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

A visual chat robot session generation method

A chat robot and visual technology, applied in instruments, biological neural network models, special data processing applications, etc., can solve problems such as low educational efficiency and lack of meaning in picture books, and achieve the effect of effective reading

Active Publication Date: 2019-03-01
JIANGXI NORMAL UNIV
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of reading, there is no inspiration, no questioning, no advice, and no guidance. Therefore, it is easy to cause problems such as lack of meaning in picture book reading and low educational efficiency.
In the field of visual dialogue robot research at home and abroad, there is no published work with picture books as the research object.

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
  • A visual chat robot session generation method
  • A visual chat robot session generation method
  • A visual chat robot session generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0041] The invention proposes a conversation generation method of a visual chatting robot, which is mainly applied to conversation generation of a reading robot. The inventor found that the pictures and words in the picture book content are complementary and interdependent. When the robot and the child interact with the picture book reading, the comprehensive understanding of the two modal data is the basis and premise for continuous and reasonable visual dialogue. .

[0042] figure 1 It is a schematic diagram of an implementation scheme of a visual chat robot session generation method according to an embodiment of the present invention, figure 2 It is a flow chart of a method for generating a conversation of a visual ...

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 visual chat robot session generation method. The method comprises the following steps: S1, extracting hierarchical global context information of reading object contents; andS2, acquiring session history information, and generating a continuous multi-round visual session by combining the global context information of the content of the reading object. The visual chattingrobot can simulate teachers, generate guidance questions, guide children to think and observe picture book contents in the reading process, effective reading is achieved, the problem about the picturebook contents proposed by the children can also be positively responded, and therefore good interactive dialogues can be conducted on the picture book contents and the children.

Description

technical field [0001] The invention relates to the cross technical field of computer vision and natural language processing, in particular to a method for generating conversations of a visual chat robot. Background technique [0002] Chatbot is a very popular artificial intelligence research and development and product direction today. Applications based on chatbot systems emerge in endlessly, such as Apple Siri, Microsoft Cortana and Xiaoice. However, no matter whether it is oriented to the open field or the limited field, the data resources and factual basis used by the current mainstream chatbots are all based on a single natural language mode. If the chat robot has visual computing capabilities, then the chat robot can not only complete the natural language dialogue, but also the content of the dialogue can be carried out around the relevant visual image content, and use it as a topic for multiple rounds of continuous interaction with the user. We refer to such robots...

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): G06F16/332G09B7/02G06N3/04
CPCG09B7/02G06N3/044G06N3/045
Inventor 江爱文
Owner JIANGXI NORMAL UNIV
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