Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Conversation management method and system of outbound system, electronic equipment and storage medium

A dialogue management and pre-storage technology, applied in neural learning methods, telephone communication, electrical components, etc., can solve the problems that the outbound system cannot communicate with users in spoken language, and achieve the effects of humanized communication, labor cost saving, and flexible design

Pending Publication Date: 2020-05-05
CTRIP COMP TECH SHANGHAI
View PDF9 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a dialogue management method, system, electronic equipment and storage medium for an outbound system in order to overcome the defect that the outbound system cannot communicate with users in spoken language in the prior art

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
  • Conversation management method and system of outbound system, electronic equipment and storage medium
  • Conversation management method and system of outbound system, electronic equipment and storage medium
  • Conversation management method and system of outbound system, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] This embodiment provides a dialog management method for an outbound call system. Such as figure 1 As shown, the dialogue management method of the outgoing call system of the present embodiment includes the following steps:

[0069] Step S101, acquiring semantic information;

[0070] Step S102, updating the current dialog state according to the semantic information;

[0071] Step S103, inputting the dialogue state into a pre-stored state machine to perform a state jump;

[0072]Step S104, the outbound call system outputs a question and answer according to the state after the state machine jumps. The dialog management method of the outbound system in this embodiment can realize oral communication between the user and the outbound system, and the outbound system can reply to the user's questions, realize humanized communication, improve user acceptance, and save a lot of labor costs for the enterprise. When the user side is an extension, the outbound call system of the...

Embodiment 2

[0074] On the basis of Embodiment 1, this embodiment provides a dialog management method for an outbound call system. Such as figure 2 As shown, after step S104, the dialog management method of the outbound call system of this embodiment further includes the following steps:

[0075] Step S201, after the state machine jumps to the preset state, input the semantic information into the pre-trained reinforcement learning model;

[0076] Step S202, the outbound call system outputs a question and answer according to the output result of the reinforcement learning model.

[0077] The dialogue management method of the outbound call system of this embodiment uses the trained reinforcement learning model for dialogue management, and uses the state machine to quickly collect man-machine dialogue data during the initial cold start of the dialogue for the training of the reinforcement learning model. In the hot start phase, switch to the reinforcement learning model for dialogue explor...

Embodiment 3

[0079] On the basis of Embodiment 2, this embodiment provides a dialog management method for an outbound call system. Such as image 3 As shown, before step S101, the dialog management method of the outbound call system of this embodiment also includes the following steps:

[0080] Step S100, acquiring slot information in domain information, which is used to form a dialog state;

[0081] Divide according to different fields, and determine the information that needs to be obtained according to the field information. For example, for the common order confirmation field in the OTA industry, the OTA manufacturer in this field confirms to the hotel whether an order can be accepted, and extracts the slot information that needs to be obtained, such as : Can be determined, if not sure, extract the reason. According to the slot information, the robot's actions are targeted. For example, if the acquired slot information includes "sure", "full room", "not cooperative", etc., the robot ...

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 conversation management method and system of an outbound system, electronic equipment and a storage medium. The conversation management method comprises the steps of obtaining semantic information; updating a current dialogue state according to the semantic information; inputting the dialogue state into a pre-stored state machine to carry out state jump, wherein the outbound system outputs questions and answers according to the skipped state of the state machine, and uses reinforcement learning to improve the generalization performance of the dialogue system. According to the conversation management method of the outbound system, spoken language communication between the user and the outbound system can be achieved, the outbound system can reply to the problem ofthe user, humanized communication is achieved, the acceptability of the user is improved, a large amount of labor cost is saved for enterprises, and when the user side is an extension set, the outbound system can achieve switching and is flexible in design.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a dialog management method, system, electronic equipment and storage medium of an outbound call system. Background technique [0002] For some service industries, such as the OTA (online travel) industry, there is a great demand for outbound calls, and many OTA companies will have their own outbound call systems. The existing outbound system uses the IVR (Interactive Voice Response) system. The user can give information feedback through the buttons, and the user cannot communicate with the outbound system in spoken language. The existing outbound system cannot reply to the user's questions. For the user In the case of an extension, the existing outbound call system cannot implement transfer. The existing outbound call system is rigid in design, lacks humanized communication, and has low user acceptance. Contents of the invention [0003] The technical probl...

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): G06F16/332G06F16/903G06F16/33G06N3/08H04M3/493
CPCG06F16/3329G06F16/90344G06F16/3344G06F16/3343G06N3/08H04M3/4936
Inventor 江小林罗超胡泓
Owner CTRIP COMP TECH SHANGHAI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com