Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Robot knowledge base construction system and method based on synonymous multi-context analysis

A technology for building methods and knowledge bases, applied in semantic analysis, knowledge expression, instruments, etc., which can solve problems such as monotony, inability to fully realize the diversity and richness of artificial responses, and the inability of response content to be accurate and correct.

Active Publication Date: 2020-03-06
STATE GRID CORP OF CHINA +2
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1) Due to the large business volume, many people are required to cooperate to complete the consulting services for the vast number of power users, and it is impossible to achieve indiscriminate services with absolutely the same standards;
[0004] 2) The method of manual response service is affected by individual emotions and work status, and the content of the response cannot be accurate;
[0005] 3) Unable to provide 24-hour all-weather service with high quality and high quantity
This method of knowledge base matching, since the output result is the content of the knowledge base with the highest matching rate, it will produce a unique result for any same question. richness

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
  • Robot knowledge base construction system and method based on synonymous multi-context analysis
  • Robot knowledge base construction system and method based on synonymous multi-context analysis
  • Robot knowledge base construction system and method based on synonymous multi-context analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] The technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention.

[0083] Such as figure 1 As shown, the embodiment of the present invention provides a method for constructing a robot knowledge base based on synonymous multi-context analysis, including the following steps:

[0084] Step S1, sorting out the traditional knowledge base: sorting out and reconstructing the traditional knowledge base to realize filtering of redundant data, correction of obsolete data, and screening and correction of typos. The specific implementation method is:

[0085] 1) The traditional knowledge base is a "question-answer" content pair, first sorted according to the content of the question, and export all the sorted results from the database to the excel table;

[0086] 2) In the excel sheet, check the content of the questions one by one, and merge or delete the entries with the same or...

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 robot knowledge base construction system and method based on synonymous multi-context analysis, which realize the scheme from seven aspects of traditional knowledge base arrangement, question bank word segmentation, response bank word segmentation, synonymous expansion, context analysis, knowledge base indexing and new knowledge base construction. The method comprises: firstly, arranging an original knowledge base; performing word segmentation processing on the questioning sentences and the answering sentences in the knowledge base, and extracting keywords; performingsimilarity calculation and synonymy expansion on the keywords; determining adaptation scores of the keywords in the statement at the same time through context analysis, and constructing a multi-way tree index keyword at the same time; and finally, constructing a new knowledge base, and flexibly and randomly replacing synonyms in the response words by realizing similarity calculation of the synonyms, thereby realizing construction of the knowledge base with unchanged response theme content and diversified response modes.

Description

technical field [0001] The present invention relates to the field of electronic information technology, in particular to a system and method for constructing a robot knowledge base based on synonymous multi-context analysis, which establishes a robot knowledge base system with automatic semantic association to support the diversification of terms used by answering robots, Anthropomorphic question and answer to realize fully automatic and accurate customer question response for electric power customer service. Background technique [0002] Responding to inquiries and questions from network users is an important part of the daily work of electric power customer service, and it is the main window for improving service quality and gathering user reputation. The traditional manual user response method can no longer meet the service needs of the majority of power users, mainly reflected in: [0003] 1) Due to the large business volume, many people are required to cooperate to com...

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): G06F16/33G06F16/332G06F16/35G06F40/289G06F40/30G06N5/02
CPCG06F16/3329G06F16/3344G06F16/35G06N5/022Y02D10/00
Inventor 陈沙沙上官朝晖刘首文应君裕李凡温兵兵廖玉坤刘奕
Owner STATE GRID CORP OF CHINA
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
Eureka Blog
Learn More
PatSnap group products