Deep learning-based dialogue method, device and equipment

A technology of deep learning and dialogue equipment, applied in the field of artificial intelligence, can solve problems such as ineffective processing and utilization of dialogue history information, reply sentences that cannot meet user needs, etc., and achieve the effect of improving dialogue quality, effective processing and utilization

Active Publication Date: 2018-04-06
HUAWEI TECH CO LTD
View PDF6 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the existing technology cannot effectively process and utilize dialogue history information, resulting in the reply sentence output by the dialogue system may not meet the needs of users, the embodiment of the present invention provides a dialogue method, device and equipment based on deep learning

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
  • Deep learning-based dialogue method, device and equipment
  • Deep learning-based dialogue method, device and equipment
  • Deep learning-based dialogue method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0136] Example 1, such as Figure 4G Shown:

[0137] User: How is the weather in Beijing today?

[0138] DS: partly cloudy

[0139] User: What about tomorrow?

[0140] DS: light rain

[0141] User: What about Shanghai?

[0142] DS: Today or tomorrow?

[0143] In the above dialogue, when the dialogue system generates the reply "today or tomorrow?", assuming that the system has just generated the words "today" and "still" in sequence, when generating the next word, the dialogue system uses The state vector of the decoded neural network (after the word "or" is generated) and the vector generated in the neural network for encoding are fed into the neural network for attention vector synthesis together with the sentence to be replied ("What about Shanghai?") Network, the attention vector that produces passes through the neural network (such as CNN++) that is used for retrieval, generates the information that can represent the state vector of the neural network for decoding, t...

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 deep learning-based dialogue method, device and equipment, and belongs to the field of artificial intelligence. The method includes the steps of obtaining a to-be-answered statement; encoding the to-be-answered statement to obtain a first vector, wherein the first vector is the representation of the to-be-answered statement; obtaining the dialogue history information corresponding to the to-be-answered statement, wherein the dialogue history information includes at least one round of dialogue statements, and each round of dialogue statements includes two dialogue statements; synthesizing an attention vector by using the first vector and a decoding state vector, wherein the decoding state vector is used for representing the state of a decoder when the most recent word in an answered sentence is output, and the attention vector is used for representing a search intention; enabling each dialogue statement to interact with the attention vector respectively to extract the information related to the search intention in each dialogue statement to obtain multiple result vectors; generating a to-be-decoded vector based on the multiple result vectors; decoding the to-be-decoded vector to obtain a next word in the answered sentence. According to the method, device and equipment, the answered sentence takes a dialogue history as reference.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a dialogue method, device and equipment based on deep learning. Background technique [0002] Natural language dialogue is one of the most challenging problems in artificial intelligence, and now there are many practical dialogue systems, such as Apple Siri. These dialogue systems can have simple dialogues with people and complete some simple tasks, such as asking about the weather and checking stocks. [0003] The dialogue system based on deep learning is the development direction of the current dialogue system. After obtaining the sentence to be replied input by the user, the method for generating the reply sentence includes: encoding the sentence to be replied into a vector; decoding the vector to obtain the reply sentence. [0004] In the process of generating reply sentences, this kind of dialogue system cannot effectively process and utilize the dialogue hist...

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): G06F17/30G06N99/00
CPCG06F16/90332G06N20/00G06F40/216G06F40/35G06F40/56G06N3/084G06N3/044G06N3/045G06F16/00G06N99/00G06F40/30G06F16/2455G06N3/08
Inventor 吕正东何山江强
Owner HUAWEI TECH CO LTD
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