Interaction method and system for intelligent man-machine conversation and electronic equipment

An interactive system and human-computer dialogue technology, applied in the computer field, can solve problems such as lack of context understanding ability, rigid reply, deviation of reply content, etc., to achieve the effect of improving flexibility and richness, and increasing usage viscosity

Pending Publication Date: 2021-06-11
ZTE CORP
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most of the customer service is not user-friendly, and the replies are relatively rigid; and lack of good context understanding ability, semantic recognition is not accurate, resulting in large deviations in reply content, affecting user experience

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
  • Interaction method and system for intelligent man-machine conversation and electronic equipment
  • Interaction method and system for intelligent man-machine conversation and electronic equipment
  • Interaction method and system for intelligent man-machine conversation and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0125] Example 1: Outgoing call scenario

[0126] refer to Figure 11 As shown, in this scenario, the user interacts with the personalized customer service robot through the phone. The automated robot mainly performs the following steps in the dialogue interaction process:

[0127] Step 402: Receive the phone voice message sent by the user: what data package is there now?

[0128] It should be understood that in step 402, the received voice message carries basic user information, so as to create a user profile.

[0129] Step 404: Match the user portrait established based on the voice message with a calm and personalized customer service robot.

[0130] Step 406: Intention Classification: Telecommunication Field Map.

[0131] Step 408: Dialogue management: no interaction is required, and the intention is clear.

[0132] Step 410: Decision-making content: existing traffic packages: 19 yuan package, 59 yuan package, 99 yuan package.

[0133] Step 412: Personalized reply: He...

example 2

[0135] Example 2: WeChat interaction scenario

[0136] refer to Figure 12 As shown, in this scenario, the user interacts with the personalized customer service robot through WeChat, and the system defaults that the personalized customer service robot has collected historical interaction information in advance to build various models and knowledge bases; The following steps are mainly performed in the process:

[0137] Step 502: Receive the WeChat voice message sent by the user: which one sends the voice call?

[0138] It should be understood that in step 502, the received voice message carries basic user information, so as to facilitate the establishment of a user profile.

[0139] Step 504: Match the user portrait created based on the voice message with a cute personalized customer service robot.

[0140] Step 506: Intent Classification: Telecommunications Field Map.

[0141] Step 508: Dialogue management: the restoration needs to be omitted, and the restored entity is a...

example 3

[0145] Example 3: Direct Human-Computer Interaction Scenario

[0146] refer to Figure 13 As shown, in this scenario, the user directly interacts with the personalized customer service robot, and the system defaults that the personalized customer service robot has collected historical interaction information in advance to build various models and knowledge bases; correspondingly, the personalized robot Mainly perform the following steps:

[0147] Step 602: Receive a text message sent by the user: how old are you?

[0148] It should be understood that in step 602, the received voice message carries basic user information, so as to facilitate the establishment of a user profile.

[0149] Step 604: The user portrait established based on the text message is matched with a cute personalized customer service robot.

[0150] Step 606: Intent Classification: Chat FAQ.

[0151] Step 608: Dialogue management: clear intent.

[0152] Step 610: Decision-making content: I am 5 years ol...

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 discloses an intelligent man-machine conversation interaction method and system and electronic equipment, and the main content comprises the steps: determining a personalized conversation style matched with a user, accurately predicting intention information expressed by a user message based on a machine learning algorithm, and determining a conversation mode based on the intention information and a historical conversation record. And determining personalized reply content according to the determined conversation style, intention information and conversation mode, and returning the personalized reply content to the user side. Furthermore, the reply content can be accurately matched according to the prediction intention, the reply content can be enriched by adopting a personalized conversation style or even adding emotional colors, and one or more rounds of conversation interaction can be executed under the determined conversation mode. Therefore, the flexibility and richness of conversation reply are improved, and the use viscosity of the user is increased.

Description

technical field [0001] This specification relates to the field of computer technology, and in particular to an interactive method, system and electronic equipment for intelligent human-computer dialogue. Background technique [0002] In the field of network operation and customer service, improving enterprise operating efficiency, reducing costs, and improving customer satisfaction are the key points that must be captured in the current technological development environment. Among them, intelligent customer service has gradually become the main carrier for enterprises to provide services to external users and internal digital transformation. [0003] At present, most of the customer service services are not humane enough, and the replies are relatively rigid; and lack of good context understanding ability, semantic recognition is not accurate, resulting in large deviations in reply content, affecting user experience. [0004] With the continuous advancement of technology, u...

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): G06F16/33G06F16/332G06F16/35
CPCG06F16/3329G06F16/3344G06F16/35
Inventor 曹东岩周祥生屠要峰郭斌
Owner ZTE 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

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