A dialog system automatic optimization method based on log learning

A dialogue system and automatic optimization technology, applied in the field of automatic optimization of dialogue systems based on log learning, can solve the problems of manual editing and editing of knowledge bases, consume a lot of manpower for editing and editing, and make it difficult to understand answers, so as to reduce workload, reduce manpower and material resources, and improve The effect of user experience

Active Publication Date: 2019-03-12
SHANDONG SYNTHESIS ELECTRONICS TECH
View PDF11 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These two technical models have their own advantages and disadvantages: the first model has relatively reasonable answers but requires a lot of editing manpower; the second model does not require manpower editing but often generates incomprehensible answers
[0004] A human-computer dialogue system based on a large-scale artificial knowledge base and semantic retrieval has a serious flaw: every update of the knowledge base requires manual editing.

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
  • A dialog system automatic optimization method based on log learning
  • A dialog system automatic optimization method based on log learning
  • A dialog system automatic optimization method based on log learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] refer to figure 1 , shows the overall flow of the present invention through dialogue log learning optimization dialog system, the overall flow includes the following specific modules or steps:

[0026] 1) The speech recognition module, which recognizes the user's speech as a natural language text, which is used as the text input of the feedback dialogue system in the present invention.

[0027] 2) Service identification module M1. The main function of this module is to judge whether the text input by the user is in the background knowledge base of the robot, and use the result of this recognition to label the log, and use this tag as a distinguishing mark in the log learning module of the present invention.

[0028] 3) Business matching module M2. This module is mainly used to match the identified business questions with specific entries in the knowledge base. The input content of the module is the user's questions, and the output of the module is the matched standard...

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 a dialog system automatic optimization method based on log learning, Based on log analysis, semantic recognition and knowledge extraction technology, the knowledge base in thebackground of the system will automatically expand with the gradual increase of dialogue records, and the robot will know more and more, and eventually cover all the dialogue scenarios that may be involved in the interaction, and improve the user experience. The method realized by the invention has a high level of automation, and compared with the method of using pure human power to collect and edit, the invention can greatly reduce the manpower and material resources required for system maintenance.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to the field of human-computer natural language interaction of artificial intelligence, in particular to an automatic optimization method of a dialogue system based on log learning. Background technique [0002] Log analysis technology is mainly used in the fields of security supervision and precision marketing, and its application in the field of robot dialogue is relatively rare. The work of log learning and log analysis is slightly different, but log learning includes log analysis. In addition to analyzing operation logs, log learning also uses the analysis results to optimize and improve the original operating system. Current patents involving log learning techniques include tasks such as anti-crawler and network access security, both of which fall under the domain of security oversight. [0003] There are two main technical modes for robots to realize natural language 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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F16/18G06F17/27
CPCG06F40/30
Inventor 王太浩朱锦雷张传锋申冲
Owner SHANDONG SYNTHESIS ELECTRONICS TECH
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