User portrait modeling method and system based on topic detection in text dialogue

A modeling method, a technology in dialogue, applied in the fields of semantic tool creation, electronic digital data processing, digital data information retrieval, etc., which can solve problems such as incapable of intelligent answering by users, addition of dialogue topic factors, etc.

Active Publication Date: 2021-08-31
EMOTIBOT TECH LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, the technical defect in the prior art is: in the existing human-computer dialogue system, there is no dialogue topic factor representing the user's personality added to the user portrait, so that in the process of man-machine dialogue, it is impossible to give more intelligent information according to the user's personality. answer

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
  • User portrait modeling method and system based on topic detection in text dialogue
  • User portrait modeling method and system based on topic detection in text dialogue

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 It shows a flow chart of a user portrait modeling method based on topic detection in text dialogue provided by the first embodiment of the present invention; figure 1 As shown, the user portrait modeling method based on topic detection in text dialogue provided by Embodiment 1 of the present invention includes:

[0050] Step S1, obtaining multiple topics of the text input by the user through the topic recognition system, the multiple topics include main topics and secondary topics;

[0051] Step S2, mapping multiple topics into a graph-structured topic relationship graph to form a topic map;

[0052] Step S3, update the topic map through logical rules or machine learning methods to obtain the user portrait of the user.

[0053] The technical solution of the user portrait modeling method based on topic detection in text dialogue provided by the present invention is: firstly obtain multiple topics of the text input by the user through the topic recognition syst...

Embodiment 2

[0108] The user portrait modeling method based on topic detection in text dialogue provided by Embodiment 1 of the present invention, and the user portrait modeling system 10 based on topic detection in text dialogue are applied to a man-machine dialogue system, and the specific process is as follows:

[0109]The user enters a text sentence, for example: Is there any news about Faye Wong?

[0110] The topic recognition system detects the topic in the sentence that the user is talking about. For example, the main topic in the previous sentence is "artist" and the secondary topic is "singer";

[0111] Map the main topic "artist" and the secondary topic "singer" to the topic map;

[0112] According to logical rules or machine learning algorithms, the personalized map (topic map) is updated. Through the topic map, it is possible to know the degree of personal preference for different topics and give intelligent answers.

[0113] Through the user portrait modeling method and syste...

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 present invention provides a user portrait modeling method and system based on topic detection in text dialogue. The method is: obtain multiple topics of text input by the user through a topic recognition system, and the multiple topics include main topics and secondary topics; Map multiple topics into a graph-structured topic relationship graph to form a topic map; update the topic map through logical rules or machine learning methods to obtain user portraits of users. The user portrait modeling method and system based on topic detection in the text dialogue of the present invention divides the topics in the user dialogue text into main topics and secondary topics, and establishes a topic graph for the main topics and secondary topics, according to each user The topics contained in the conversation content of the user update the topic map to obtain the user portrait of the user. According to the user portrait, in the process of man-machine dialogue, the user's personality factors are considered to make the man-machine dialogue more intelligent.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to the field of artificial intelligence dialogue. Background technique [0002] Existing artificial intelligence dialogue systems model users based on their own information, such as gender, age, hometown, occupation, etc., and do not take user personality, such as topics of interest, as factors in forming user portraits. In natural conversations between people, frequently discussed topics represent personal interests. Therefore, in the artificial intelligence dialogue system, the topic that the user is interested in is an important factor in the user portrait. [0003] Therefore, the technical defect in the prior art is: in the existing man-machine dialogue system, there is no dialogue topic factor representing the user's personality added to the user portrait, so that in the process of man-machine dialogue, it is impossible to give more intelligent information according to t...

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 Patents(China)
IPC IPC(8): G06F16/332G06F16/36
CPCG06F16/3329G06F16/367
Inventor 简仁贤李佳纯
Owner EMOTIBOT TECH LTD
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