Label mining method and device based on user chat records

A technology of user tags and chat records, applied in special data processing applications, natural language data processing, instruments, etc., can solve the problems of reducing user experience, difficult to obtain, and data sparsity can not be recommended services.

Active Publication Date: 2021-01-29
南京云问网络技术有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in actual usage, a large amount of information collection is a burden for users, which seriously reduces the user experience. In addition, use

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
  • Label mining method and device based on user chat records
  • Label mining method and device based on user chat records
  • Label mining method and device based on user chat records

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] The present invention will be further illustrated below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0091] Such as figure 1 As shown, the embodiment of the present invention provides a method for mining tags based on user chat records, including:

[0092] Step 1: Preprocess the chat data generated by chatting with the user through the voice assistant. Preprocessing can clean user questions and avoid the impact of data noise on accuracy. Preprocessing specifically includes Unicode, Simplified and Traditional conversion, and removal of invalid characters in sequence. The unified encoding is preferably UTF8 encoding. After the Simplified-Traditional conversion, it will be converted to...

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 label mining method and device based on user chat records. The method comprises the steps of: preprocessing chat data generated by chat between a voice assistant and a user;extracting user tags from the preprocessed chat data based on a label extraction model and a statistical method; and mining all labels with similarity higher than a set threshold based on a relationship discovery model. According to the method and device of the invention, by means of the machine learning method of the neural network, the model can select a proper label according to semanteme, anda label effect is good; after a system runs for a period of time, more user chat data can be accumulated, labeling training can be carried out again to achieve a better effect, and further optimization can be supported; after early-stage manual labeling, labels can be automatically extracted in the later stage, a large amount of manpower is saved, and the efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of voice assistants, in particular to a tag mining method and device based on user chat records. Background technique [0002] In the smart voice assistant scenario, in order to provide better services for users, it is usually necessary to build portraits and tags for users, and then recommend services to users based on these tags. [0003] Personalized recommendations are throughout the entire process of interacting with users. On the one hand, it can recommend some knowledge or business information based on the user's job characteristics, such as new policies related to it, etc. At the same time, it can also discuss related topics based on the user's personal preferences, talking about what they like to eat and what movies they like to watch etc. Become a fully humanized voice assistant, penetrate into every corner of the user's work and life, and improve user stickiness. [0004] In the current situati...

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): G06F16/33G06F16/332G06F16/35G06F40/216G06F40/289
CPCG06F16/3329G06F16/3335G06F16/3343G06F16/35G06F40/216G06F40/289
Inventor 王清琛张蹲孟凡华茆传羽杜振东程云张洪磊
Owner 南京云问网络技术有限公司
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