Supercharge Your Innovation With Domain-Expert AI Agents!

Cultural relic question-answering system and question-answering method based on knowledge graph

A technology of knowledge graph and question answering system

Pending Publication Date: 2022-05-13
NORTHWEST UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditionally, users can only search for questions in search engines in the public domain, but the displayed results have too much irrelevant information and cannot be accurately associated with other relevant information.

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
  • Cultural relic question-answering system and question-answering method based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0037] Such as figure 1 As shown, a question answering system for museum cultural relics based on knowledge graph includes the following components:

[0038] Interactive front-end module;

[0039] Build a text preprocessing module;

[0040] Build a matching problem module;

[0041] Build a knowledge map module;

[0042] Described text preprocessing module comprises word segmentation template, part-of-speech tagging template, named entity recognition template;

[0043] Described matching problem module comprises mark natural language question template, key part replaces template, generates CQL statement template;

[0044] The knowledge map module includes cultural relic data crawling templates, data sorting templates, and NEO4J templates.

[0045] Construct a knowledge map based on cultural relics data, display high-frequency query questions, and c...

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

According to the cultural relic question-answering system and method based on the knowledge graph, the knowledge graph based on cultural relic data is constructed, question display is inquired at high frequency, and a common question template is constructed; according to the method, word embedding is carried out on an input question, the processes of named entity recognition and relation extraction are completed based on a BERT pre-training model, BERT, BILSTM and CRF, finally related entities and relations correspond to a question query template, CQL query statements are constructed, then related results are queried in a knowledge graph represented by NEO4J and returned, and finally the related results are displayed to a user. According to the system, tourists can better know related extension information such as backgrounds of related cultural relics, and the browsing experience of users is improved.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs and natural language processing, and in particular relates to a cultural relics question answering system and question answering method based on knowledge graphs. Background technique [0002] Now, when tourists are watching museum exhibits, more information about a certain cultural relic is explained by the tour guide. When there is a tour guide, the tour guide is also in a one-to-many state, which cannot satisfy everyone's individual preferences. When there is no tour guide, some tourists will feel that this cultural relic is meaningless, just a dead thing. Traditionally, users can only search for questions in search engines in the public domain, but the displayed results have too much irrelevant information, and cannot be well and accurately related to other relevant information. In the question answering system based on the knowledge map, after the user asks and searches in natural ...

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): G06F16/33G06F16/332G06F16/36G06F40/295G06N3/04G06N3/08G06N5/02
CPCG06F16/3329G06F16/3344G06F16/367G06F40/295G06N3/08G06N5/02G06N3/044
Inventor 贺小伟冯强
Owner NORTHWEST UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More