Question classification method in computer question and answer system

A question answering system and classification method technology, applied in computing, text database clustering/classification, special data processing applications, etc., can solve problems such as difference and incomplete expression, and achieve the effect of improving applicability and improving readiness.

Active Publication Date: 2019-09-20
THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, there are some flaws in the user intent recognition of questions that only rely on natural language dialogue. On the one hand, the user's question may be expressed incompletely; on the other hand, in different contexts...

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
  • Question classification method in computer question and answer system
  • Question classification method in computer question and answer system
  • Question classification method in computer question and answer system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0083] In Embodiment 2, the implementation process of the present invention is described by taking the mobile phone voice assistant as an example. The invention belongs to the natural language understanding content of the natural language processing part in the voice assistant. The input is speech recognition to generate user natural language questions, and the output is the user's intention classification. The processing is mainly divided into two parts, including the offline preprocessing part and the online prediction part.

[0084] The offline preprocessing part mainly includes data labeling and model training. Specifically, the data annotation is mainly to obtain the user's historical questions, and for each sentence, mark the context information composed of 10 words and the intent field to which the question belongs. The domain of intent covers services supported by mobile assistants, such as chatting, dialing, SMS, ticket booking, alarm clock, etc., and contextual inf...

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 a question classification method in a computer question and answer system, which is used for classifying and predicting questions of a user based on context data of the user. The method mainly comprises the following steps: 1, constructing context environment information influencing user intention according to an intelligent question and answer system application field; 2, obtaining the situation information data of the user by means of user portrait construction, log analysis and sensor reading; thirdly3, designing a problem intention prediction network based on an attention mechanism is designed, embedding the situation information is embedded into a problem, forming the problem distributed representation considering the situation is formed, and substituting the problem is substituted into the model for prediction; and 4, performing the model training and prediction. The method solves the problems that the user intention identification only depends on the problem of natural language dialogue, the problem of incomplete expression of the user is possible, and the expression meanings of the questions under different backgrounds are different, and the intention identification accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of natural language intelligent question answering, in particular to a method for classifying question sentences in a computer question answering system. Background technique [0002] Chatbots, voice assistants, and automatic customer service have brought great convenience to people's lives, and at the same time saved labor costs in some industries. They are currently hot research topics in natural language processing. The success of these applications depends not only on the recognition of speech content, but also on the understanding of the meaning of sentences, which is called intent recognition. Intent recognition aims to determine the intent of user conversations, which can be viewed as a classification problem. Define various possible intentions in this field in advance, and then use the classification method to classify questions into certain types of intentions and hand them over to the dialogue man...

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): G06F16/35G06F16/332G06N3/04
CPCG06F16/355G06F16/3329G06N3/044G06N3/045
Inventor 吴振锋荀智德陆辰葛唯益贺成龙王振宇
Owner THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
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