CN112115379A - Rice variety selection method and device based on knowledge graph - Google Patents
Rice variety selection method and device based on knowledge graph Download PDFInfo
- Publication number
- CN112115379A CN112115379A CN202010986156.7A CN202010986156A CN112115379A CN 112115379 A CN112115379 A CN 112115379A CN 202010986156 A CN202010986156 A CN 202010986156A CN 112115379 A CN112115379 A CN 112115379A
- Authority
- CN
- China
- Prior art keywords
- rice
- rice variety
- knowledge
- variety
- user
- 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.)
- Pending
Links
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 330
- 235000009566 rice Nutrition 0.000 title claims abstract description 330
- 238000010187 selection method Methods 0.000 title claims abstract description 18
- 240000007594 Oryza sativa Species 0.000 title 1
- 241000209094 Oryza Species 0.000 claims abstract description 329
- 238000000034 method Methods 0.000 claims abstract description 61
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 230000006399 behavior Effects 0.000 claims description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 10
- 239000002689 soil Substances 0.000 claims description 9
- 230000001488 breeding effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 241000607479 Yersinia pestis Species 0.000 claims description 5
- 238000003306 harvesting Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 claims description 3
- 238000010845 search algorithm Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000009395 breeding Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
- G06F16/319—Inverted lists
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Marine Sciences & Fisheries (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a rice variety selection method based on a knowledge graph, which comprises the steps of acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database, and establishing a rice variety knowledge graph by a semi-automatic method; and executing rice variety selection based on a program developed by a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation. The method is suitable for multi-scene and different-level users to select rice varieties, so that rice variety selection is more scientific and authoritative, and has accuracy and usability. Furthermore, the method is beneficial to realizing knowledge reasoning and auxiliary decision in the rice variety selection method based on the knowledge map, avoids the repeated production of knowledge and improves the utilization efficiency of the knowledge. The disclosure also provides a rice variety selection device based on the knowledge graph.
Description
Technical Field
The disclosure relates to the technical field of computer agriculture automation, in particular to a rice variety selection method and device based on a knowledge graph.
Background
Rice is an important and indispensable agricultural product on the dining table of common people. The planting of high-quality and high-yield rice has important significance for meeting the requirements of consumers and increasing the income of rice planting main bodies. Variety selection is the first and most important line of rice planting. However, the main rice planting body still faces a number of difficulties in selecting rice varieties: the rice varieties on the market are uneven in quality and hard to distinguish; variety selection is closely related to local soil, weather, market demand, labor force, mechanization and the like, and the variety selection is often considered to be wrong and difficult to quantitatively evaluate; the information about rice varieties on the Internet has the problems of multi-source, isomerism, dispersion and the like, so that rice growers can be helpless; the new rice variety is endlessly cultivated, and a grower often feels that the variety is difficult to verify. In conclusion, a set of intelligent and precise rice variety selection method is provided, and scientificity and authority of rice variety selection are ensured.
Disclosure of Invention
In order to solve the technical problems in the prior art, the embodiment of the disclosure provides a rice variety selection method and device based on a knowledge graph, data related to rice are acquired through a search engine query mode and a user behavior collection and evaluation mode, and a rice variety knowledge graph is established through a semi-automatic method; rice variety selection is performed based on a program developed by a rice variety knowledge graph. The method is suitable for multi-scene and different-level users to select rice varieties, so that rice variety selection is more scientific and authoritative, and has accuracy and usability. Furthermore, the method is beneficial to realizing knowledge reasoning and auxiliary decision in the rice variety selection method based on the knowledge map, avoids the repeated production of knowledge and improves the utilization efficiency of the knowledge.
In a first aspect, the embodiments of the present disclosure provide a method for selecting rice varieties based on a knowledge graph, including the following steps: acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database, and establishing a rice variety knowledge graph by a semi-automatic method; and executing rice variety selection based on a program developed by a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation.
In one embodiment, the obtaining of the data related to rice through a search engine query manner and a user behavior gathering and evaluating manner includes: obtaining variety information, county soil information and meteorological information in Baidu encyclopedia, interactive encyclopedia and national rice breeding center by crawler technology; and collecting the names of the rice varieties, planting areas, lodging resistance, stress resistance, yield per mu, rice yield, selling price, taste, growth pictures and pest pictures in different periods, and quantitatively or qualitatively evaluating the conditions of the selected varieties of rice.
In one embodiment, the selecting the neo4j database as a non-relational database and establishing the rice variety knowledge graph by a semi-automated method comprises the following steps:
establishing a knowledge frame of rice seed selection;
automatically extracting entities and relations in the knowledge framework through natural language processing and machine learning methods;
and generating CSV documents by the acquired entity and relationship data, and supplementing the entities and the relationships into the knowledge framework by a load CSV method, an admin import method or an apoc plug-in to form a complete rice variety knowledge graph.
In one embodiment, the method further comprises the following steps: dynamic completion of the user behavior data in the rice variety knowledge map is carried out by combining the apoc plug-in neo4j with the Timer in the python library.
In one embodiment, performing rice variety selection based on a program developed from a rice variety knowledge-graph comprises: executing rice variety recommendation based on a program developed by a rice variety knowledge graph;
the executing rice variety recommendation based on the program developed by the rice variety knowledge graph comprises:
the system automatically acquires the area where the user is located according to the IP address or the LBS service of the mobile phone, and inquires weather conditions and soil conditions of the area and all varieties suitable for the area in a knowledge graph by using cypher sentences to execute recommended operation according to the area; and/or
The system recommends operation according to evaluation based on the evaluation of various performances of different users on the planted variety after rice harvest through a collaborative filtering algorithm; and/or
Based on the established variety knowledge graph, a knowledge graph query and reasoning technology is adopted, and the operation is comprehensively recommended by considering the area factor and the evaluation level factor in a weight mode.
In one embodiment, the method further comprises the following steps: adopting a collaborative filtering algorithm based on users;
the step of acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database and establishing a rice variety knowledge graph by a semi-automatic method comprises the following steps:
acquiring a user who has a preference behavior to the same rice variety by using a reverse table from the rice variety to the user;
the similarity between the users is obtained according to a preset first formula,
wherein N (u) represents a rice variety set which is interesting to the user u, and N (v) represents a rice variety set which is interesting to the user v;
calculating the interest degree of a user to a certain rice variety according to a preset second formula, performing reverse order processing on the interest degree, and recommending the rice varieties ranked a few times to the user;
where S (u, K) is the set of K users with the closest interest to user u, N (i) is the set of all users who like item i, wuvIs the similarity between user u and user v, rviThe hidden feedback information represents the interest degree of the user v in the rice variety i, and is set to be 1 for simplifying the calculation.
In one embodiment, the method further comprises the following steps: adopting a collaborative filtering algorithm based on articles;
the step of acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database and establishing a rice variety knowledge graph by a semi-automatic method comprises the following steps:
obtaining rice varieties with similar characteristics by using a reverse table from a user to the rice varieties;
according to a preset third formula, the similarity between the rice varieties is worked out,
wherein N (i) represents a set of users interested in rice variety i, and N (j) represents a set of rice varieties interested in rice variety j;
calculating the interest degree of a user to a certain rice variety according to a preset fourth formula, performing reverse order processing on the interest degree, and recommending the rice varieties ranked a few times to the user;
wherein S (j, K) is a set of K varieties closest to rice variety j, N (u) is a set of rice varieties liked by user u, and wijIs the similarity between rice variety i and rice variety j, ruiThe hidden feedback information represents the interest degree of the user u in the rice variety i, and is set to be 1 for simplifying the calculation.
In one embodiment, performing rice variety selection based on a program developed from a rice variety knowledge-graph comprises: performing rice variety search based on a program developed by a rice variety knowledge graph;
the performing rice variety searches based on the rice variety knowledge-graph developed program comprises:
according to a preset search algorithm, the name of a rice variety is used as a keyword, and the information of the rice variety and the family information are obtained in a way of searching a path in a knowledge graph;
wherein the family information comprises: and obtaining the variety information of the same female parent, male parent or family line of the rice variety.
In one embodiment, performing rice variety selection based on a program developed from a rice variety knowledge-graph comprises: executing rice variety question-answering based on a program developed by a rice variety knowledge graph;
the program developed based on the rice variety knowledge-graph for executing rice variety quiz includes:
the system carries out word segmentation on the proposed questions by using jieba, and extracts entities and relations in the question sentences to generate triples of the proposed questions;
establishing a synonym dictionary for the words related in the triples, and replacing synonyms of the entities and the relations in the internal database and the words with similar meanings to the entities and the relations, so that the accuracy of question answering is increased;
and matching the question triples with the knowledge graph to determine the answer to the question.
In a second aspect, the disclosed embodiments provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method described above.
In a third aspect, the disclosed embodiments provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method described above when executing the program.
In a fourth aspect, the present disclosure provides a device for selecting rice varieties based on a knowledge-graph, the device including: the acquisition and establishment module is used for acquiring data related to rice through a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database and establishing a rice variety knowledge graph through a semi-automatic method; the selection module is used for executing rice variety selection based on a program developed by a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation.
The invention provides a rice variety selection method and device based on a knowledge graph, which are characterized in that data related to rice are acquired through a search engine query mode and a user behavior collection and evaluation mode, a neo4j database is selected as a non-relational database, and a rice variety knowledge graph is established through a semi-automatic method; and executing rice variety selection based on a program developed by a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation. The method is suitable for multi-scene and different-level users to select rice varieties, so that rice variety selection is more scientific and authoritative, and has accuracy and usability. Furthermore, the method is beneficial to realizing knowledge reasoning and auxiliary decision in the rice variety selection method based on the knowledge map, avoids the repeated production of knowledge and improves the utilization efficiency of the knowledge.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced as follows:
FIG. 1 is a schematic flow chart illustrating the steps of a method for selecting rice cultivars based on a knowledge-based map according to an embodiment of the invention;
FIG. 2 is a schematic ontology diagram of a method for selecting rice cultivars based on knowledge-based mapping according to an embodiment of the invention;
FIG. 3 is a schematic view of a knowledge-map visualization of a method for selecting rice cultivars based on a knowledge-map according to an embodiment of the invention;
FIG. 4 is a schematic structural diagram of a rice variety selection apparatus based on a knowledge-graph according to an embodiment of the present invention.
Detailed Description
The present application will now be described in further detail with reference to the accompanying drawings and examples.
In the following description, the terms "first" and "second" are used for descriptive purposes only and are not intended to indicate or imply relative importance. The following description provides embodiments of the disclosure, which may be combined or substituted for various embodiments, and this application is therefore intended to cover all possible combinations of the same and/or different embodiments described. Thus, if one embodiment includes feature A, B, C and another embodiment includes feature B, D, then this application should also be considered to include an embodiment that includes one or more of all other possible combinations of A, B, C, D, even though this embodiment may not be explicitly recited in text below.
In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the following description will be made in detail by using examples and with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It should be noted that the concept of the knowledge graph is proposed by google in 2012, and the knowledge is represented in a graphical manner, so as to restore the original view of the knowledge, thereby having important significance for integrating knowledge resources and improving the knowledge utilization efficiency. The invention discloses a rice variety selection method and device based on a knowledge graph, which are used for establishing the knowledge graph by integrating knowledge of varieties, soil, weather and the like and providing services such as individual recommendation, accurate search, intelligent question answering, crowdsourcing evaluation, visual output and the like for rice planters on the basis.
Secondly, it should be noted that the method and the device for selecting rice varieties based on the knowledge graph are mainly oriented to rice breeding experts and rice planting subjects. Among them, the main tasks of the breeding experts are: providing technical service in the planting process for a grower who selects a certain variety, providing a basis for the next improvement of breeding according to evaluation data provided by the grower, providing authoritative data for further improving the variety knowledge map, and performing information completion on the knowledge map; the rice planting main body is mainly oriented to registered users, and only provides simple recommendation and search functions for non-registered users, and does not provide subsequent technical services and natural language question-answering functions. In addition, for the registered user, it is required to provide basic information such as a mobile phone number and a location area, and each time a new variety is selected, it is also required to provide information on the variety planted in the previous year.
As shown in fig. 1, a schematic flow chart of a method for selecting rice cultivars based on knowledge-mapping in an embodiment specifically includes the following steps:
Specifically, in an embodiment, the acquiring data related to rice through a search engine query manner and a user behavior gathering and evaluating manner includes: obtaining variety information, county soil information and meteorological information in Baidu encyclopedia, interactive encyclopedia and national rice breeding center by crawler technology; and collecting the names of the rice varieties, planting areas, lodging resistance, stress resistance, yield per mu, rice yield, selling price, taste, growth pictures and pest pictures in different periods, and quantitatively or qualitatively evaluating the conditions of the selected varieties of rice. Furthermore, it should be noted that the registered user provides rice variety evaluation, growth, and pest and disease picture while performing rice variety selection and enjoying related technical services, and these data are equivalent to acquiring knowledge in a crowd-sourced manner. Therefore, the diversity, the accuracy and the practicability of the data related to the rice are improved.
In addition, in one embodiment, it should be further noted that the selecting the neo4j database as a non-relational database and establishing the rice variety knowledge graph by a semi-automated method includes: establishing a knowledge framework of rice seed selection, and forming a rice variety knowledge body as shown in figure 2; automatically extracting entities and relations in the knowledge framework through natural language processing and machine learning methods; generating a CSV document by the acquired entity and relationship data, and supplementing the entity and relationship into the knowledge framework through a load CSV method, an admin import method or an apoc plug-in, so as to form a complete rice variety knowledge graph as shown in FIG. 3, wherein it needs to be noted that each newly registered user is an entity in the rice variety knowledge graph, and the user entity dynamically grows along with the increase of registered users and automatically establishes contact with other entities. Therefore, the accuracy and the availability of the rice variety knowledge graph are improved. In addition, the rice variety selection method based on the knowledge graph further comprises the following steps: dynamic completion of the user behavior data in the rice variety knowledge map is carried out by combining the apoc plug-in neo4j with the Timer in the python library. Specifically, the registered user can provide variety evaluation, growth and pest and disease damage pictures while performing variety selection and enjoying related technical services, the data can be used for further complementing the knowledge graph, and the perfect knowledge graph can promote knowledge sharing, so that better variety selection and technical services are provided for the user, and the accuracy and the practicability of the rice variety knowledge graph are improved.
And 104, executing rice variety selection based on a program developed by the rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question and answer operation. Wherein, the expression form of the program developed based on the rice variety knowledge graph at the server end is the rice variety knowledge graph stored by a neo4j graph database; the expression form at different terminals is specifically as follows: the method comprises the steps of visually interacting with a server side through a desktop computer and interacting with the server side through an applet, wherein the applet comprises but is not limited to a WeChat applet. Therefore, the flexibility and the usability of the program developed based on the rice variety knowledge graph are improved.
Specifically, in one embodiment, performing rice variety selection based on a program developed from a rice variety knowledge-graph comprises: executing rice variety recommendation based on a program developed by a rice variety knowledge graph; the executing rice variety recommendation based on the program developed by the rice variety knowledge graph comprises: the system automatically acquires the area where the user is located according to the IP address or the mobile LBS service, and queries the meteorological conditions of the area in the knowledge graph by adopting cypher sentences, such as: sunlight and accumulated temperature, soil conditions, for example: the soil type and water system, and all varieties suitable for the area execute the recommended operation according to the area; or the system recommends operation according to evaluation based on the evaluation of various performances of the planted variety by different users after rice harvesting through a collaborative filtering algorithm; or based on the established variety knowledge graph, adopting a knowledge graph query and reasoning technology, and taking the region factors and the evaluation level factors into consideration in a weighting mode to carry out comprehensive recommendation operation. Therefore, the comprehensiveness of rice variety selection based on the knowledge map is improved.
In addition, it should be further noted that the collaborative filtering algorithm may adopt a user-based collaborative filtering algorithm, and the step 102 specifically includes:
and step 1021, obtaining the users who have favorite preference behaviors to the same rice variety by using the inverted list from the rice variety to the users.
Step 1022, the similarity between users is obtained according to the following formula 1,
wherein N (u) represents a set of rice varieties of interest to user u, and N (v) represents a set of rice varieties of interest to user v.
Step 1023, according to the following formula 2, calculating the interest degree of the user to a certain rice variety, and processing the interest degree in a reverse order, recommending the rice varieties with the top ranking to the user,
where S (u, K) is the set of K users with the closest interest to user u, N (i) is the set of all users who like item i, wuvIs the similarity between user u and user v, rviThe hidden feedback information represents the interest degree of the user v in the rice variety i, and is set to be 1 for simplifying the calculation.
Or by using a collaborative filtering algorithm based on the article, the step 102 specifically includes:
step 1021', obtaining rice varieties with similar characteristics by using the inverted list from the user to the rice varieties.
Step 1022', the similarity between the rice varieties is obtained according to the following formula 3,
wherein N (i) represents a set of users interested in rice variety i, and N (j) represents a set of rice varieties interested in rice variety j.
Step 1023', according to the following formula 4, calculating the interest degree of the user to a certain rice variety, and performing reverse order processing on the interest degree, recommending the rice varieties with the top ranking to the user,
wherein S (j, K) is a set of K varieties closest to rice variety j, N (u) is a set of rice varieties liked by user u, and wijIs the similarity between rice variety i and rice variety j, ruiThe hidden feedback information represents the interest degree of the user u in the rice variety i, and is set to be 1 for simplifying the calculation.
Further, in one embodiment, performing rice variety selection based on the program developed by the rice variety knowledge-graph comprises: performing rice variety search based on a program developed by a rice variety knowledge graph; the performing rice variety searches based on the rice variety knowledge-graph developed program comprises: according to a preset search algorithm, the name of a rice variety is used as a keyword, and the information of the rice variety and the family information are obtained in a way of searching a path in a knowledge graph; wherein the family information comprises: and obtaining the variety information of the same female parent, male parent or family line of the rice variety. Therefore, the accuracy and comprehensiveness of rice variety searching based on the knowledge map are improved.
Further, in one embodiment, performing rice variety selection based on the program developed from the rice variety knowledge-graph comprises: executing rice variety questions and answers based on a program developed by a rice variety knowledge graph, wherein the questions and answers may be: what varieties are suitable for planting in the four-level region? How do dragon rice 18 perform? What are new examined rice varieties in 2017? Which varieties have stronger lodging resistance? Based on the above questions, programs developed based on rice variety knowledge maps provide answers to users in a way of asking and answering with natural understanding. That is, the program developed based on the rice variety knowledge-graph to perform rice variety quiz includes: the system uses jieba to carry out word segmentation on the questions, establishes a synonym dictionary for the words related in the triples, replaces synonyms of the entities and the relations in the internal database and the words with the meanings similar to the entities and the relations, and increases the accuracy of question answering; and matching the question triples with the knowledge graph to determine the answer to the question. Therefore, the intelligence and the usability of the rice variety search based on the knowledge graph are improved.
In addition, it should be noted that the method for selecting rice varieties based on knowledge-graph according to the present disclosure further includes: for a certain rice variety selected by a user, the rice variety selection method based on the knowledge graph disclosed by the disclosure can display all entities directly or indirectly connected with the rice variety entity in a graph form by taking the entity represented by the rice variety as a center, so that the user can more specifically know the related information of the rice variety. Meanwhile, based on the evaluation data of the user on the rice variety, the comprehensive expressive force of the rice variety is visually displayed in a radar map form, so that the user can visually and comprehensively know various characteristics of the rice variety. Therefore, the convenience and the usability of the rice variety selection based on the knowledge map are improved.
The invention provides a rice variety selection method based on a knowledge graph, which comprises the steps of acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database, and establishing a rice variety knowledge graph by a semi-automatic method; and executing rice variety selection based on a program developed by a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation. The method is suitable for multi-scene and different-level users to select rice varieties, so that rice variety selection is more scientific and authoritative, and has accuracy and usability. Furthermore, the method is beneficial to realizing knowledge reasoning and auxiliary decision in the rice variety selection method based on the knowledge map, avoids the repeated production of knowledge and improves the utilization efficiency of the knowledge.
Based on the same invention concept, a rice variety selection device based on the knowledge graph is also provided. Because the principle of solving the problems by the device is similar to that of the rice variety selection method based on the knowledge graph, the implementation of the device can be realized according to the specific steps of the method, and repeated parts are not repeated.
Fig. 4 is a schematic structural diagram of a rice variety selection apparatus based on a knowledge-map in an embodiment. The device 10 for selecting rice varieties based on knowledge-maps comprises: an acquisition and establishment module 200 and a selection module 400.
The acquisition and establishment module 200 is used for acquiring data related to rice through a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database and establishing a rice variety knowledge graph through a semi-automatic method; the selection module 400 is configured to perform rice variety selection based on a program developed by a rice variety knowledge-graph, wherein the rice variety selection includes rice variety recommendation, rice variety search, and rice variety question-and-answer operations.
The invention provides a rice variety selection device based on a knowledge graph, which obtains data related to rice by an obtaining and establishing module through a search engine query mode and a user behavior searching and evaluating mode, selects a neo4j database as a non-relational database and establishes the rice variety knowledge graph through a semi-automatic method; and finally, executing rice variety selection through a program developed by a selection module based on a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation. The device is suitable for multi-scene and different-level users to select rice varieties, so that rice variety selection is more scientific and authoritative, and has accuracy and usability. Furthermore, the method is beneficial to realizing knowledge reasoning and auxiliary decision in the rice variety selection method based on the knowledge map, avoids the repeated production of knowledge and improves the utilization efficiency of the knowledge.
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by the processor in fig. 1.
The embodiment of the invention also provides a computer program product containing the instruction. Which when run on a computer causes the computer to perform the method of fig. 1 described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
Also, as used herein, the use of "or" in a list of items beginning with "at least one" indicates a separate list, e.g., "A, B or at least one of C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the described example is preferred or better than other examples.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. A rice variety selection method based on a knowledge graph is characterized by comprising the following steps:
acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database, and establishing a rice variety knowledge graph by a semi-automatic method;
and executing rice variety selection based on a program developed by a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation.
2. The method of claim 1, wherein the obtaining data related to rice through search engine query and user behavior gathering and evaluation comprises: obtaining variety information, county soil information and meteorological information in Baidu encyclopedia, interactive encyclopedia and national rice breeding center by crawler technology; and collecting the names of the rice varieties, planting areas, lodging resistance, stress resistance, yield per mu, rice yield, selling price, taste, growth pictures and pest pictures in different periods, and quantitatively or qualitatively evaluating the conditions of the selected varieties of rice.
3. The method of claim 1, wherein said selecting a neo4j database as a non-relational database and building a rice variety knowledgegraph by a semi-automated method comprises:
establishing a knowledge frame of rice seed selection;
automatically extracting entities and relations in the knowledge framework through natural language processing and machine learning methods;
and generating CSV documents by the acquired entity and relationship data, and supplementing the entities and the relationships into the knowledge framework by a load CSV method, an admin import method or an apoc plug-in to form a complete rice variety knowledge graph.
4. The method of knowledge-graph-based rice variety selection of claim 3, further comprising: dynamic completion of the user behavior data in the rice variety knowledge map is carried out by combining the apoc plug-in neo4j with the Timer in the python library.
5. The method of claim 1, wherein performing rice variety selection based on a program developed by a rice variety knowledge-graph comprises: executing rice variety recommendation based on a program developed by a rice variety knowledge graph;
the executing rice variety recommendation based on the program developed by the rice variety knowledge graph comprises:
the system automatically acquires the area where the user is located according to the IP address or the LBS service of the mobile phone, and inquires weather conditions and soil conditions of the area and all varieties suitable for the area in a knowledge graph by using cypher sentences to execute recommended operation according to the area; and/or
The system recommends operation according to evaluation based on the evaluation of various performances of different users on the planted variety after rice harvest through a collaborative filtering algorithm; and/or
Based on the established variety knowledge graph, a knowledge graph query and reasoning technology is adopted, and the operation is comprehensively recommended by considering the area factor and the evaluation level factor in a weight mode.
6. The method of knowledge-graph-based rice variety selection of claim 1, further comprising: adopting a collaborative filtering algorithm based on users;
the step of acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database and establishing a rice variety knowledge graph by a semi-automatic method comprises the following steps:
acquiring a user who has a preference behavior to the same rice variety by using a reverse table from the rice variety to the user;
the similarity between the users is obtained according to a preset first formula,
wherein N (u) represents a rice variety set which is interesting to the user u, and N (v) represents a rice variety set which is interesting to the user v;
calculating the interest degree of a user to a certain rice variety according to a preset second formula, performing reverse order processing on the interest degree, and recommending the rice varieties ranked a few times to the user;
where S (u, K) is the set of K users with the closest interest to user u, N (i) is the set of all users who like item i, wuvIs the similarity between user u and user v, rviIs hidden feedback information representing the user v to the rice productThe interest level of seed i is set to 1 for simplicity of calculation.
7. The method of knowledge-graph-based rice variety selection of claim 1, further comprising: adopting a collaborative filtering algorithm based on articles;
the step of acquiring data related to rice by a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database and establishing a rice variety knowledge graph by a semi-automatic method comprises the following steps:
obtaining rice varieties with similar characteristics by using a reverse table from a user to the rice varieties;
according to a preset third formula, the similarity between the rice varieties is worked out,
wherein N (i) represents a set of users interested in rice variety i, and N (j) represents a set of rice varieties interested in rice variety j;
calculating the interest degree of a user to a certain rice variety according to a preset fourth formula, performing reverse order processing on the interest degree, and recommending the rice varieties ranked a few times to the user;
wherein S (j, K) is a set of K varieties closest to rice variety j, N (u) is a set of rice varieties liked by user u, and wijIs the similarity between rice variety i and rice variety j, ruiThe hidden feedback information represents the interest degree of the user u in the rice variety i, and is set to be 1 for simplifying the calculation.
8. The method of claim 1, wherein performing rice variety selection based on a program developed by a rice variety knowledge-graph comprises: performing rice variety search based on a program developed by a rice variety knowledge graph;
the performing rice variety searches based on the rice variety knowledge-graph developed program comprises:
according to a preset search algorithm, the name of a rice variety is used as a keyword, and the information of the rice variety and the family information are obtained in a way of searching a path in a knowledge graph;
wherein the family information comprises: and obtaining the variety information of the same female parent, male parent or family line of the rice variety.
9. The method of claim 1, wherein performing rice variety selection based on a program developed by a rice variety knowledge-graph comprises: executing rice variety question-answering based on a program developed by a rice variety knowledge graph;
the program developed based on the rice variety knowledge-graph for executing rice variety quiz includes:
the system carries out word segmentation on the proposed questions by using jieba, and extracts entities and relations in the question sentences to generate triples of the proposed questions;
establishing a synonym dictionary for the words related in the triples, and replacing synonyms of the entities and the relations in the internal database and the words with similar meanings to the entities and the relations, so that the accuracy of question answering is increased;
and matching the question triples with the knowledge graph to determine the answer to the question.
10. A device for selecting rice varieties based on a knowledge-graph, the device comprising:
the acquisition and establishment module is used for acquiring data related to rice through a search engine query mode and a user behavior collection and evaluation mode, selecting a neo4j database as a non-relational database and establishing a rice variety knowledge graph through a semi-automatic method;
the selection module is used for executing rice variety selection based on a program developed by a rice variety knowledge graph, wherein the rice variety selection comprises rice variety recommendation, rice variety search and rice variety question-answer operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010986156.7A CN112115379A (en) | 2020-09-18 | 2020-09-18 | Rice variety selection method and device based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010986156.7A CN112115379A (en) | 2020-09-18 | 2020-09-18 | Rice variety selection method and device based on knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112115379A true CN112115379A (en) | 2020-12-22 |
Family
ID=73800736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010986156.7A Pending CN112115379A (en) | 2020-09-18 | 2020-09-18 | Rice variety selection method and device based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112115379A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN113434644A (en) * | 2021-05-25 | 2021-09-24 | 北京农业信息技术研究中心 | Agricultural technology knowledge service method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777051A (en) * | 2016-12-09 | 2017-05-31 | 重庆邮电大学 | A kind of many feedback collaborative filtering recommending methods based on user's group |
| CN108664564A (en) * | 2018-04-13 | 2018-10-16 | 东华大学 | A kind of improvement collaborative filtering recommending method based on item contents feature |
| CN109862431A (en) * | 2019-01-23 | 2019-06-07 | 重庆第二师范学院 | A kind of TV programme mixed recommendation method based on MCL-HCF algorithm |
| CN110188208A (en) * | 2019-06-04 | 2019-08-30 | 河海大学 | A kind of the information resources inquiry recommended method and system of knowledge based map |
| CN111538847A (en) * | 2020-04-16 | 2020-08-14 | 北方民族大学 | Ningxia rice knowledge graph construction method |
-
2020
- 2020-09-18 CN CN202010986156.7A patent/CN112115379A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777051A (en) * | 2016-12-09 | 2017-05-31 | 重庆邮电大学 | A kind of many feedback collaborative filtering recommending methods based on user's group |
| CN108664564A (en) * | 2018-04-13 | 2018-10-16 | 东华大学 | A kind of improvement collaborative filtering recommending method based on item contents feature |
| CN109862431A (en) * | 2019-01-23 | 2019-06-07 | 重庆第二师范学院 | A kind of TV programme mixed recommendation method based on MCL-HCF algorithm |
| CN110188208A (en) * | 2019-06-04 | 2019-08-30 | 河海大学 | A kind of the information resources inquiry recommended method and system of knowledge based map |
| CN111538847A (en) * | 2020-04-16 | 2020-08-14 | 北方民族大学 | Ningxia rice knowledge graph construction method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113434644A (en) * | 2021-05-25 | 2021-09-24 | 北京农业信息技术研究中心 | Agricultural technology knowledge service method and system |
| CN113434644B (en) * | 2021-05-25 | 2023-09-12 | 北京农业信息技术研究中心 | Agricultural technology knowledge service method and system |
| 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 |
| CN113342938B (en) * | 2021-06-21 | 2024-03-08 | 南京农业大学 | Corn seed selection and precise sowing decision-making method combining knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Oikonomidis et al. | Deep learning for crop yield prediction: a systematic literature review | |
| Gutiérrez et al. | A review of visualisations in agricultural decision support systems: An HCI perspective | |
| Senapathi et al. | The impact of over 80 years of land cover changes on bee and wasp pollinator communities in England | |
| US20120215795A1 (en) | System and Method For Intelligent Job Hunt | |
| Wagner et al. | Sampling from social networks with attributes | |
| Rodríguez et al. | Using linguistic incomplete preference relations to cold start recommendations | |
| Connor et al. | Sustainable rice production in the Mekong River Delta: Factors influencing farmers’ adoption of the integrated technology package “One Must Do, Five Reductions”(1M5R) | |
| Adetimehin et al. | Utilization of agricultural information and knowledge for improved production by rice farmers in Ondo State, Nigeria | |
| AU2010284506A1 (en) | Semantic trading floor | |
| WO2011153171A2 (en) | Data isolating research tool | |
| CN112115379A (en) | Rice variety selection method and device based on knowledge graph | |
| Aleixandre-Tudó et al. | Bibliometric and social network analysis in scientific research on precision agriculture | |
| Godara et al. | Sequential pattern mining combined multi-criteria decision-making for farmers’ queries characterization | |
| CN113434644B (en) | Agricultural technology knowledge service method and system | |
| Widayat et al. | Recommendations for Choosing a Place to Stay in the Greater Malang Area Using SAW and TOPSIS | |
| Yang et al. | Finding experts in community question answering based on topic-sensitive link analysis | |
| CN108536763B (en) | Pull-down prompting method and device | |
| CN114860917B (en) | Agricultural knowledge question-answering method, device, electronic equipment and storage medium | |
| Xiong et al. | Identifying mechanisms underlying peer effects on multiplex networks | |
| Salim et al. | The adoption of Internet of Things in urban farming. | |
| CN108509610A (en) | A kind of search method and system of activity and companion | |
| CN116186210A (en) | User portrait construction method and device for agricultural technology knowledge question and answer | |
| Amer-Yahia et al. | SubDEx: Exploring Ratings in Subjective Databases | |
| Koenderink et al. | Expert-based ontology construction: A case-study in horticulture | |
| Adetimehim et al. | Utilization of Agricultural Information and Knowledge for improved production by Rice Farmers in Ondo State, Nigeria |
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 |