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

Intelligent question-answering method and system based on power grid field scheduling scene knowledge graph

A technology of knowledge graph and intelligent question answering, which is applied in the fields of electrical digital data processing, computing models, semantic analysis, etc., and can solve problems such as weak ability to answer questions, lack of power field, and insufficient intelligence

Pending Publication Date: 2021-03-19
CHINA SOUTHERN POWER GRID COMPANY
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The intelligent question answering system has already blossomed in many fields in society, but there is still a lack of related products in the power field, or the ability to answer questions is not strong enough, and it is not smart 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
  • Intelligent question-answering method and system based on power grid field scheduling scene knowledge graph
  • Intelligent question-answering method and system based on power grid field scheduling scene knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] An intelligent question-and-answer method based on the knowledge map of dispatching scenarios in the power grid field according to the present invention combines the characteristics of data in the electric power field and the business requirements of dispatching scenarios. The question-and-answer system also includes four pre-preparation processes, which are:

[0049] (1) Construct a knowledge map of power dispatching scenarios

[0050] The process includes data collection and sorting, and then completes the construction of the knowledge graph through steps such as knowledge modeling, knowledge extraction, and knowledge fusion. The knowledge base is stored in Neo4j.

[0051] (2) Basic information maintenance

[0052] After the knowledge graph is built, a lot of data maintenance work needs to be done according to the characteristics of the business data in the power dispatching scenario and its accuracy requirements.

[0053] ◆Dictionary maintenance

[0054] a. Special...

Embodiment 2

[0164] Correspondingly, an intelligent question answering system based on the knowledge map of dispatching scenarios in the power grid field of the present invention includes:

[0165] The question acquisition module is used to acquire the question corpus in the power grid field dispatching scenario;

[0166] The entity recognition module is used to perform named entity recognition on the problem corpus to obtain the named entity recognition result;

[0167] The feature conversion module is used to convert the named entity recognition results into entities and attributes in the knowledge graph;

[0168] The sentence pattern classification module is used to carry out the sentence pattern classification to the converted result to obtain the sentence pattern classification result;

[0169] The knowledge extraction module is used to perform semantic analysis on the sentence pattern classification result, and if the sentence pattern analysis result is an understandable sentence pa...

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 an intelligent question-answering method and system based on a power grid domain scheduling scene knowledge graph. The method comprises the following steps: obtaining questioncorpora in a power grid domain scheduling scene; performing named entity identification on the problem corpus to obtain a named entity identification result; converting the named entity identificationresult into entities and attributes in the knowledge graph; carrying out sentence pattern classification on the converted result to obtain a sentence pattern classification result; conducting semantic analysis on sentence pattern classification results, and if sentence analysis results are understandable sentence patterns, extracting triple information related to the knowledge base; generating acypher query statement based on the triple information; obtaining a query result from the Neo4j knowledge base; and inputting the query result into a question and answer template in the scene classification model to generate an answer. Semantic analysis is performed on questions through a natural language processing technology, entity links and attribute links are combined to be converted into gallery query statements, results are queried from a knowledge base, and answers are obtained in combination with question and answer templates.

Description

technical field [0001] The invention belongs to the technical field of power grid dispatching, and in particular relates to an intelligent question answering method based on a dispatching scene knowledge map in the power grid field, and also relates to an intelligent question answering system based on a dispatching scene knowledge map in the power grid field. Background technique [0002] The power grid includes three major links of power generation, transmission and distribution, and the entire physical structure is a huge and complex network. Due to the characteristics of the physical structure of the power grid, the graph data structure is used to create a grid data model, which is very suitable; and the graph data structure does not have associated foreign keys, and the relationship between nodes is associated, and the performance is greatly improved compared with the traditional data structure. [0003] The intelligent question answering system has already blossomed in ...

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): G06F16/332G06F16/33G06F16/338G06F16/35G06F16/36G06F40/205G06F40/295G06F40/30G06N20/00
CPCG06F16/3329G06F16/3344G06F16/338G06F16/35G06F16/367G06F40/205G06F40/295G06F40/30G06N20/00Y04S10/50
Inventor 吴小刚辛阔邱生敏唐卓尧程哲孙雁斌梁寿愚杨凡单政博陈兴望许士锦吕耀棠王子强
Owner CHINA SOUTHERN POWER GRID COMPANY
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