User question and knowledge point matching method and device

A knowledge point and user technology, applied in the computer field, can solve problems such as poor matching effect, difficult model training, and poor quality of intelligent customer service service, and achieve the effect of improving service quality and matching effect.

Active Publication Date: 2019-06-07
ADVANCED NEW TECH CO LTD
View PDF8 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these models all have some problems: for example, some models are poor in disambiguation and multi-result selection, and some models are difficult to train and have poor results.
In short, the existing customer service system does not perform well in matching user questions and knowledge points, and the service quality of intelligent customer service is not good.

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
  • User question and knowledge point matching method and device
  • User question and knowledge point matching method and device
  • User question and knowledge point matching method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The solution provided in this specification will be described below with reference to the accompanying drawings.

[0047] In the embodiment of this specification, a matching model based on business maps (also referred to as a natural language processing model) and a deep structured semantic model (DSSM) are combined, and the matching result of the map is used as the For the input of the deep structured semantic model, the matching results of the map are sorted and optimized through the deep structured semantic model, which can improve the matching effect between user questions and knowledge points, and correspondingly improve the service quality of intelligent customer service. Deep structured semantic model is a modeling technology based on deep neural network, which can project different types of text with pairwise relationship into a common low-dimensional semantic space, and then complete the subsequent machine learning tasks. This specification In the embodiment, 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 embodiment of the invention provides a user question and knowledge point matching method and device. The method comprises the following steps: taking the user question as the input of a pre-trained natural language processing model; obtaining a matching node set formed by semantic nodes matched with the user question in a pre-established service guide graph, when the matching node set is matched with a plurality of links of the service guide map, the service guide map is matched; adding the knowledge points mounted on the leaf node of each link into a knowledge point set matched with the question of the user; taking the user question and the knowledge point title of each knowledge point in the knowledge point set as the input of a pre-trained deep structured semantic model; obtaining the similarity between the user question and the knowledge point title of each knowledge point in the knowledge point set; according to the similarity between the user question and the knowledge pointtitle of each knowledge point in the knowledge point set, the knowledge points matched with the user question are determined, the matching effect between the user question and the knowledge points canbe improved, and the service quality of the intelligent customer service is correspondingly improved.

Description

technical field [0001] One or more embodiments of this specification relate to the computer field, and in particular, to a method and apparatus for matching user questions and knowledge points. Background technique [0002] In intelligent customer service, the user's language is colloquial and simplified in the process of interaction with the robot, and improving the matching ability and effect of the customer service robot is very important to the entire customer service system, which directly affects the service experience of the customer service system. [0003] The traditional customer service system can be roughly divided into four modules according to the common characteristics of its framework. The four modules are: question analysis, phrase mapping, disambiguation and query construction. The existing customer service system models usually use the method of calculating the text similarity between the input text and the target text to complete the matching between the...

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): G06F16/332G06F16/33
Inventor 马良庄石志伟胡翔张望舒刘俊宏蔡捷
Owner ADVANCED NEW TECH 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