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

Dialogue automatic reply system based on deep learning and reinforcement learning

A technology of reinforcement learning and dialogue system, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as inability to realize intelligent chat

Active Publication Date: 2017-02-22
EMOTIBOT TECH LTD
View PDF7 Cites 101 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Therefore, the defect in the existing technology is: the existing man-machine dialogue system implementation method cannot give accurate and in line with the user's personality answer according to the user's intention or context, and cannot realize intelligent chat

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
  • Dialogue automatic reply system based on deep learning and reinforcement learning
  • Dialogue automatic reply system based on deep learning and reinforcement learning
  • Dialogue automatic reply system based on deep learning and reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] figure 1 Shows a schematic diagram of an automatic reply dialogue system 10 based on deep learning and reinforcement learning provided by the first embodiment of the present invention, such as figure 1 As shown, the first embodiment provides an automatic reply dialogue system 10 based on deep learning and reinforcement learning, including:

[0045] The user interaction module 101 is used to receive question information input by the user in the dialogue system interface;

[0046] The session management module 102 is used to record the user's activity state, the activity state includes historical dialogue information, user position change information, and user mood change information;

[0047] The user analysis module 103 is used to analyze the user's registration information and activity status, make a portrait for the user, and obtain user portrait information. The user portrait information is used to describe the personality characteristics of the user, and the user's registra...

Embodiment 2

[0099] The present invention is an automatic reply dialogue system 10 based on deep learning and reinforcement learning, combined with the user’s dialogue content on the system interface, specifically introduces the system process of the present invention;

[0100] User: Hello!

[0101] System: Good afternoon, how can I help you?

[0102] User: My computer does not display after booting.

[0103] System: Sorry for you. Are you using Windows operating system?

[0104] User: No, Linux system.

[0105] System: Is there any error message?

[0106] The user conducts a man-machine dialogue in the system interface, and enters the text information of the user dialogue, such as "hello". The system first converts the "hello" code into a word vector to facilitate the computer to calculate, and then for simple hello information, the system According to the preset mode, the corresponding answer will be given, such as "Good afternoon, how can I help you?" or "Good afternoon, what can I do?", and then...

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 dialogue automatic reply system based on deep learning and reinforcement learning. The dialogue automatic reply system comprises a user interaction module which receives question information inputted by a user in a dialogue system interface; a session management module which records the active state of the user, wherein the active state includes historical dialogue information, user position transformation information and user emotion change information; a user analysis module which analyzes registration information and the active state of the user and portraits for the user so as to obtain user portrait information; a dialogue module which generates reply information through a language module according to the question information of the user with combination of the portrait of the user; and a model learning module which updates the language model through the reinforcement learning technology according to the reply information generated by the language model. According to the dialogue automatic reply system based on deep learning and reinforcement learning, the reply of the dialogue meeting the personality of the user can be given according to the dialogue text inputted by the user with combination of context information, the personality characteristics of the user and the intentions in the dialogue.

Description

Technical field [0001] The invention relates to the field of artificial intelligence, in particular to the field of intelligent human-machine dialogue. Background technique [0002] With the continuous evolution of human society informatization and the rising cost of human services, people increasingly hope to communicate with computers through natural language. Intelligent dialogue robot systems have become products born under this historical background, especially those that can understand users. The dialogue robot system that can memorize the user's historical dialogue, can take care of the user's emotions, and can provide users with personalized services is becoming the direction and focus of research and development of major companies and academic research institutions. [0003] The first implementation in the prior art requires constructing various answers to various questions and accurately designing the selection logic, which requires a huge investment of manpower. If you ...

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): G10L15/22
CPCG10L15/22G10L2015/227G10L2015/228
Inventor 简仁贤吴文杰
Owner EMOTIBOT TECH LTD
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