Multi-service scene dialogue method and system

A dialogue system, multi-service technology, applied in the field of communication, can solve the problems of poor flexibility, cumbersome operation, high cost of BERT model training, and achieve the effect of making up for the time-consuming training and quick response

Pending Publication Date: 2021-05-04
青牛智胜(深圳)科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, in order to realize intent recognition, classification algorithms are mostly used, that is, to fix the category of dialog intent first, and then to identify; the shortcomings of this method include: it cannot be applied to multi-service scenarios, and the flexibility is poor. If you need to increase the dialog intent in real time, you must use Fast response server; BERT model and dialogue process are one-to-one correspondence, poor versatility, and the construction of dialogue process is difficult and cumbersome to operate; BERT model has high training cost, large amount of data, time-consuming training, and slow response

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
  • Multi-service scene dialogue method and system
  • Multi-service scene dialogue method and system
  • Multi-service scene dialogue method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024]The embodiment of the present invention provides a multi-service scene conversation method, such asfigure 1 As shown, including the following steps:

[0025]Step S1: After receiving the reply statement, it is determined whether there is a backpoint pair in the database.

[0026]In this embodiment, the standby statement to be repurchant can stem from the purchase of the product / server or the caller or provide the product / service party, the statement can be a text message or voice message. If a voice message, use the ASR to first convert into text, if the text The message does not need to be converted; the backup dialogue is mainly used in the process of use according to the actual needs.

[0027]Step S2: If there is no dialogue, the BERT model to be recovered by the statement is entered, and the induction classification will be dialogue, according to the intended dialogue intention and its associated initial reply;

[0028]If there is a back-to-diverse point, all the backup dialogue is...

Embodiment 2

[0055]The embodiment of the present invention provides a multi-service scene conversation system, a multi-service scenario conversation method, such as the implementation of the embodiment, such asimage 3As shown, including:

[0056]The determination unit 10 is used to determine if there is a backpoint in the database after receiving the reply statement;

[0057]The classification unit 11 is used for non-replenishing dialogue intentions, and the BERT model to be recovered by the statement is intended to classify.

[0058]The reply unit 12 is used to respond to the initial reply content according to the intended conversation and its associated initial reply;

[0059]The comparison unit 13 is used to compare all the backup dialogue and the standby statement when there is a backup dialogue.

[0060]The reply unit 12 is also used to reply according to the backup dialogue and the retrievalful reply content associated with the backup dialogue that is the most similar to the statement of the statement to...

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 multi-service scene dialogue method and system. The method specifically comprises the steps of judging whether there is a post-complement dialogue intention in a database or not after a to-be-replied statement is received; if no post-complement dialogue intention exists, inputting the to-be-replied statement into the trained BERT model for dialogue intention classification, and replying according to the obtained dialogue intention and the associated initial reply content; if the post-complementdialogue intention exists, comparing all post-complement dialogue contents with the to-be-replied statement; if the obtained similarity is not less than the preset value when the obtained similarity is the maximum, replying according to the post-complement dialogue intention associated with the post-complement dialogue content most similar to the statement to be replied and the post-complement reply content associated with the post-complement dialogue content; and if the obtained similarity is still less than the preset value when the obtained similarity is maximum, skipping to the step of inputting the BERT model. The problem of multi-round intelligent dialogues in different business scenes can be solved, quick response is realized, the defects of time consumption and response delay of BERT model training are overcome, and meanwhile, different dialogue processes share the same intention classification model.

Description

Technical field[0001]The present invention relates to the field of communication technologies, and more particularly to a multi-service scene conversation method and system.Background technique[0002]AI dialogue robots can replace automatic reply. At present, in order to implement intent, mostly use the classification algorithm, the first fixed dialogue category, then identify; the shortcomings of this method include: unable to apply to multi-service scene, flexible, if needed to increase the conversation in real time, must be used Quick response server; BERT model and dialog process is a corresponding, poor genericity, and the difficulty of the conversation process is difficult, and the operation is cumbersome; the training cost of the BERT model is high, the data volume is large, the training consumption, and the reaction is hysteresis.[0003]Therefore, there is still a need to improve the existing business scene dialogue method to solve the above deficiencies.Inventive content[0004...

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): G06F16/332G06F16/33G06F16/35G06F40/194
CPCG06F16/3329G06F16/3343G06F16/3344G06F16/355G06F40/194
Inventor 余代康袁小琴
Owner 青牛智胜(深圳)科技有限公司
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