Knowledge graph common sense question and answer method and system based on staged query

A knowledge graph and staged technology, which is applied in the field of knowledge graph common sense question answering method and system based on staged query, can solve problems such as difficult pruning, large amount of calculation, and knowledge graph question answering technology cannot solve complex problems, and achieves functionality. full effect

Active Publication Date: 2021-06-18
CHINA THREE GORMUSEUM +1
View PDF8 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Knowledge graph question answering technology for solving simple problems cannot solve complex problems
In addition to solving simple questio

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
  • Knowledge graph common sense question and answer method and system based on staged query
  • Knowledge graph common sense question and answer method and system based on staged query
  • Knowledge graph common sense question and answer method and system based on staged query

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0039] A specific implementation of training and building an improved question answering model, including:

[0040] S1: Obtain the original question data set, and preprocess the data in the data set to obtain the training set;

[0041] S2: Input the data in the training set into the trained entity recognition model to obtain the data of the marked entity;

[0042] S3: Input the data of marked entities into the trained constraint language recognition model, and obtain the data of marked entities and constraints;

[0043] S4: Input the data marked with entities and constraints into the question structure classification model for classification, and classify the results according to the questions; establish a question classification list and a semantic structure tree template list according to the classification results;

[0044] S5: Use the semantic structure tree template list to process the subject, the number of constraint words and the hierarchical structure of constraint w...

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 belongs to the field of knowledge graph automatic question answering, and particularly relates to a knowledge graph common sense question answering method and system based on staged query, and the method comprises the steps: obtaining a question statement, preprocessing the question statement, and converting the question statement into a question sequence; inputting the question sequence into a trained improved question and answer model to obtain a question and answer result, wherein the improved question and answer model comprises an entity recognition model, a constraint language recognition model and a question structure classification model. According to the method, complex questions or simple questions are converted into the question semantic structure tree based on the statement structure, the answers to the questions are searched step by step by updating the undetermined nodes, and the searching process is simplified from complexity to simplicity.

Description

technical field [0001] The invention belongs to the field of automatic question answering of knowledge graphs, and in particular relates to a knowledge graph common sense question answering method and system based on staged query. Background technique [0002] In recent years, with the rapid development of artificial intelligence, its most representative intelligent question and answer frequently appears in people's field of vision. This is inseparable from the development of the field of knowledge engineering represented by knowledge graphs, which store data in the form of triples. The triplet of "head entity-relationship-tail entity" is stored in the knowledge map, in which the entity is a node and the relationship is an edge, presenting a network structure diagram with node and connection edge information. Knowledge graphs can be applied in many fields, such as medical, military, cultural, financial, architectural, etc., and are indispensable and important technologies 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
IPC IPC(8): G06F16/332G06F16/33G06F16/35G06F16/36G06F40/14G06F40/247G06F40/295G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/3329G06F16/3344G06F16/367G06F16/35G06F40/14G06F40/247G06F40/295G06F40/30G06N3/08G06N3/044G06F18/214
Inventor 唐昌伦赵卓田侃张殊张晨吴涛张浩然王宇轩
Owner CHINA THREE GORMUSEUM
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap