 | 2017-06-09 | 中国电子科技集团公司第三十二研究所 | System and method for constructing knowledge graph for information analysis |
| CN108804521A (en) * | 2018-04-27 | 2018-11-13 | 南京柯基数据科技有限公司 | A kind of answering method and agricultural encyclopaedia question answering system of knowledge based collection of illustrative plates |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
| CN108984661A (en) * | 2018-06-28 | 2018-12-11 | 上海海乂知信息科技有限公司 | Entity alignment schemes and device in a kind of knowledge mapping |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
Non-Patent Citations (3)
| Title |
|---|
| HAORAN SUN等: ""Topic Model Based Konwledge Graph for Entity Similarity Measuring"", 《2018 IEEE 15TH INTERNATIONAL CONFERENCE ON E-BUSINESS ENGINEERING》 * |
| 夏迎春: "" 基于知识图谱的农业知识服务系统研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王子涵等: ""基于实体相似度信息的知识图谱补全算法"", 《第七届中国数据挖掘会议》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465287A (en) * | 2019-09-09 | 2021-03-09 | 国际商业机器公司 | Improving farm farming quality |
| CN113010529A (en) * | 2019-12-19 | 2021-06-22 | 广州极飞科技股份有限公司 | Crop management method and device based on knowledge graph |
| CN111507758A (en) * | 2020-04-09 | 2020-08-07 | 深圳传世智慧科技有限公司 | Semantic analysis-based investigation method, device, system and server |
| CN111507758B (en) * | 2020-04-09 | 2023-10-31 | 深圳传世智慧科技有限公司 | Investigation method, device, system and server based on semantic analysis |
| CN111488741A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Tax knowledge data semantic annotation method and related device |
| CN113761971B (en) * | 2020-06-02 | 2023-06-20 | 中国人民解放军战略支援部队信息工程大学 | Remote sensing image target knowledge graph construction method and device |
| CN113761971A (en) * | 2020-06-02 | 2021-12-07 | 中国人民解放军战略支援部队信息工程大学 | Method and device for constructing target knowledge graph of remote sensing image |
| CN112199508A (en) * | 2020-08-10 | 2021-01-08 | 淮阴工学院 | Parameter adaptive agricultural knowledge graph recommendation method based on remote supervision |
| CN112199508B (en) * | 2020-08-10 | 2024-01-19 | 淮阴工学院 | Parameter self-adaptive agricultural knowledge graph recommendation method based on remote supervision |
| CN112329468A (en) * | 2020-11-03 | 2021-02-05 | 中国平安财产保险股份有限公司 | Method and device for constructing heterogeneous relation network, computer equipment and storage medium |
| CN112329468B (en) * | 2020-11-03 | 2023-07-25 | 中国平安财产保险股份有限公司 | Method and device for constructing heterogeneous relation network, computer equipment and storage medium |
| CN113220827B (en) * | 2021-04-23 | 2023-03-28 | 哈尔滨工业大学 | Construction method and device of agricultural corpus |
| CN113220827A (en) * | 2021-04-23 | 2021-08-06 | 哈尔滨工业大学 | Construction method and device of agricultural corpus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110209839B (en) | 2021-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110209839A (en) | Agricultural knowledge map construction device, method and computer readable storage medium | |
| Liu et al. | Tomato diseases and pests detection based on improved Yolo V3 convolutional neural network | |
| CN113590837B (en) | Deep learning-based food and health knowledge graph construction method | |
| CN108182262A (en) | Intelligent Answer System construction method and system based on deep learning and knowledge mapping | |
| CN110597969B (en) | Agricultural knowledge intelligent question and answer method and system and electronic equipment | |
| CN112231460B (en) | Construction method of question-answering system based on agricultural encyclopedia knowledge graph | |
| CN112199508B (en) | Parameter self-adaptive agricultural knowledge graph recommendation method based on remote supervision | |
| CN111966787B (en) | Knowledge graph-based construction method of intelligent fishery question-answering robot | |
| CN117216294A (en) | Agricultural knowledge graph construction method, device, equipment and storage medium | |
| Deepa et al. | An effective automated ontology construction based on the agriculture domain | |
| CN114021546A (en) | Peach production knowledge open question-answering method and device for migrating context network | |
| Mohapatra et al. | Using TF-IDF on Kisan call centre dataset for obtaining query answers | |
| CN116010564A (en) | Construction method of rice pest question-answering system based on multi-mode knowledge graph | |
| Wang et al. | A Weakly-Supervised Method for Named Entity Recognition of Agricultural Knowledge Graph. | |
| CN114780740A (en) | Construction method of tea knowledge graph | |
| CN112231535B (en) | Method for making multi-modal data set in field of agricultural diseases and insect pests, processing device and storage medium | |
| CN113434644A (en) | Agricultural technology knowledge service method and system | |
| Gao | The Application of Information Classification in Agricultural Production Based on Internet of Things and Deep Learning | |
| Suganya et al. | Ontology based information extraction-a review | |
| Phoksawat et al. | Ontology-based knowledge and optimization model for Decision Support System to intercropping | |
| CN114996474A (en) | Construction method of grape planting knowledge map database | |
| CN114860917A (en) | Agricultural knowledge question-answering method, device, electronic equipment and storage medium | |
| Montellano | Butterfly, Larvae and Pupae Defects Detection Using Convolutional Neural Network and Apriori Algorithm | |
| Hashmi et al. | Machine Learning and Deep Learning for Smart Agriculture and Applications | |
| Alimkar et al. | KISAN MITRA: AN INTELLIGENT CHATBOT |
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 |