Check patentability & draft patents in minutes with Patsnap Eureka AI!

Method and device for man-machine conversations

A technology of man-machine dialogue and dialogue robot, which is applied in the computer field, can solve problems such as small dialogue sets, achieve a balance between efficiency and effect, improve efficiency, and ensure accuracy

Active Publication Date: 2018-07-24
HUAWEI TECH CO LTD
View PDF4 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current dialogue collection is usually only a very small and sparse collection. No matter how intelligent the matching model we define, it cannot solve the problem of "answering the wrong question".

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
  • Method and device for man-machine conversations
  • Method and device for man-machine conversations
  • Method and device for man-machine conversations

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0099] The technical solution in this application will be described below with reference to the accompanying drawings.

[0100] With the development of deep learning, the academic community has proposed a "sequence-to-sequence" learning model based on deep neural network architecture. The natural language dialogue technology based on deep neural network is used to train a natural language dialogue system on large-scale dialogue data. The system accepts the user's input sequence, and then outputs a sequence of responses word by word through the calculation of a multi-layer neural network.

[0101] figure 1 is a schematic diagram of the architecture of a generative dialogue model. Such as figure 1 As shown, the architecture of the generative dialogue model includes an encoder (Encoder) and a decoder (Decoder). The Encoder-Decoder framework can be regarded as a model in the field of text processing, which can be understood as a general processing model in which one sentence g...

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 application provides a method and device for man-machine conversations which can generate accurate answers in a self-adaptive manner according to conversation content. The method is applied to thedevice for man-machine conversations. The device is pre-equipped with multiple conversation robots. Each conversation robot is used for carrying out man-machine conversations according to at least one topic. The method comprises the following steps: acquiring text inputted by a user; determining at least one topic related to the text, determining a target conversation robot from the multiple conversation robots according to the at least one topic related to the text and a pre-defined mapping relationship between each conversation robot and each topic, wherein a target topic corresponding to atarget conversation robot is a part of or the whole of at least one topic related to the text; and distributing the text to the target robot and acquiring a response to the text from the target conversation robot, wherein the response is the one generated by the target conversation robot according to at least one semantic understanding of the text.

Description

technical field [0001] The present application relates to the computer field, and more specifically, relates to a method and device for man-machine dialogue. Background technique [0002] With the rapid development of mobile Internet and smart terminals, the application of man-machine dialogue is becoming more and more extensive. At present, the widely used dialogue robots are mainly search-type dialogue robots, that is, they rely on the construction of a very large dialogue database and intelligent matching technology. When the content of the appropriate answer is found, the situation of "answering the wrong question" appears. However, the current dialogue collection is usually only a very small and sparse collection. No matter how intelligent the matching model we define, it cannot solve the problem of "answering the wrong question". [0003] At present, a generative dialogue robot is known, which can understand the user's question through deep learning, and then generat...

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): G06F17/30G06F17/27
CPCG06F16/3329G06F40/30G06F16/353G06F40/35G06N5/043G06N3/084G06N3/044G06N3/045G10L13/08G10L15/22G10L2015/225G10L2015/228G06F16/3344H04L51/02
Inventor 尚利峰吕正东李航
Owner HUAWEI TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More