Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Interactive-question semantic understanding method in intelligent customer services

A technology of intelligent customer service and semantic understanding, applied in the field of semantic recognition, can solve the problem of low accuracy of semantic understanding, and achieve the effect of ensuring coherence, improving work efficiency and improving accuracy

Active Publication Date: 2018-04-27
KANGCHENG INVESTMENT CHINA
View PDF10 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a semantic understanding method for interactive questions in intelligent customer service, which is used to solve the problem of low semantic understanding accuracy in existing intelligent customer service, so as to ensure the continuity of conversation between intelligent customer service and customers

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
  • Interactive-question semantic understanding method in intelligent customer services
  • Interactive-question semantic understanding method in intelligent customer services
  • Interactive-question semantic understanding method in intelligent customer services

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The specific implementation of the method for semantic understanding of interactive questions in intelligent customer service provided by the present invention will be described in detail below in conjunction with the accompanying drawings.

[0059] The way to realize flow processing in the current interactive question-and-answer processing is mainly through flow charts. The currently widely used interactive question answering based on flowchart is mainly implemented in the following two ways: through constructing question answering trees and through intent recognition and task templates.

[0060] Realizing interactive question and answer processing by constructing a question and answer tree refers to processing appropriate answers in interactive question and answer by constructing a two-layer flowchart to calculate the relationship between nodes. Among them, the first-level flow chart is the classification tree of the corpus, and each classification node of the classif...

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 provides an interactive-question semantic understanding method in intelligent customer services. The method includes the following steps that the conversation content between current intelligent customer services and clients is subjected to co-text language environment expression, wherein co-text language environment expression comprises event expression and language environment expression; according to the co-text language environment expression, a conversation semantic event graph is constructed; according to multiple conversation corpora of the intelligent customer services and the clients, a business logic tree is constructed; according to a determined finite state automata, an order state machine is established; according to the semantic event graph, logic decision branches are selected from the business logic tree; according to the logic decision branches and the order state machine, a semantic processing template is returned to the intelligent customer services, and semantic expression generation is carried out. According to the interactive-question semantic understanding method in the intelligent customer services, interaction questions and answers based on aflow diagram are achieved, the accuracy of client interrogation understanding of the intelligent customer services is increased, the consistency between the intelligent customer services and client conversations is guaranteed, and the work efficiency of the intelligent customer services is improved.

Description

technical field [0001] The invention relates to the technical field of semantic recognition, in particular to a method for understanding the semantics of interactive questions in intelligent customer service. Background technique [0002] According to statistics, the ratio of the number of orders to the number of consulting users of e-commerce websites is about 4%. The ratio will vary for different types of e-commerce websites, but overall from this ratio, it can be seen that the cost pressure of customer service on e-commerce websites is huge. , and with the continuous development of business and the increase in the number of orders, the cost of customer service will become higher and higher, which greatly restricts the cost control of e-commerce. Therefore, the research and development of e-commerce intelligent customer service system is extremely urgent. [0003] Semantic understanding itself is difficult to define, and the current realization of true semantic understandi...

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): G06F17/27G06F9/448G06Q30/06G06N5/04
CPCG06N5/046G06Q30/01G06Q30/0635G06F16/322G06F16/3329G06F16/35G06F16/367G06F40/216G06F40/253G06F40/284G06F40/30
Inventor 章振增谭明
Owner KANGCHENG INVESTMENT CHINA
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
Eureka Blog
Learn More
PatSnap group products