Question answering method and device based on knowledge graph, storage medium and question answering robot

A technology of knowledge graphs and questions, applied in the field of artificial intelligence, can solve problems such as easy recognition errors, lack of possession, and inaccurate answers, and achieve the effect of improving accuracy

Pending Publication Date: 2022-04-15
ALIBABA (CHINA) CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For complex problems with constraints and multi-hop relationships, which contain a large number of attributes and constraints and complex multi-hop relationships, the multi-hop relationships that appear in the problem and the constraint attributes of constraints are easy to identify errors, resulting in query graphs In the case of multi-hop relationship errors and constraint mounting errors, the question and answer results are wrong, and the intelligent dialogue ability is insufficient. It is only suitable for single-relationship problems with constraints or multi-hop relationship problems, but it is not capable of dealing with problems with For complex questions with constraints and multi-hop relationships, the answer to complex questions with constraints and multi-hop relationships is not accurate enough

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
  • Question answering method and device based on knowledge graph, storage medium and question answering robot
  • Question answering method and device based on knowledge graph, storage medium and question answering robot
  • Question answering method and device based on knowledge graph, storage medium and question answering robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

[0038] First, the nouns involved in this application are explained:

[0039] Query Graph: A subgraph structure similar to a knowledge graph, which can be directly mapped into a logical semantic expression, such as the query language SPARQL. With this, semantic analysis is reduced to the generation of query graphs and formalized as a staged search problem. figure 1 An example of a query...

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 question answering method and device based on a knowledge graph, a storage medium and a question answering robot. According to the method, the entities, the first-level attributes and the first-level constraint information contained in the question can be recognized for the input question, the object type attributes in the first-level attributes can serve as the second-level entities, the attributes of the second-level entities in the question are recognized, and the multi-hop attributes are obtained; the method comprises the steps of obtaining a question, identifying constraint information of a multi-hop attribute in the question to obtain a multi-hop constraint, generating a query graph containing an entity of the question, a first-level attribute, first-level constraint information, the multi-hop attribute and the multi-hop constraint, and generating a multi-constraint multi-hop query graph corresponding to the complex question aiming at the complex question with constraints and a multi-hop relationship. Through the multi-constraint multi-hop query graph, the accurate reply information corresponding to the complex question can be queried, the dialogue ability of processing complex questions with constraints and multi-hop relationships is achieved, and the reply accuracy of the complex questions with constraints and multi-hop relationships is improved.

Description

technical field [0001] The present application relates to artificial intelligence technology, and in particular to a question-answering method, device, storage medium and question-answering robot based on a knowledge map. Background technique [0002] With the development of artificial intelligence, intelligent dialogue products such as intelligent customer service Q&A robots have dialogue capabilities such as task-based Q&A, Frequently Asked Questions (FAQ for short), and Q&A based on knowledge pictures, which can replace manual Q&A to a certain extent. service, which can reduce the labor cost of the question-and-answer service and improve the efficiency of the question-and-answer service. [0003] At present, the query graph of the question answering system design based on the knowledge map defines the entity, the attribute of the entity, and the constraint, and the attribute of the entity is used to describe the entity. For complex problems with constraints and multi-hop...

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): G06F16/332G06F16/33G06F40/279
Inventor 乐兴虎
Owner ALIBABA (CHINA) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products