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

Semantic information acquisition system and method based on posture control

A semantic information and collection system technology, applied in the field of legal consulting services, can solve the problem that legal service robots cannot collect semantic information, achieve high recognition accuracy, reduce task load, and improve accuracy

Active Publication Date: 2020-06-12
重庆大牛认知科技有限公司
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention intends to provide a semantic information collection system and method based on posture control to solve the problem that legal service robots cannot collect accurate semantic information

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
  • Semantic information acquisition system and method based on posture control
  • Semantic information acquisition system and method based on posture control
  • Semantic information acquisition system and method based on posture control

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Semantic information collection system based on posture control, such as figure 1 As shown, it includes an image acquisition module, a sound acquisition module, a server, and an output module. The server includes a speech recognition module, a body language analysis module, a legal database, and a processing module. The image acquisition module uses an OV7670 camera, the sound acquisition module uses a microphone, and the server It adopts STM32F103C8T6 single-chip microcomputer, and the output module adopts LP140QH1SPA2 ThinkPad New touch LCD screen.

[0058] The image acquisition module and the sound acquisition module are respectively used to obtain the user's video data and sound information in real time;

[0059] The speech recognition module includes a speech feature extraction sub-module, a corpus database and a result generation sub-module. The speech feature extraction sub-module is used to preprocess the sound information by filtering and framing; and process the sou...

Embodiment 2

[0082] Compared with the first embodiment, the only difference is that the target detection sub-module is also used to extract the user's head region in the image according to the contour features to generate second window information, where the second window information also includes the user's facial features ;

[0083] The body language judgment sub-module is also used to take the facial features as the reference object and judge the relative position information of the reference object in two adjacent frames of images. If the relative position information is a vertical change, it is judged as positive semantic information, otherwise, if the relative position is The information changes horizontally and is judged as negative semantic information.

[0084] Semantic information collection method based on posture control. The above system is based on this method and includes the following steps:

[0085] S1. Obtain the user's video data and sound information in real time through the ...

Embodiment 3

[0096] Compared with the second embodiment, the only difference is that it also includes a self-correction step. After the text information is obtained through the result generation sub-module, the feature vectors that appear continuously in the text information are extracted according to preset conditions. If the length and direction of the other feature vectors are different, the video data of the node where the feature vector occurs is extracted and processed to obtain body language information; if the body language information does not match the text information, a prompt box will pop up to inform the user.

[0097] Take a two-dimensional space as an example. Since the feature vector is a vector, it is a quantity that has both magnitude and direction. Combined with the actual situation, when the user is making a voice call, the entire sentence usually includes repeated words. The size and direction of the feature vector of the repeated speech are the same. Assuming that there ...

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 relates to the field of legal consultation service, in particular to a semantic information acquisition system and method based on posture control, the system comprises an image acquisition module, a sound acquisition module, a server and an output module, and the server comprises a voice recognition module, a body language analysis module, a legal database and a processing module; the image acquisition module and the sound acquisition module are respectively used for acquiring video data and sound information of a user in real time; the voice recognition module is used for receiving and processing the voice information and generating corresponding text information; the body language analysis module is used for receiving and processing the video data and generating image data; feature information in the image data is extracted, and body language information is generated; the legal database is used for storing a plurality of legal information in advance; and the processingmodule is used for receiving and processing the body language information and the text information. By adopting the scheme, the problem that a legal service robot cannot acquire accurate semantic information can be solved.

Description

Technical field [0001] The invention relates to the field of legal consulting services, in particular to a semantic information collection system and method based on posture control. Background technique [0002] At present, Chinese society is in a stage of industrial transformation, and people's demand for legal services is also increasing. Legal workers are struggling to deal with various legal consultations every day, so legal service robots came into being. Relying on the Internet, big data and cloud computing technology, the legal service robot can effectively integrate the rule of law propaganda, legal aid, lawyers, notarization, judicial appraisal, people's mediation, community corrections and other resources to provide the general public with a comprehensive, all-weather, uninterrupted law Publicity, legal consultation, service guidance service. [0003] For example, the Chinese Patent Publication No. CN109108989A discloses a semantically recognized legal service robot, wh...

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): G06F16/9032G06F16/9035G06K9/00G06Q50/18G10L15/26G10L15/30
CPCG06F16/90332G06F16/9035G06Q50/18G10L15/30G06V40/20
Inventor 吴怡
Owner 重庆大牛认知科技有限公司
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