An intelligent customer service response method and system

A technology of intelligent customer service and customer service, applied in the field of intelligent customer service, can solve problems such as low response efficiency and poor user experience, and achieve the effects of improving user experience, ensuring accuracy, ensuring accuracy and real-time

Active Publication Date: 2021-03-26
南京星云数字技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide an intelligent customer service response method and system, which can solve the problems of low response efficiency and poor user experience in the prior art relying on manual customer service

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
  • An intelligent customer service response method and system
  • An intelligent customer service response method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] see figure 1 , the present embodiment provides an intelligent customer service answering method, including:

[0054] Step S1, preprocessing customer service historical chat sentences to export customer service corpus, obtaining a language recognition model through word segmentation training on customer service corpus, and building a business knowledge base by presetting business modules in multiple fields. The business module stores an elasticsearch database of knowledge data in this field, Knowledge data includes keyword answers, indexes and corresponding search fields; step S3, preset greeting keywords and corresponding answers to build a greeting scene knowledge base, when the corpus of user questions hits the greeting keywords after word segmentation by the language recognition model, then from the greeting scene Call the corresponding answer from the knowledge base to answer the user. When the corpus of the user’s question does not hit the greeting keyword after th...

Embodiment 2

[0071] see figure 1 with figure 2 , the present embodiment provides an intelligent customer service response system, including:

[0072] Model training unit 1 is used to preprocess customer service historical chat sentences to export customer service corpus, obtain a language recognition model through word segmentation training on customer service corpus, and preset business modules in multiple fields to build a business knowledge base. The business modules store knowledge data in this field The elasticsearch database, knowledge data includes keyword answers, indexes and corresponding search fields;

[0073] Greeting scene unit 3, which is used to preset greeting keywords and corresponding answers to build a greeting scene knowledge base. When the corpus asked by the user hits the greeting keyword after word segmentation by the language recognition model, the corresponding answer is called from the greeting scene knowledge base to answer the user , when the corpus asked by ...

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 intelligent customer service response method and system, relates to the technical field of intelligent customer service, and can solve the problems of low response efficiency and poor user experience caused by manual customer service in the prior art. The method includes: preprocessing customer service historical chat sentences to export customer service corpus, and obtaining a language recognition model through word segmentation training on customer service corpus; performing intent recognition and matching corresponding business modules on the corpus of user questions, and using the result of intent recognition in the elasticsearch corresponding to the business module The database is searched and analyzed, and the output related keyword answers are summarized to form a pre-selected data set; the text formed after word segmentation of the user question corpus is used as input to perform elasticsearch retrieval in the pre-selected data set to output candidate keyword answers; the word-segmented keywords and candidate The keyword answers are converted into word vectors, and the WMD algorithm is used to calculate the similarity between each word segmentation keyword and each candidate keyword answer, and the keyword answer is selected to answer the user based on the similarity value.

Description

technical field [0001] The present invention relates to the technical field of intelligent customer service, in particular to an intelligent customer service answering method and system. Background technique [0002] With the rapid development of e-commerce business, the rapid increase in the number of customer service inquiries has brought a lot of pressure on the customer service work of the platform, especially during the "Double Eleven" and other major shopping festivals, the manual customer service system alone can no longer meet the needs. Business needs, and at the same time, it is impossible to provide 7*24 hours of uninterrupted consulting services. For customers, if they cannot get timely and accurate responses, it will lead to poor user experience. Contents of the invention [0003] The purpose of the present invention is to provide an intelligent customer service response method and system, which can solve the problems of low response efficiency and poor user e...

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): G06F16/332G06F16/33G06F40/242G06F40/289G06F40/30
CPCG06F16/3329G06F16/3344G06F40/242G06F40/289G06F40/30
Inventor 龚雪飞周彬汤毅平杜柏圣
Owner 南京星云数字技术有限公司
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