Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022161954 - ENABLING TRAINING OF AN ML MODEL FOR MONITORING A PERSON

Publication Number WO/2022/161954
Publication Date 04.08.2022
International Application No. PCT/EP2022/051645
International Filing Date 25.01.2022
IPC
G08B 21/04 2006.1
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
21Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
02Alarms for ensuring the safety of persons
04responsive to non-activity, e.g. of elderly persons
G08B 29/24 2006.1
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
29Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
18Prevention or correction of operating errors
20Calibration, including self-calibrating arrangements
24Self-calibration, e.g. compensating for environmental drift or ageing of components
G06V 10/70 2022.1
G08B 13/196 2006.1
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
13Burglar, theft or intruder alarms
18Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
189using passive radiation detection systems
194using image scanning and comparing systems
196using television cameras
G08B 29/18 2006.1
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
29Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
18Prevention or correction of operating errors
G06N 20/00 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
CPC
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06V 40/20
G08B 13/19686
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
13Burglar, theft or intruder alarms
18Actuation by interference with heat, light or radiation of shorter wavelength; Actuation by intruding sources of heat, light or radiation of shorter wavelength
189using passive radiation detection systems
194using image scanning and comparing systems
196using television cameras
19678User interface
19686Interfaces masking personal details for privacy, e.g. blurring faces, vehicle license plates
G08B 21/04
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
21Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
02Alarms for ensuring the safety of persons
04responsive to non-activity, e.g. of elderly persons
G08B 21/0407
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
21Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
02Alarms for ensuring the safety of persons
04responsive to non-activity, e.g. of elderly persons
0407based on behaviour analysis
G08B 21/043
GPHYSICS
08SIGNALLING
BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
21Alarms responsive to a single specified undesired or abnormal operating condition and not elsewhere provided for
02Alarms for ensuring the safety of persons
04responsive to non-activity, e.g. of elderly persons
0407based on behaviour analysis
043detecting an emergency event, e.g. a fall
Applicants
  • ASSA ABLOY AB [SE]/[SE]
Inventors
  • PERNYER, Kenneth
  • CRASTO, Nieves
Agents
  • KRANSELL & WENNBORG KB
Priority Data
2150084-826.01.2021SE
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) ENABLING TRAINING OF AN ML MODEL FOR MONITORING A PERSON
(FR) ACTIVATION DE L'ENTRAÎNEMENT D'UN MODÈLE ML POUR LA SURVEILLANCE D'UNE PERSONNE
Abstract
(EN) It is provided a method for enabling training of a machine learning, ML, model, for monitoring a person based on a data feed capable of depicting a person. The method is performed by a training data provider (i). The method comprises: obtaining (40) a data feed capable of depicting the person; selecting (42) a level of anonymisation, from a plurality of levels of anonymisation; anonymising (44) the data feed according to the selected level of anonymisation, resulting in a processed data feed; and transmitting (47) the processed data feed as training data for training a central ML model in a central node. Different levels of anonymisation are available and a change in level can be requested by the central node.
(FR) L'invention concerne un procédé d'activation de l'entraînement d'un modèle d'apprentissage automatique (ML) pour la surveillance d'une personne sur la base d'un flux de données susceptible de représenter une personne. Le procédé est mis en œuvre par un fournisseur de données d'entraînement (1). Le procédé comprend : l'obtention (40) d'un flux de données capable de représenter la personne ; la sélection (42) d'un niveau d'anonymisation, à partir d'une pluralité de niveaux d'anonymisation ; l'anonymisation (44) du flux de données selon le niveau d'anonymisation sélectionné, conduisant à un flux de données traité ; et la transmission (47) du flux de données traité en tant que données d'entraînement destinées à entraîner un modèle ML central dans un nœud central. Différents niveaux d'anonymisation sont disponibles et un changement de niveau peut être demandé par le nœud central.
Related patent documents
Latest bibliographic data on file with the International Bureau