Customer voice intelligent insight system

A customer-oriented and intelligent technology, applied in speech analysis, speech recognition, digital data information retrieval, etc., can solve the problems of undiscovered products covering the whole process, and achieve the effect of product improvement and service improvement

Pending Publication Date: 2020-11-20
CHINA FIRST AUTOMOBILE
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the existing similar technologies only focus on a certain part, such as network information acquisition, etc., but so far no product has been found that can cover the entire process from network information acquisition, semantic analysis to multi-mode presentation, and closed-loop problems

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
  • Customer voice intelligent insight system
  • Customer voice intelligent insight system
  • Customer voice intelligent insight system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] like figure 1As shown, the customer voice intelligence insight system of the present invention includes a text preprocessing engine and a pre-trained business label recognition model, an emotion recognition model and a physical part recognition model; the customer voice data is cleaned through the text preprocessing engine to filter out meaningless Words and words, and then perform word segmentation and ngram processing to obtain word segmentation character variables corresponding to individual characters and words and equal-length character variables corresponding to sentences of equal length; word segmentation character variables and equal-length character variables are respectively input into pre-trained business The label recognition model, the emotion recognition model and the entity part recognition model respectively obtain the business label, emotion label, entity part label and question label confirmed by the model recognition.

[0039] The business label recog...

Embodiment 2

[0050] like figure 1 As shown, the customer voice intelligence insight system of the present invention includes a text preprocessing engine and a pre-trained business label recognition model, an emotion recognition model and a physical part recognition model; the customer voice data is cleaned through the text preprocessing engine to filter out meaningless Words and words, and then perform word segmentation and ngram processing to obtain word segmentation character variables corresponding to individual characters and words and equal-length character variables corresponding to sentences of equal length; word segmentation character variables and equal-length character variables are respectively input into pre-trained business The label recognition model, the emotion recognition model and the entity part recognition model respectively obtain the business label, emotion label, entity part label and question label confirmed by the model recognition.

[0051] The business label reco...

Embodiment 3

[0062] like figure 2 As shown, the training methods of the business label recognition model, emotion recognition model and entity part recognition model are as follows:

[0063] Step 1. Collect about 20,000 pieces of Internet customer voice data for a period of time and manually label them by experts, that is, give each piece of customer voice data corresponding to manually labeled business labels, emotional labels, and related physical part labels and question labels, as shown in Table 1;

[0064] Table 1

[0065]

[0066] Among them, the attribution relationship involved in manual labeling of business tags has three levels, with a total of 85 tags: the first-level business tags are divided into two categories: product (for the R&D department) and marketing (for the sales department) according to the business structure; The user perception contacts in the experience and sales process are divided into 18 categories; the third-level business labels are further subdivided i...

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 relates to an intelligent customer voice insight system. The system comprises a text preprocessing engine, a pre-trained service label recognition model, an emotion recognition model andan entity part recognition model, wherein client voice data is cleaned through a text preprocessing engine, meaningless characters and words are filtered out, then word segmentation and ngram processing are carried out, and word segmentation character variables corresponding to single characters and words and equal-length character variables corresponding to sentences equal in length are obtained, and the word segmentation character variable and the equal-length character variable are respectively inputted into a pre-trained service label identification model, an emotion identification modeland an entity part identification model to obtain a service label, an emotion label, an entity part label and a problem label which correspond to the customer voice data and are identified and confirmed by the models. According to the method, accurate semantic analysis and sentiment analysis can be carried out on the voice of the customer by crawling all comment contents of related channels, so product improvement and service promotion are realized.

Description

technical field [0001] The invention belongs to the technical field of product monitoring and relates to a customer voice intelligence insight system. Background technique [0002] With the development of the Internet industry and various social media, more and more users choose to express their experience on social media and other channels, which also makes companies start to reach users by grabbing customer voices on the Internet , Solve the problems reported by users on the network media in a timely manner, and control the spread of negative public opinion. There are also many technologies for obtaining customer voices on the existing market, but basically there are certain defects. [0003] Most of the existing similar technologies only focus on a certain part, such as network information acquisition, etc., but so far no product has been found that can cover the entire process from network information acquisition, semantic analysis to multi-mode presentation, and closed...

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): G06F40/279G06F40/289G06F40/205G06F40/30G06F16/335G10L15/22G10L25/63
CPCG10L15/22G10L25/63G06F16/335G06F40/205G06F40/279G06F40/289G06F40/30
Inventor 奚天奇路帅冯彪田明刘颖王朝徐智
Owner CHINA FIRST AUTOMOBILE
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