Automatic answering method and device based on Bayesian network reasoning

A Bayesian network, automatic technology, applied in the field of artificial intelligence, can solve problems such as rigidity, the overall dialogue is not reasonable, and not humanized enough, and the overall dialogue is accurate.

Active Publication Date: 2019-10-08
广州探迹科技有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current question and answer system often ignores this part, making the overall dialogue seem unreasonable, rigid, and not humane 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
  • Automatic answering method and device based on Bayesian network reasoning
  • Automatic answering method and device based on Bayesian network reasoning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0040] see figure 1 , figure 1 It is a schematic flowchart of an embodiment of an automatic answering method based on Bayesian network reasoning provided by the present invention; an embodiment of the present invention provides an automatic answering method based on Bayesian network reasoning, including steps S1-S6;

[0041] S1. Obtain the call data of the user in the dialogue graph, and extract actual dialogue data from the call data.

[0042] S2. Predict the re...

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 automatic answering method based on Bayesian network reasoning. The method comprises the steps of obtaining the conversation data of a user in a conversation map, extractingthe actual conversation data from the conversation data; predicting the response probability of each speech node of the actual dialogue data through the dialogue map; obtaining a first response probability, analyzing the actual dialogue data reasonably; generating records with correct answers; summarizing the records with correct answers into the reasonable conversation data; carrying out speechnode statistics on the reasonable conversation data according to the knowledge base response mapping table; obtaining the bayesian network distribution, and predicting the response probability of eachspeech node of the reasonable conversation data to obtain the second response probability, the rationality of the first response probability and the second response probability is judged, judging thereasonability of the first response probability and the reasonability of the second response probability, generating the response probability after rationality judgment, and outputting the tactical node with the maximum response probability, so that the dynamic judgment can be conducted on the original dialogue map prediction data, and the overall dialogue is more accurate and more intelligent.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an automatic answering method and device based on Bayesian network reasoning. Background technique [0002] Most of the automatic answering systems currently built integrate sub-modules such as intent analysis, sentiment analysis, multi-round conversations, and knowledge questions and answers, and are deduced and managed according to the carefully designed dialogue graphs to complete the actual dialogue. [0003] However, since the dialogue map needs to be pre-designed, and with the increase in the size of the speech node, the workload of this design will also increase significantly, and it is easy to hide more design irrationality. In addition, knowledge questions and answers often correspond to a large number of speech skills, and these knowledge contents are often closely related. The current question answering system often ignores this part, making the overal...

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): G06F16/332G06N5/04G06N7/00
CPCG06F16/3329G06N5/04G06N7/01
Inventor 陈开冉黎展陶峰
Owner 广州探迹科技有限公司
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