CN114490964A - Soil fertility knowledge question-answering method, system, equipment and medium based on knowledge map - Google Patents
Soil fertility knowledge question-answering method, system, equipment and medium based on knowledge map Download PDFInfo
- Publication number
- CN114490964A CN114490964A CN202111581504.3A CN202111581504A CN114490964A CN 114490964 A CN114490964 A CN 114490964A CN 202111581504 A CN202111581504 A CN 202111581504A CN 114490964 A CN114490964 A CN 114490964A
- Authority
- CN
- China
- Prior art keywords
- question
- soil fertility
- knowledge
- entity
- data
- 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
- 239000002689 soil Substances 0.000 title claims abstract description 101
- 230000035558 fertility Effects 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000000605 extraction Methods 0.000 claims description 13
- 238000002372 labelling Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 230000008520 organization Effects 0.000 abstract description 2
- 230000004044 response Effects 0.000 abstract description 2
- 230000002349 favourable effect Effects 0.000 abstract 1
- 230000001737 promoting effect Effects 0.000 abstract 1
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 21
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 10
- 229910052757 nitrogen Inorganic materials 0.000 description 10
- 229910052698 phosphorus Inorganic materials 0.000 description 10
- 239000011574 phosphorus Substances 0.000 description 10
- 235000013339 cereals Nutrition 0.000 description 8
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 6
- 239000004927 clay Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 239000011591 potassium Substances 0.000 description 6
- 229910052700 potassium Inorganic materials 0.000 description 6
- 239000004576 sand Substances 0.000 description 6
- 230000004720 fertilization Effects 0.000 description 5
- 239000000843 powder Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- -1 organic matters Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 229920000742 Cotton Polymers 0.000 description 2
- 244000068988 Glycine max Species 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 244000061456 Solanum tuberosum Species 0.000 description 2
- 235000002595 Solanum tuberosum Nutrition 0.000 description 2
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 240000008042 Zea mays Species 0.000 description 2
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 2
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 235000005822 corn Nutrition 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000005416 organic matter Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 235000017060 Arachis glabrata Nutrition 0.000 description 1
- 244000105624 Arachis hypogaea Species 0.000 description 1
- 235000010777 Arachis hypogaea Nutrition 0.000 description 1
- 235000018262 Arachis monticola Nutrition 0.000 description 1
- 235000014698 Brassica juncea var multisecta Nutrition 0.000 description 1
- 235000006008 Brassica napus var napus Nutrition 0.000 description 1
- 240000000385 Brassica napus var. napus Species 0.000 description 1
- 235000006618 Brassica rapa subsp oleifera Nutrition 0.000 description 1
- 235000004977 Brassica sinapistrum Nutrition 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 229910019142 PO4 Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000618 nitrogen fertilizer Substances 0.000 description 1
- 235000020232 peanut Nutrition 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- NBIIXXVUZAFLBC-UHFFFAOYSA-K phosphate Chemical compound [O-]P([O-])([O-])=O NBIIXXVUZAFLBC-UHFFFAOYSA-K 0.000 description 1
- 239000010452 phosphate Substances 0.000 description 1
- 239000002686 phosphate fertilizer Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Probability & Statistics with Applications (AREA)
- Molecular Biology (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Human Computer Interaction (AREA)
- Mathematical Optimization (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a soil fertility knowledge question-answering method, a soil fertility knowledge question-answering system, soil fertility knowledge question-answering equipment and a soil fertility knowledge question-answering medium based on a knowledge graph. The method comprises the steps of triggering a question-answering task, wherein the question-answering task comprises a natural language question sentence input into the soil fertility field; identifying the natural language question to obtain an entity and entity attribute relation in the natural language question; linking the entity and entity attribute relationship to a pre-constructed soil fertility knowledge map to obtain an attribute value or a relationship object of the entity and entity attribute relationship in the soil fertility knowledge map; and outputting a question-answer result, and outputting the attribute value or the relation object as the question-answer result of the question-answer task. The method can realize quick response of the soil fertility related problems, and is favorable for promoting innovation of soil fertility knowledge organization and knowledge utilization mode in artificial intelligence environment.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a soil fertility knowledge question-answering method, a soil fertility knowledge question-answering system, soil fertility knowledge question-answering equipment and a soil fertility knowledge question-answering medium based on a knowledge graph.
Background
The rapid development of artificial intelligence technology has prompted the emergence of a series of new technologies, and an automatic question-answering system is a representative result thereof. Different from the traditional search engine, the question-answering system can answer the fact questions by accurate and concise answers, and the use cost of the user is reduced. The knowledge graph is a novel knowledge storage form, and data logically form a huge network. Compared with the traditional relational database, the knowledge map can better describe the semantic relation between the entities and conforms to the thinking of human beings on the objective world.
In the prior art, according to literature research and internet query and search results, no vertical domain knowledge map directly related to the soil fertility field exists so far. Therefore, it is necessary to develop a soil fertility knowledge question-answering method and system based on the knowledge map.
Disclosure of Invention
The invention aims to provide a soil fertility knowledge question-answering system based on an intellectual map so as to fill the blank area in the prior art.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the soil fertility knowledge question-answering method based on the knowledge map comprises the following steps:
triggering a question-answering task, wherein the question-answering task comprises a natural language question sentence input into the soil fertility field;
identifying the natural language question to obtain an entity and entity attribute relation in the natural language question;
linking the entity and entity attribute relationship to a pre-constructed soil fertility knowledge map to obtain an attribute value or a relationship object of the entity and entity attribute relationship in the soil fertility knowledge map;
and outputting a question-answer result, and outputting the attribute value or the relation object as the question-answer result of the question-answer task.
Further, the entity and entity attribute relationship in the natural language question obtained by identifying the natural language question is identified by a named entity identification algorithm.
Further, the construction of the soil fertility knowledge graph comprises the following steps:
obtaining source data, wherein the source data comprises structured data, semi-structured data and unstructured data;
carrying out data cleaning, data labeling, named entity identification, attribute extraction and relationship extraction on the semi-structured data and the unstructured data;
storing the structured data and the semi-structured data and the unstructured data which are subjected to data processing through a triple format;
and importing the data in the triple format into a database to construct a soil fertility knowledge map.
Further, the data sources of the source data include literature data, web page data and experimental data.
Further, the structured data extracts the relationship between the named entity and the entity through an inverse distance weighted interpolation method, and the semi-structured data and the unstructured data extract the relationship between the named entity and the entity through a supervised entity relationship extraction method of deep learning.
Further, the named entity extraction of the semi-structured data and the unstructured data is realized based on an ERNIE-BiLSTM-CRF model, which specifically comprises:
obtaining a word vector of a target text;
inputting a word vector into a bidirectional LSTM model to capture context features and obtain longer-distance semantic information;
obtaining label transition probability and constraint conditions from data obtained by decoding semantic information through CRF (conditional random access memory), and obtaining category information of each label through training and learning;
and the ERNIE-BilSTM-CRF model is trained after entity and relation labeling is carried out on txt texts of soil fertility journal documents.
Further, the relationship between the semi-structured data and the unstructured data is extracted based on a PCNN-Attention model, and the PCNN-Attention model is trained after entity and relationship labeling is carried out through txt texts of soil fertility journal documents.
In order to solve the technical problem, an embodiment of the present application further provides a soil fertility knowledge question-answering system based on a knowledge graph, and the following technical scheme is adopted:
a soil fertility knowledge question-answering system based on a knowledge graph comprises:
the query module is used for triggering a question and answer task, wherein the question and answer task comprises a natural language question sentence input into the soil fertility field;
the identification module is used for identifying the natural language question to obtain an entity and entity attribute relation in the natural language question;
the interaction module is used for linking the entity and entity attribute relation to a pre-constructed soil fertility knowledge graph to obtain an attribute value or a relation object of the entity and entity attribute relation in the soil fertility knowledge graph;
and the output module is used for outputting a question-answer result and outputting the attribute value or the relation object as the question-answer result of the question-answer task.
In order to solve the above technical problem, the present invention further provides a computer device, which includes a memory and a processor, wherein the memory stores computer readable instructions, and the processor executes the computer readable instructions to implement the steps of the above-mentioned soil fertility knowledge question-answering method based on the knowledge map.
In order to solve the above technical problem, the present invention further provides a computer readable storage medium, having computer readable instructions stored thereon, which when executed by a processor implement the steps of the above-mentioned soil fertility quiz method based on a knowledge graph.
Compared with the prior art, the invention has the advantages that: according to the method, a question-answer task is triggered, wherein the question-answer task comprises a natural language question sentence input into the soil fertility field, and the natural language question sentence is identified to obtain an entity and an entity attribute relation in the natural language question sentence; linking the entity and entity attribute relationship to a pre-constructed soil fertility knowledge map to obtain an attribute value or a relationship object of the entity and entity attribute relationship in the soil fertility knowledge map; and outputting a question-answer result, and outputting the attribute value or the relation object as the question-answer result of the question-answer task, so that the quick response of the soil fertility-related questions can be realized, and the innovation of soil fertility knowledge organization and knowledge utilization mode under the artificial intelligence environment can be promoted.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a soil fertility knowledge question-answering method of the knowledge-graph of the present invention.
FIG. 2 is a flow chart of the construction of a soil fertility intellectual map in the present invention.
FIG. 3 is a conceptual layer diagram of the soil fertility domain ontology in the present invention.
Fig. 4 is a detailed flowchart of step S3 in the present invention.
FIG. 5 is a schematic diagram of a soil fertility knowledge question-answering system based on a knowledge graph in the present invention.
FIG. 6 is a block diagram of the basic structure of a computer device in one embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, and the scope of the present invention will be more clearly and clearly defined.
Referring to fig. 1 and 2, the embodiment discloses a soil fertility knowledge question-answering method based on a knowledge graph, which includes the following steps:
and step S1, triggering a question-answer task, wherein the question-answer task comprises a natural language question sentence input into the soil fertility field.
Specifically, in practical application, the input of the natural language question in the dialog box may be performed, the question may also be asked in the form of voice, and if the input voice is in the form of voice, the input voice may be converted into the natural language question.
And step S2, identifying the natural language question to obtain the entity and entity attribute relation in the natural language question.
The method can also comprise the step of judging whether the natural language question belongs to the field of soil fertility, if so, executing the step S2, and otherwise, prompting to execute the step S1 again. The specific implementation can be judged by identifying whether the natural language question has a preset keyword or not.
Specifically, the recognition can be performed by a named entity recognition algorithm.
And step S3, linking the entity and entity attribute relationship to a pre-constructed soil fertility knowledge map to obtain the attribute value or relationship object of the entity and entity attribute relationship in the soil fertility knowledge map.
The construction of the knowledge graph selects a top-down mode, and the construction process comprises a concept layer and a data layer, wherein the concept layer is a template normal form of data, and the data layer is specific data filling. Firstly, combining expert definition and data content to construct a soil fertility field body (concept layer), then obtaining related ternary group data through operations such as IDW (inverse distance weighting) interpolation, data cleaning, data labeling, named entity identification, attribute relation extraction and the like on the basis of the body according to field data characteristics, storing the related ternary group data into a Neo4j database to form an Anhui soil fertility knowledge map, and simultaneously carrying out visualization operation and a specific knowledge reasoning process, wherein the specific flow is shown in figure 2.
The Soil fertility field ontology comprises three layers in total, wherein the highest father class is Concepts (Concepts), and the subclasses thereof comprise 4 classes of regions (Districts), Soil fertility (Soil fertility), Fertilization management (Fertilization), and common Crops (Crops). Wherein, the regional classes comprise 4 subclasses of Province (Province), City (City), County/district (County), Town/County/street (Town); the soil fertility class comprises 8 subclasses of pH, organic matter (SOM), Total Nitrogen (TN), Total Phosphorus (TP), total potassium (TK), Available Nitrogen (AN), Available Phosphorus (AP), Clay (Clay), Powder (Powder) and Sand (Sand); the fertilization management class comprises 3 subclasses of a Nitrogen fertilizer (Nitrogen fertilzer), a Phosphate fertilizer (Phosphate fertilzer) and a Potassium fertilizer (Potasidum); common crop species include Wheat (Wheat), Rice (Rice), Corn (Corn), canola (Rape), Potato (Potato), Cotton (Cotton), Peanut (peanout), Soybean (Soybean)8 subclasses.
Modeling for a concept allows for a number of different options when building an ontology. And the concept description has the mismatching problem of description because the ontology has the opposite direction from the high level to the low level. In the embodiment, the ontology is constructed in a way of collaborative manual construction of domain experts, matching problems of a concept layer (as shown in fig. 3) of the ontology are unified during construction, but heterogeneous problems of the concept layer of the ontology need to be considered during information interaction with other application systems.
Specifically, as shown in fig. 4, the construction of the soil fertility intellectual map in this embodiment includes the following steps:
and step S30, obtaining source data, wherein the source data comprises structured data, semi-structured data and unstructured data.
The data sources of the source data comprise literature data, webpage data and experimental data.
Wherein, taking Anhui province as an example, the three data sources are specifically analyzed, and the webpage data comprises: relevant information and data of a soil total nitrogen, total phosphorus, total potassium, pH, available phosphorus, available nitrogen, organic matters, clay grains, sand grains and a particle distribution diagram (1980) 1996) of the second soil census Anhui province in China are obtained by applying from a national science and technology basic condition platform-a national earth system scientific data center platform (http:// www.geodata.cn), and the network data comprise a soil testing formula query system of soil fertility data of a specific region in Anhui province; literature data includes: journal documents with the theme related to soil fertility in Anhui province and the theme related to common crop fertilization management policies, and data can be obtained through experiments aiming at some data which are not available at present. The basic structure of the data obtained by the platform application is relatively fixed, and belongs to structured data; while other types pertain to semi-structured and unstructured data.
And step S31, performing data cleaning, data labeling, named entity identification, attribute extraction and relationship extraction on the semi-structured data and the unstructured data.
Specifically, taking Anhui province as an example, the soil general survey data focuses on the physicochemical properties (soil fertility indexes) of different soil species, and the data is mostly the average value of a plurality of sampling points in different regions and cannot correspond to addresses of town/villages. In addition, at the time of soil general survey, administrative divisions in Anhui province have changed greatly. Therefore, according to the data characteristics of the 1:400 million soil total nitrogen, total phosphorus, total potassium, pH, available phosphorus, available nitrogen, organic matter, clay, sand and particle distribution diagram (1980-.
The structured data in the embodiment extracts the relationship between the named entity and the entity through an inverse distance weighted interpolation method, and the logical support of the method is the first law of geography, namely the similar principle. The IDW interpolation calculation method is as follows:
in the formula: z (X0), estimate point X0 attribute value; z (xi) estimating the attribute value of the ith point Zi in the peripheral area of the point X0; n, the number of points in the local neighborhood; wi, Xi points are weighted with X0 points, and the inverse distance power value depends on the inverse distance weighting method.
And extracting the relationship between the named entity and the entity by the semi-structured data and the unstructured data through a supervised entity relationship extraction method of deep learning.
Preferably, the relationship between the semi-structured data and the unstructured data is extracted based on a PCNN-Attenttion model, and the PCNN-Attenttion model is trained after labeling the entities and the relationship according to txt text of soil fertility journal literature.
Specifically, the named entity extraction of the semi-structured data and the unstructured data is realized based on an ERNIE-BiLSTM-CRF model, which specifically includes:
firstly, obtaining a word vector of a target text; then, inputting the word vector to a bidirectional LSTM model to capture context features and obtain longer-distance semantic information; and finally, obtaining the label transition probability and constraint conditions through training and learning of data obtained by decoding the semantic information through a CRF (conditional random access memory), so as to obtain the category information of each label.
The experimental results obtained by the method have the accuracy of 95.44%, the recall rate of 97.10% and the F1 value of 96.26%.
Wherein, the ERNIE-BilSTM-CRF model is trained by labeling entities and relations through txt texts of soil fertility journal literature.
And step S32, storing the structured data and the semi-structured data and the unstructured data after data processing through a triple format. The soil fertility knowledge map is conveniently constructed by a professional map database after being stored in the format.
And step S33, importing the data in the triple format into a database to construct a soil fertility knowledge map.
Specifically, data in a triple format is imported into a graph database Neo4j, and a soil fertility knowledge graph with comprehensive information is constructed.
And step S4, outputting a question-answer result, and outputting the attribute value or the relationship object as the question-answer result of the question-answer task.
Specifically, the attribute value or the relationship object of the entity and the entity attribute relation in the soil fertility knowledge graph is obtained, and the attribute value or the relationship object is output.
The method can ask questions of soil total nitrogen, total phosphorus, total potassium, pH, available phosphorus, available nitrogen, organic matters, clay grains, sand grains and powder grain data from provincial administrative regions (such as Anhui province) to soil total nitrogen, total phosphorus, total potassium, pH, available phosphorus, available nitrogen, organic matters, clay grains, sand grains and powder grains, and returns corresponding data answers; and a fertilization management suggestion of a certain region or a certain crop can be asked to obtain a text answer.
Referring to fig. 5, this embodiment further provides a soil fertility knowledge question-answering system of a knowledge graph, which adopts the following technical scheme: the query module 10 is used for triggering a question and answer task, wherein the question and answer task comprises a natural language question sentence input into the soil fertility field; the identification module 20 is configured to identify the natural language question to obtain an entity and an entity attribute relationship in the natural language question; the interaction module 30 is configured to link the entity and entity attribute relationship to a pre-constructed soil fertility knowledge graph to obtain an attribute value or a relationship object of the entity and entity attribute relationship in the soil fertility knowledge graph; and the output module 40 is used for outputting a question-answer result and outputting the attribute value or the relationship object as the question-answer result of the question-answer task.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 6, fig. 6 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It is noted that only computer device 4 having components 41-43 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable gate array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 4. Of course, the memory 41 may also include both internal and external storage devices of the computer device 4. In this embodiment, the memory 41 is generally used for storing an operating system installed on the computer device 4 and various types of application software, such as computer readable instructions of a soil fertility knowledge question-answering method based on a knowledge map. Further, the memory 41 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute computer readable instructions or process data stored in the memory 41, for example, execute computer readable instructions of the method for knowledge-map-based soil fertility quiz.
The network interface 43 may comprise a wireless network interface or a wired network interface, and the network interface 43 is generally used for establishing communication connection between the computer device 4 and other electronic devices.
The computer device provided in this embodiment may perform the steps of the above-described soil fertility quiz method based on a knowledge-graph. Here, the steps of the soil fertility quiz method based on the knowledge graph may be the steps of the soil fertility quiz method based on the knowledge graph in each of the above embodiments.
The present application further provides another embodiment, which is a computer-readable storage medium having computer-readable instructions stored thereon which are executable by at least one processor to cause the at least one processor to perform the steps of the method for knowledgemap-based soil fertility quiz as described above.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, various changes or modifications may be made by the patentees within the scope of the appended claims, and within the scope of the invention, as long as they do not exceed the scope of the invention described in the claims.
Claims (10)
1. A soil fertility knowledge question-answering method based on a knowledge graph is characterized by comprising the following steps:
triggering a question-answering task, wherein the question-answering task comprises a natural language question sentence input into the soil fertility field;
identifying the natural language question to obtain an entity and entity attribute relation in the natural language question;
linking the entity and entity attribute relationship to a pre-constructed soil fertility knowledge map to obtain an attribute value or a relationship object of the entity and entity attribute relationship in the soil fertility knowledge map;
and outputting a question-answer result, and outputting the attribute value or the relation object as the question-answer result of the question-answer task.
2. The soil fertility knowledge question-answering method based on the knowledge graph of claim 1, wherein the recognition of the natural language question to obtain the entity and entity attribute relationship in the natural language question is performed by a named entity recognition algorithm.
3. The soil fertility knowledge question-answering method based on the knowledge graph of claim 1, wherein the construction of the soil fertility knowledge graph comprises the following steps:
obtaining source data, wherein the source data comprises structured data, semi-structured data and unstructured data;
carrying out data cleaning, data labeling, named entity identification, attribute extraction and relationship extraction on the semi-structured data and the unstructured data;
storing the structured data and the semi-structured data and the unstructured data which are subjected to data processing through a triple format;
and importing the data in the triple format into a map database to construct a soil fertility knowledge map.
4. The knowledgebase map-based soil fertility knowledge question-answering method according to claim 3, wherein the data sources of the source data include literature data, web data and experimental data.
5. The knowledge-graph-based soil fertility knowledge question-answering method according to claim 4, wherein the structured data is used for extracting the relationship between the named entity and the entity through an inverse distance weighted interpolation method, and the semi-structured data and the unstructured data are used for extracting the relationship between the named entity and the entity through a supervised entity relationship extraction method of deep learning.
6. The knowledge-graph-based soil fertility knowledge question-answering method according to claim 5, wherein the named entity extraction of the semi-structured data and the unstructured data is realized based on an ERNIE-BilSTM-CRF model, and specifically comprises the following steps:
obtaining a word vector of a target text;
inputting a word vector into a bidirectional LSTM model to capture context features and obtain longer-distance semantic information;
obtaining label transition probability and constraint conditions from data obtained by decoding semantic information through CRF (conditional random access memory), and obtaining category information of each label through training and learning;
and the ERNIE-BilSTM-CRF model is trained after entity and relation labeling is carried out on txt texts of soil fertility journal documents.
7. The method of claim 5, wherein the relationships between the semi-structured data and the unstructured data are extracted based on a PCNN-Attenttion model, and wherein the PCNN-Attenttion model is trained after labeling the entities and relationships with txt text of the soil fertility journal literature.
8. A system of a knowledge-graph-based soil fertility knowledge question-answering method according to any one of claims 1-7, comprising:
the query module is used for triggering a question and answer task, wherein the question and answer task comprises a natural language question sentence input into the soil fertility field;
the identification module is used for identifying the natural language question to obtain an entity and entity attribute relation in the natural language question;
the interaction module is used for linking the entity and entity attribute relation to a pre-constructed soil fertility knowledge map to obtain an attribute value or a relation object of the entity and entity attribute relation in the soil fertility knowledge map;
and the output module is used for outputting a question-answer result and outputting the attribute value or the relation object as the question-answer result of the question-answer task.
9. A computer device comprising a memory and a processor, wherein the memory has stored therein computer readable instructions which, when executed by the processor, implement the steps of the knowledgemap-based soil fertility quiz method of any one of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the knowledgegraph-based soil fertility quiz method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111581504.3A CN114490964B (en) | 2021-12-22 | 2021-12-22 | Knowledge graph-based soil fertility knowledge question-answering method, system, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111581504.3A CN114490964B (en) | 2021-12-22 | 2021-12-22 | Knowledge graph-based soil fertility knowledge question-answering method, system, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114490964A true CN114490964A (en) | 2022-05-13 |
| CN114490964B CN114490964B (en) | 2024-08-09 |
Family
ID=81494932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111581504.3A Active CN114490964B (en) | 2021-12-22 | 2021-12-22 | Knowledge graph-based soil fertility knowledge question-answering method, system, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114490964B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114637766A (en) * | 2022-05-18 | 2022-06-17 | 山东师范大学 | Intelligent question-answering method and system based on natural resource industrial chain knowledge graph |
| CN114860917A (en) * | 2022-07-06 | 2022-08-05 | 中化现代农业有限公司 | Agricultural knowledge question-answering method, device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021000676A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Q&a method, q&a device, computer equipment and storage medium |
| CN113342938A (en) * | 2021-06-21 | 2021-09-03 | 南京农业大学 | Corn seed selection and accurate sowing decision method combining knowledge graph |
-
2021
- 2021-12-22 CN CN202111581504.3A patent/CN114490964B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021000676A1 (en) * | 2019-07-03 | 2021-01-07 | 平安科技（深圳）有限公司 | Q&a method, q&a device, computer equipment and storage medium |
| CN113342938A (en) * | 2021-06-21 | 2021-09-03 | 南京农业大学 | Corn seed selection and accurate sowing decision method combining knowledge graph |
Non-Patent Citations (1)
| Title |
|---|
| 张颖;陈桂芬;: "基于Citespace的土壤肥力知识图谱可视化挖掘与分析", 中国农机化学报, no. 03, 15 March 2016 (2016-03-15), pages 1 - 4 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114637766A (en) * | 2022-05-18 | 2022-06-17 | 山东师范大学 | Intelligent question-answering method and system based on natural resource industrial chain knowledge graph |
| CN114860917A (en) * | 2022-07-06 | 2022-08-05 | 中化现代农业有限公司 | Agricultural knowledge question-answering method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114490964B (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103440287B (en) | A kind of Web question and answer searching system based on product information structure | |
| WO2020237856A1 (en) | Smart question and answer method and apparatus based on knowledge graph, and computer storage medium | |
| CN112819023B (en) | Sample set acquisition method, device, computer equipment and storage medium | |
| CN110276023B (en) | POI transition event discovery method, device, computing equipment and medium | |
| CN110750649A (en) | Knowledge graph construction and intelligent response method, device, equipment and storage medium | |
| CN114490964B (en) | Knowledge graph-based soil fertility knowledge question-answering method, system, equipment and medium | |
| Li et al. | Knowledge transfer and adaptation for land-use simulation with a logistic cellular automaton | |
| CN117216194B (en) | Knowledge question-answering method and device, equipment and medium in literature and gambling field | |
| CN113254630A (en) | Domain knowledge map recommendation method for global comprehensive observation results | |
| CN112966053B (en) | Knowledge graph-based marine field expert database construction method and device | |
| CN112330510A (en) | Volunteer recommendation method and device, server and computer-readable storage medium | |
| CN112463986A (en) | Information storage method and device | |
| CN116796730A (en) | Text error correction method, device, equipment and storage medium based on artificial intelligence | |
| Zhang et al. | Early detection of technology opportunity based on analogy design and phrase semantic representation | |
| CN115062617A (en) | Task processing method, device, equipment and medium based on prompt learning | |
| CN113785317A (en) | Feedback mining using domain-specific modeling | |
| CN117408339A (en) | Location class topic knowledge graph construction method with intelligent entity ambiguity identification | |
| CN117033816A (en) | Parking recommendation method and device, electronic equipment and storage medium | |
| CN116702784A (en) | Entity linking method, entity linking device, computer equipment and storage medium | |
| US11755837B1 (en) | Extracting content from freeform text samples into custom fields in a software application | |
| JP7236501B2 (en) | Transfer learning method and computer device for deep learning model based on document similarity learning | |
| CN115129885A (en) | Entity chain pointing method, device, equipment and storage medium | |
| CN111062477B (en) | Data processing method, device and storage medium | |
| CN115114441A (en) | Query graph construction method and device, storage medium and electronic equipment | |
| Gutiérrez et al. | KD SENSO-MERGER: An architecture for semantic integration of heterogeneous data |
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 |