Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-round dialogue method and device in knowledge question-answering system

A question answering system and knowledge technology, applied in the field of information processing, can solve the problems of cumbersome question answering system and low accuracy rate, and achieve the effect of extremely low cost, reduced labor cost, and guaranteed accuracy

Pending Publication Date: 2021-01-08
SHANGHAI MININGLAMP ARTIFICIAL INTELLIGENCE GRP CO LTD
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the above-mentioned technical problems of cumbersome question answering system and low accuracy rate, the present invention proposes a multi-round dialogue method and device in the knowledge 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
  • Multi-round dialogue method and device in knowledge question-answering system
  • Multi-round dialogue method and device in knowledge question-answering system
  • Multi-round dialogue method and device in knowledge question-answering system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] refer to Figure 1 to Figure 4 As shown, this example discloses a specific implementation of a multi-round dialogue method (hereinafter referred to as "method") in a knowledge question answering system.

[0061] Specifically, the method disclosed in this embodiment mainly includes the following steps:

[0062] Step S1: Obtain the historical entities and historical relations of the current question.

[0063] Specifically, the knowledge graph is essentially a semantic network, its nodes represent entities or concepts, and edges represent various semantic relationships between entities / concepts. The knowledge graph (or knowledge base) can be regarded as the carrier of knowledge units subject to ontology control. Knowledge graph is a graph-based data structure, and its storage methods mainly have two forms: RDF storage format and graph database (Graph Database).

[0064] The knowledge question answering system refers to the question answering system based on the knowledg...

Embodiment 2

[0087] refer to Figure 5 As shown, this example discloses a specific implementation of a multi-round dialogue method (hereinafter referred to as "method") in a knowledge question answering system.

[0088] Specifically, the method disclosed in this embodiment mainly includes the following steps:

[0089] S10: Obtain historical entities and historical relationships of the current question sentence.

[0090] S20: Compose candidate paths according to the adjacent relationships of the historical entities in the knowledge base and the adjacent entities.

[0091] S30: Perform weighting processing on the features of the candidate paths to obtain a final path.

[0092] S40: Obtain an answer according to the final path and return it to the user.

[0093] The method disclosed in this embodiment is the same as the technical solution of the multi-round dialogue method in the knowledge question answering system disclosed in the first embodiment, please refer to the description in the f...

Embodiment 3

[0095] In combination with the multi-turn dialogue method in the knowledge question answering system disclosed in Embodiment 1, this embodiment discloses a specific implementation example of a multi-turn dialogue device (hereinafter referred to as "device") in the knowledge question answering system.

[0096] refer to Image 6 As shown, the device includes:

[0097] Obtaining module: obtaining the historical entity and historical relationship of the current question;

[0098] Entity linking module: filter out candidate entities according to the current question sentence;

[0099] Entity screening module: weighting the features of the candidate entities to obtain the main entity;

[0100] Candidate path generation module: form candidate paths according to the adjacent relationship between the main entity and the historical entity in the knowledge base and adjacent entities;

[0101] Path screening module: weighting the features of the candidate path to obtain the final path;...

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 discloses a multi-round dialogue method and device in a knowledge question-answering system. The multi-round dialogue method comprises the following steps: acquiring a historical entityand a historical relationship of a current question sentence; screening out candidate entities according to the current questions; performing weighting processing on the features of the candidate entities to obtain a main entity; forming a candidate path according to the adjacent relationship between the main entity and the historical entity in the knowledge base and the adjacent entities; performing weighting processing on the features of the candidate paths to obtain a final path; obtaining an answer according to the final path and returning the answer to the user; and obtaining all entitiesand all relationships of the final path as historical entities and historical relationships of the next round of questions and answers. Through the method, the historical information of the previousquestion sentence is completely added into the current question and answer, so that the historical information acquisition accuracy is ensured, and a large amount of labor cost is avoided.

Description

technical field [0001] The invention relates to the field of information processing, in particular to a multi-round dialogue method and device in a knowledge question answering system. Background technique [0002] The knowledge question answering system refers to the question answering system based on the knowledge graph library, which is mainly used in medical, banking, insurance, retail and other industries. The knowledge graph library consists of a large number of triples, which include entities and relationships, and can be written in the form of (entity 1, relationship, entity 2). The knowledge question answering system receives the natural language questions entered by the user, and performs semantic analysis and understanding on the questions, uses the knowledge graph database to query and reason to obtain the answer path and answer that best matches the question, and finally returns the answer to the user. [0003] The multi-round dialogue in the knowledge question...

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): G06F16/33G06F16/332G06F40/295
CPCG06F16/3329G06F16/3344G06F40/295
Inventor 张文剑薛小娜
Owner SHANGHAI MININGLAMP ARTIFICIAL INTELLIGENCE GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com