Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020087848 - REAL-TIME BEHAVIOR IDENTIFICATION SYSTEM BASED ON LORA AND CAPSULE, AND OPERATING METHOD THEREFOR

Publication Number WO/2020/087848
Publication Date 07.05.2020
International Application No. PCT/CN2019/079387
International Filing Date 23.03.2019
IPC
G06K 9/62 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6267
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6267Classification techniques
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • 山东大学 SHAN DONG UNIVERSITY [CN]/[CN]
Inventors
  • 许宏吉 XU, Hongji
  • 石磊鑫 SHI, Leixin
  • 陈敏 CHEN, Min
  • 张贝贝 ZHANG, Beibei
  • 李梦荷 LI, Menghe
Agents
  • 济南金迪知识产权代理有限公司 JINAN JINDI INTELLECTUAL PROPERTY AGENCY CO., LTD
Priority Data
201811294526.X01.11.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) REAL-TIME BEHAVIOR IDENTIFICATION SYSTEM BASED ON LORA AND CAPSULE, AND OPERATING METHOD THEREFOR
(FR) SYSTÈME D'IDENTIFICATION DE COMPORTEMENT EN TEMPS RÉEL BASÉ SUR LORA ET CAPSULE, ET PROCÉDÉ DE FONCTIONNEMENT ASSOCIÉ
(ZH) 一种基于Lora和Capsule的实时行为识别系统及其工作方法
Abstract
(EN)
The invention relates to a real-time behavior identification system based on Lora and Capsule, and an operating method therefor. The system comprises a behavior information physical layer, a behavior information access layer, a behavior information platform layer, and a behavior information application layer. According to the present invention, the transmission of the behavior information access layer is implemented by a Lora node and a Lora base station, thereby realizing a remote-distance and low-power-consumption behavior information transmission; behavior information uncertainty is subject to inconsistency and incompleteness processing so as to improve the credibility of behavior information; and Capsule is used to automatically obtain useful features and the spatial relationship between features so as to perform behavior identification, thereby greatly improving the identification precision.
(FR)
L'invention concerne un système d'identification de comportement en temps réel basé sur Lora et Capsule, et son procédé de fonctionnement. Le système comprend une couche physique d'informations de comportement, une couche d'accès aux informations de comportement, une couche de plateforme d'informations de comportement et une couche d'application d'informations de comportement. Selon la présente invention, la transmission de la couche d'accès aux informations de comportement est mise en œuvre par un nœud Lora et une station de base Lora, réalisant ainsi une transmission d'informations de comportement à distance et à faible consommation d'énergie; l'incertitude d'informations de comportement est soumise à un traitement d'incohérence et d'inachèvement de façon à améliorer la crédibilité des informations de comportement; et Capsule est utilisé pour obtenir automatiquement des caractéristiques utiles et la relation spatiale entre des caractéristiques de façon à effectuer une identification de comportement, améliorant ainsi considérablement la précision d'identification.
(ZH)
本发明涉及一种基于Lora和Capsule的实时行为识别系统及其工作方法,该系统包括行为信息物理层、行为信息接入层、行为信息平台层、行为信息应用层。本发明将行为信息接入层的传输采用Lora节点、Lora基站,实现远距离、低功耗的行为信息传输;对行为信息不确定性进行了不一致和不完备性方面的处理,提高行为信息的可信度;采用Capsule自动获取有用特征以及特征之间的空间关系来进行行为识别,在精度方面有了很大的提升。
Also published as
Latest bibliographic data on file with the International Bureau