Identification method and system for intelligent quality inspection of service forbidden words

A recognition method and technology of forbidden language, applied in semantic analysis, natural language data processing, digital data information retrieval, etc., can solve problems such as inaccurate quality inspection results, inability to meet actual needs, and non-standard customer service, so as to improve accuracy rate effect

Active Publication Date: 2020-04-28
GUANGZHOU BAILING DATA CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the quality inspection method of service ban in intelligent quality inspection is relatively single. It is often to directly search the service ban keyword for the content of the customer service conversation text....

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
  • Identification method and system for intelligent quality inspection of service forbidden words
  • Identification method and system for intelligent quality inspection of service forbidden words
  • Identification method and system for intelligent quality inspection of service forbidden words

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] The present invention is used in the recognition method of the forbidden words of the intelligent quality inspection service, and the overall process is as follows figure 1 , including the following steps:

[0027] S1. Data input, text transcription: transcribe customer service recording data into customer service text data.

[0028] S2. Text preprocessing: perform letter case conversion and part-of-speech tagging on the transcribed customer service text data. Since the letter case of the text data is not uniform, the letter case conversion can ensure the consistency of the text data, so the lowercase letters in the text data are uniformly converted into upper letters. Part-of-speech tagging uses a statistical model-based tagging method to mark the part-of-speech of each word after sentence segmentation through the part-of-speech tagging set, so as to facilitate the application of subsequent text semantic analysis.

[0029] S3. Keyword search: match the preprocessed t...

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 a natural language processing technology, in particular to an identification method and system for intelligent quality inspection of service forbidden words, and the method comprises: performing text transcription and text preprocessing, i.e., carrying out the letter capital and lower-case conversion and part-of-speech tagging of text data of customer service; performing keyword retrieval; performing text transcription error identification, i.e., judging whether text transcription is reasonable or wrong according to historical customer service session text data; performing text semantic analysis, i.e., analyzing semanteme of the text in the customer service session content hitting the service forbidden word keyword to obtain an identification result of whether thesupport staff uses forbidden words or not ; and filtering an identification result that the support staff does not use forbidden words to obtain a final inspection result. The context of the keywordsin the text and historical session text data are combined in the text analysis process, and the accuracy of quality inspection is improved through rule matching.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a method and system for identifying forbidden words in intelligent quality inspection services. Background technique [0002] Service quality inspection is a very important quality control link in the hotline service operation process. Traditional service quality inspection mainly relies on manual random inspection of daily agent recordings for follow-up and analysis. Formulate improvement plans and implement improvement plans for various problems found, so as to further improve the internal service quality control system, and objectively and truly reflect the rapid response and close cooperation between the front desk and the back office of the call center from the data. Look for service shortcomings, put forward suggestions and suggestions for improvement, and assist in business process improvement, so as to continuously improve the service level of...

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): G06F40/151G06F40/242G06F40/30G06F16/332G06F16/33
CPCG06F16/3344G06F16/3346G06F16/3329Y02P90/30
Inventor 姜磊杨钊赖招展许伟斌周晓明朱振航何慧沈广盈屈吕杰
Owner GUANGZHOU BAILING DATA CO 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