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

LSTM neural network chip and application method therefor

A technology of neural network and deep neural network, which is applied in the field of automatic chatting methods and robots, to achieve the effect of real dialogue, guaranteed accuracy and high economic benefits

Active Publication Date: 2018-08-10
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, traditional chatbots cannot meet the emotional needs of the elderly well

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
  • LSTM neural network chip and application method therefor
  • LSTM neural network chip and application method therefor
  • LSTM neural network chip and application method therefor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0038] It should be noted that, in the drawings or descriptions of the specification, similar or identical parts all use the same figure numbers. Implementations not shown or described in the accompanying drawings are forms known to those of ordinary skill in the art. Additionally, while illustrations of parameters including particular values ​​may be provided herein, it should be understood that the parameters need not be exactly equal to the corresponding values, but rather may approximate the corresponding values ​​within acceptable error margins or design constraints. In addition, the directional terms mentioned in the following embodiments, such as "upper", "lower", "front", "rear", "left", "right", etc., are onl...

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 provides an automatic chatting method based on a deep neural network, and the method comprises the following steps: obtaining the input information of a user, and generating a fixed length vector through a deep neural network coder; respectively outputting scores after the fixed length vector is inputted into a plurality of attention submodules; carrying out the comparison of the scores outputted by the plurality of attention submodules, selecting the attention submodule corresponding to the highest score as the final model, and generating answer information corresponding to theinput information. The invention also provides an automatic chatting robot based on the deep neural network. The method and robot guarantee the accuracy of answer information in a chatting process, and enable the chatting content to accord with the reality.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, in particular to an automatic chatting method and a robot based on a deep neural network. Background technique [0002] In recent years, with the rapid development of artificial intelligence, chatbots have also received extensive attention from academia and industry. [0003] However, traditional chatbots also face many problems, such as the inability to produce specific meanings in dialogue, and the lack of contextual logic, which cannot meet the needs of use. [0004] In particular, our country is rapidly entering an aging society. In the future society, how to provide for the elderly will be a huge social and economic problem. The current elderly care model mostly adopts the way that nursing staff accompany and chat with the elderly, so as to provide companionship and chat services for the elderly and provide emotional comfort for the elderly. Manually chatting with...

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): G06N3/063G06N3/04G06F17/30
CPCG06F16/3329G06F16/90332G06N3/063G06N3/045
Inventor 于涌陈云霁
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
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