A question answering method based on knowledge graph and agricultural encyclopedia question answering system
A knowledge graph, agricultural technology, applied in the direction of instruments, data processing applications, database models, etc., can solve the problems of providing services, labor-intensive, unable to automatically users, etc.
Active Publication Date: 2021-05-14
南京柯基数据科技有限公司
View PDF7 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0045] The present invention will be further elaborated below in conjunction with the embodiments of the accompanying drawings, and the purpose and effect of the present invention will become more obvious.
[0046] A question answering method based on knowledge graph, such as figure 1 shown, including:
[0047] Build the database, parse the questions and retrieve the answers, the specific steps are:
[0048] 1) Construct a database for storing knowledge in the agricultural field, a grammar library for storing synonyms sets and question templates, and a FAQ question library for storing frequently asked questions (FAQ), specifically:
[0049] 1.1 Build a knowledge map in the agricultural field, store the knowledge map data in a structured RDF (Resource Description Framework) database TDB (Triple Database), and use the TDB service to retrieve knowledge map triples;
[0050] 1.2 Construct a grammatical library for storing synonyms sets and question templates, store the synonym s...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention proposes a question-and-answer method based on knowledge graphs and an agricultural encyclopedia question-and-answer system, which can automatically analyze natural language questions raised by users, form a topology structure based on a syntax tree, and perform retrieval and comparison between the topology structure and the question templates in the grammar library , according to the mapping relationship between the topology and the predicate designation, the mapping relationship between the synonym set and the relationship or attribute in the knowledge graph, the predicate of the problem mapping is obtained, and combined with the entities identified in the problem, the final structured knowledge graph query statement is generated, according to The query statement is searched in the knowledge map, and the final result is returned. When the relevant topological structure cannot be retrieved in the question template library, the frequently asked questions and answers in the FAQ question library will be called to answer the questions. The question answering system can provide accurate answer retrieval for questions raised by users, and improve users' satisfaction with agricultural encyclopedia question retrieval.
Description
technical field [0001] The present invention relates to a question answering method based on artificial intelligence, more specifically to a question answering method based on knowledge graphs and an agricultural question answering system based on the method. Background technique [0002] In the current Internet, massive information is distributed in different information sources, and the correlation is relatively sparse. Using traditional search engines, it becomes increasingly difficult to obtain valuable information accurately and quickly. The traditional manual-based knowledge management method cannot meet the user's demand for knowledge acquisition in the agricultural field in a real-time and efficient manner. In addition, the accuracy of the answers to questions encountered in many community Q&As cannot be guaranteed, and some answers are no longer time-sensitive. In contrast, the emergence of question answering systems aims to quickly obtain high-quality information ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/332G06F16/28G06F16/35G06F40/295G06F40/284G06Q50/02
CPCG06Q50/02G06F40/284G06F40/295
Inventor 花云程吴刚杨成彪
Owner 南京柯基数据科技有限公司