Unlock instant, AI-driven research and patent intelligence for your innovation.

Candidate pool generation method

A candidate pool, N-gram technology, applied in the field of knowledge graph question answering, can solve problems such as unable to meet the needs of material culture, unable to find matching answers, etc.

Active Publication Date: 2020-10-13
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0033] The above methods often have problems that cannot find matching answers in the knowledge graph, and cannot meet people's growing material and cultural needs. Therefore, it is necessary to improve the existing methods that affect the accuracy and efficiency of the question answering system. Performance and accuracy of the question answering system

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Candidate pool generation method
  • Candidate pool generation method
  • Candidate pool generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0096] The present invention will be described in detail below in conjunction with the accompanying drawings and examples.

[0097] figure 1 The workflow of a knowledge graph question answering system is shown. figure 2 A schematic diagram of a general knowledge graph question answering system. The main purpose of the whole system is to understand the user's questions, and then find the corresponding answer from the knowledge graph and give feedback to the user. For example, if a user asks the question "Which state is Shuangfeng located in?", there is a corresponding triplet (Shuangfeng, region, California) in the knowledge graph, and the question answering system needs to identify the subject of the question (Shuangfeng ) and predicate (at), and then query in the knowledge graph to get the answer directly. Since there are many variations in the way a question is asked, how to accurately identify the predicate from various variations is a major challenge for this problem. ...

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

No PUM Login to View More

Abstract

The invention provides a candidate pool generation method, and belongs to the technical field of knowledge graph questioning and answering. According to the invention, based on candidate pool generation, the invention provides a non-strict N-element syntax character string matching method, which is characterized in that matching nodes are searched for in a knowledge graph to construct candidate pools in a mode that complete matching, partial matching and continuous matching after subject-related phrase reducing are sequentially performed on subject-related phrases in the knowledge graph, so that the entity recall rate is effectively increased while the scale of the candidate pools is reduced; furthermore, based on the candidate pool generation method, an implementation method of a simple question-answering system is provided, so that the robustness and accuracy of the question-answering system are improved; the predicate extraction method of the simple question-answering system is further improved, so that the accuracy and efficiency of the question-answering system are further improved; and compared with the prior art, the method provided by the invention has the advantage that the robustness and accuracy of the question-answering system are improved by few resources and a simple algorithm process.

Description

technical field [0001] The invention relates to a method for generating a candidate pool, in particular to a method for improving the generation performance of a candidate pool in a knowledge graph question answering system and implementing a simple question answering system based thereon, belonging to the technical field of knowledge graph question answering. Background technique [0002] With the vigorous development of Internet technology, various types of network information have exploded, and the World-Wide-Web (WWW) has developed into a large-scale distributed global information distribution center. However, the Internet is a double-edged sword. On the one hand, a large amount of information floods into the Internet, which provides strong support for information services, and the Internet has become an important way to obtain knowledge and information. On the other hand, the diversity, disorder, dispersion and information pollution of network information have caused i...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F16/33G06F16/36G06F40/253G06F40/284G06N3/04G06N3/08
CPCG06F16/3329G06F16/367G06F16/3331G06F40/253G06F40/284G06N3/08G06N3/044G06N3/045Y02D10/00
Inventor 礼欣陈森俞晓云吴昊
Owner BEIJING INSTITUTE OF TECHNOLOGYGY