EP1705617A2 - Method and device for the remote monitoring of the activity of a person within a room - Google Patents

Abstract

The method involves obtaining monitoring data relative to a preset HF electric signal produced by an electric equipment e.g. lamp, of a building from a hook-on ammeter (115). The ammeter detects the signal produced by the equipment on an electrical distribution network of the building, when a change of electric state of operation occurs in the equipment. An activity indicator detects an estimation of the activity carried on by a person from the monitoring data generated during a preset time period. The data includes information relative to a date of detection of the detected electric signal, identification data of the electric equipment, and data relating to the change of electric state of operation at the origin of the detected electric signal. Independent claims are also included for the following: (1) a data processing device for the remote monitoring of the activity of a person in a building (2) a device for the remote monitoring of the activity of a person in a building.

Description

The invention relates to the field of measuring and remotely monitoring the activity of a person, and more specifically to a method and a device for remotely monitoring the activity of a person in a building.

The systems that have been developed in this area are mostly designed for the follow-up of people considered "fragile", typically elderly people living alone. Their vocation is to detect as soon as possible an abnormal change in the activity of these people so as to trigger, if necessary, the intervention of an emergency service, a doctor or a relative of the person.

Current known systems for remote monitoring of a person in his habitat use a set of sensors appropriately distributed in this habitat. These systems require the installation of numerous dedicated sensors, such as, for example, door or window contact sensors, actimetric mattresses, sensitive floors, laser or infrared light beam presence detectors, and use detectors. in the form of a meter on appliances of everyday life (coffee maker), etc.

These systems are particularly expensive to implement, often require significant work for their implementation or involve the availability of many access points to the power grid. In addition, some detectors used in these systems often lack reliability when there are disturbances in the monitored environment related to the presence of persons other than the person to be followed, the presence of pets, or simply disturbances related to drafts or sunlight temporarily heating a part of the building.

These systems can also cause the person who is followed the unpleasant feeling of being "monitored" because of the visible omnipresence of the detection means, which is often a major obstacle to the establishment of such systems.

The object of the invention is therefore to provide a method and a device for remotely monitoring the activity of a person in a building, which do not have the drawbacks stated for known prior solutions, and in particular make it possible to reliably monitor this activity. activity while being simple and inexpensive to install.

• une étape d'obtention, d'un dispositif de détection apte à détecter sur le réseau de distribution d'électricité du bâtiment au moins un signal électrique prédéfini produit par un équipement électrique du bâtiment lorsqu'un changement d'état électrique de fonctionnement se produit dans ledit équipement électrique, de données de suivi relatives à au moins un signal électrique détecté, les données de suivi comprenant,
  • des informations relatives à une date de détection du signal électrique détecté,
  • des données d'identification de l'équipement électrique ayant produit le signal électrique détecté,
  • des données relatives au changement d'état électrique de fonctionnement à l'origine du signal électrique détecté,
• une étape de détermination, à partir de données de suivi générées au cours d'une période de temps prédéfinie, d'au moins une estimation de l'activité exercée par ladite personne.

For this purpose, the subject of the invention is a method for remotely monitoring the activity of at least one person in a building, the method comprising at least one,

• a step of obtaining, a detection device capable of detecting on the electricity distribution network of the building at least one predefined electrical signal produced by an electrical equipment of the building when a change of electrical operating state occurs in said electrical equipment, tracking data relating to at least one detected electrical signal, the tracking data including,
  • information relating to a detection date of the detected electrical signal,
  • identification data of the electrical equipment having produced the detected electrical signal,
  • data relating to the change of electrical operating state at the origin of the detected electrical signal,
• a step of determining, from monitoring data generated over a predefined period of time, at least one estimate of the activity exerted by said person.

The invention takes advantage of the fact that it is possible to detect a change of electrical state of operation of a device by detecting electrical signals produced on the electricity distribution network. Such a change in electrical operating state occurs especially when a user turns on or off either the device itself or an electrical subassembly of this device. It is therefore possible to detect the use of this device from the electrical signals produced on the electricity distribution network.

In addition, the detection of electrical signals can be performed extremely simply, for example from a simple clamp meter. This detection technique also makes it possible to observe the use of all electrical appliances in the building, from a single electrical detection point. The invention thus makes it possible to avoid the setting up of numerous sensors in a remote monitoring system of the activity of a person.

According to one characteristic of the invention, the activity estimate is determined in the form of at least one activity indicator representative of the probability of performing at least one type of activity by the person to be followed.

A probabilistic type of analysis proves to be appropriate for dealing with information related to the detection of predefined signals produced by electrical equipment. It is also sufficient to detect variations in the behavior of the person to follow.

• associer au moins un équipement électrique à chaque indicateur d'activité,
• déterminer, pour chaque équipement électrique associé à un indicateur d'activité, une valeur de pondération qui est représentative de la probabilité de réalisation du type d'activité dont cet indicateur est représentatif lorsqu'une action provoquant un changement d'état électrique de l'équipement est effectuée par la personne sur l'équipement,
• déterminer un indicateur d'activité à partir des valeurs de pondération déterminées pour les équipements électriques associés à cet indicateur d'activité.

According to one embodiment of the method according to the invention, the method comprises the preliminary steps consisting in:

• associate at least one electrical equipment with each activity indicator,
• determining, for each electrical equipment associated with an activity indicator, a weighting value that is representative of the probability of performing the type of activity for which this indicator is representative when an action causing a change of electrical state of the equipment is performed by the person on the equipment,
• determine an activity indicator from the weighting values determined for the electrical equipment associated with this activity indicator.

The generation of a weighting value for a device according to the type of activity to which it can be associated fits into a context of probabilistic analysis. It makes it possible to make the method of determining the activity indicators independent of the nature of the different devices considered since they are taken into account according to the weighting value which is assigned to them.

• le moment de la journée,
• le nombre total d'équipements électriques associés à cet indicateur d'activité,
• le nombre total d'équipements électriques détectés et associés à cet indicateur d'activité,
• la durée pendant laquelle l'équipement est resté sous tension,
• le nombre de fois que l'équipement a été mis hors ou sous tension,
• la température extérieure,
• la saison,
• le jour de la semaine,
• le degré de confiance dans les données d'identification,
• les habitudes de la personne,
• le nombre d'équipements électriques associés à cet d'activité et mis sous tension peu avant ou peu après l'équipement.

Preferably, the weighting value relating to a given piece of equipment and to a given type of activity is weighted according to at least one criterion taken from the group comprising

• the time of the day,
• the total number of electrical equipment associated with this activity indicator,
• the total number of electrical equipment detected and associated with this activity indicator,
• the duration during which the equipment has remained energized,
• the number of times the equipment has been turned off or on,
• the outside temperature,
• the season,
• the day of the week,
• the degree of confidence in the identification data,
• the habits of the person,
• the number of electrical equipment associated with this activity and energized shortly before or shortly after the equipment.

In this way, the determination of the activity indicators is adapted to both the degree of equipment of the building, the season, the time of day as well as the characteristics of use of the electrical equipment. It is therefore possible to determine the activity indicators in a fine and adapted manner to the person to follow, to his type of habitat, to his way of life. The activity indicators thus obtained are particularly relevant and representative of the activity of the person.

According to an alternative embodiment, the method according to the invention further comprises a step of determining at least one relative indicator of activity, this relative indicator of activity being representative of the normal character of the activity of the person in said building over a period of time. This determination is made from at least one activity indicator determined for the same period of time and by comparison with reference data representative of the activity of the person over the same period of time.

This relative activity indicator is a global measure of the person's activity. It facilitates the tracking of a large number of people and makes possible an automated monitoring based on the value of this global measure. This makes it possible, for example, to trigger an alert conditional on the value of this relative indicator of activity.

According to one characteristic, a change of electrical state is produced as a result of an action performed by the person on the electrical equipment, this action being able to switch on or off the electrical equipment or a sub-unit. -electrical set of electrical equipment. In this case, the tracking data includes information on the nature of the action (power on / off) causing the electrical state change.

This information, used in combination with the information on the moment of the detection, makes it possible to easily determine information relating to the total duration of use of this equipment (by difference between the date of power off and the date of entry under voltage) or the operating hours of this equipment.

• des moyens pour obtenir, d'un dispositif de détection apte à détecter sur le réseau de distribution d'électricité du bâtiment au moins un signal électrique prédéfini produit par un équipement électrique du bâtiment lorsqu'un changement d'état électrique de fonctionnement se produit dans ledit équipement électrique, des données de suivi relatives à au moins un signal électrique détecté, les données de suivi comprenant,
• des informations relatives à une date de détection du signal électrique détecté,
• des données d'identification de l'équipement électrique ayant produit le signal électrique détecté,
• des données relatives au changement d'état électrique de fonctionnement à l'origine du signal électrique détecté,
• des moyens de traitement de données permettant de déterminer, à partir de données de suivi générées au cours d'une période de temps prédéfinie, au moins une estimation de l'activité exercée par la personne.

The invention also relates to a data processing device for remotely monitoring the activity of at least one person in a building, this device comprising,

• means for obtaining, from a detection device capable of detecting on the electricity distribution network of the building at least one predefined electrical signal produced by an electrical equipment of the building when a change of state electrical operation occurs in said electrical equipment, tracking data relating to at least one detected electrical signal, the tracking data including,
• information relating to a detection date of the detected electrical signal,
• identification data of the electrical equipment having produced the detected electrical signal,
• data relating to the change of electrical operating state at the origin of the detected electrical signal,
• data processing means for determining, from monitoring data generated over a predefined period of time, at least one estimate of the activity exerted by the person.

This data processing device is preferably implemented in the form of a computer server.

• un module de détection pour détecter, sur le réseau de distribution d'électricité du bâtiment, des signaux électriques prédéfinis, chacun desquels étant produit par un équipement électrique du bâtiment lorsqu'un changement d'état électrique de fonctionnement se produit dans ledit équipement électrique;
• des moyens d'analyse pour générer, par analyse d'au moins un des signaux électriques détectés, des données de suivi incluant
• des informations relatives à une date de détection du signal électrique détecté,
• des données d'identification de l'équipement électrique ayant produit le signal électrique détecté,
• des données relatives au changement d'état électrique de fonctionnement à l'origine du signal électrique détecté,
• des moyens de traitement de données permettant de déterminer, à partir de données de suivi générées au cours d'une période de temps prédéfinie, au moins une estimation de l'activité exercée par la personne.

The invention also relates to a device for remotely monitoring the activity of at least one person in a building comprising,

• a detection module for detecting, on the building electricity distribution network, predefined electrical signals, each of which is generated by an electrical equipment of the building when a change of electrical operating state occurs in said electrical equipment;
• analysis means for generating, by analysis of at least one of the detected electrical signals, tracking data including
• information relating to a detection date of the detected electrical signal,
• identification data of the electrical equipment having produced the detected electrical signal,
• data relating to the change of electrical operating state at the origin of the detected electrical signal,
• data processing means for determining, from monitoring data generated over a predefined period of time, at least one estimate of the activity exerted by the person.

The advantages stated briefly above for the method according to the invention can be transposed to this data processing device and to this monitoring device.

• la figure 1 représente schématiquement un mode de réalisation d'un système adapté pour la mise en oeuvre du procédé selon l'invention;
• les figures 2a et 2b représentent des exemples de signaux électriques à partir desquels un actionnement d'un appareil électrique est détectable;
• la figure 3 est un organigramme illustrant les étapes d'un procédé de suivi selon l'invention ; et
• les figures 4a à 4c illustrent un mode de calcul et d'exploitation d'indicateurs d'activités selon un procédé de suivi selon l'invention.

Other objects, features and advantages of the invention will become apparent light of the description which follows, given only by way of non-limiting example, and made with reference to the accompanying drawings in which:

• FIG. 1 diagrammatically represents an embodiment of a system adapted for implementing the method according to the invention;
• Figures 2a and 2b show examples of electrical signals from which operation of an electrical apparatus is detectable;
• Fig. 3 is a flowchart illustrating the steps of a tracking method according to the invention; and
• FIGS. 4a to 4c illustrate a method of calculating and using activity indicators according to a monitoring method according to the invention.

• un dispositif 110 de détection connecté au réseau 105 de distribution d'électricité du bâtiment 100 de la personne 112 dont l'activité doit être surveillée ;
• un serveur de traitement 150 adapté à communiquer via le réseau communication 50 avec le dispositif de détection 110;
• un terminal d'exploitation 180 adapté à communiquer via le réseau de communication 50 avec le serveur de traitement 150.

With reference to FIG. 1 , an embodiment of a system adapted for implementing the method according to the invention will be described. As shown in FIG. 1, such a system comprises a communication network 50 to which are connected:

• a detection device 110 connected to the electricity distribution network 105 of the building 100 of the person 112 whose activity must be monitored;
• a processing server 150 adapted to communicate via the communication network 50 with the detection device 110;
• an operating terminal 180 adapted to communicate via the communication network 50 with the processing server 150.

In the example chosen and shown, the detection device, the processing server and the operating terminal are separate entities, however, according to an alternative embodiment, the processing server and the operating terminal can be collected geographically and integrated into a single computing device integrating the functions of the processing server and the operating terminal. Similarly, according to another embodiment, the detection device and the processing server can be merged into a single computer device integrating the functions provided by the processing server and the detection device.

In order to be able to communicate via the communication network 50, the detection device 110, the processing server 150 and the operating terminal 180 respectively comprise communication means 117, 152 and 181 adapted to the nature of the communication network 50, for example conventional PSTN modems in the case of a switched telephone network (PSTN). The network 50 can also be an Internet-type network, a private network, a telephone network mobile, a WIFI-type wireless network, etc. The method of transmitting information between the different entities of the system is also adapted to the nature of the network. In the case of a mobile telephony network, this transmission is effected for example by means of SMS short messages (short message service).

The building 100 includes a set of electrical equipment connected to the electricity distribution network 105. As shown in FIG. 1, this equipment is for example a lamp 101, a coffee maker 102, or any other electrical equipment 103.

The detection device 110 that equips the building according to the invention includes a module 115 for detecting and acquiring electrical signals generated on the electricity distribution network 105. Each of the electrical signals detected is produced by one of the electrical equipment of the building when the equipment in question changes its electrical operating state. Most often the change of operating state is due to the power on or off of the electrical equipment considered.

Indeed, it has been found that the switching on or off of an electrical equipment causes on the electrical network to which the equipment is connected, a high frequency electrical signal (HF) which is representative of the electrical equipment and the the nature of the action that triggered the signal. This RF signal is also independent of the power consumption of the electrical equipment in question.

Examples of such electrical signals are shown as a function of time in Figures 2a and 2b . These figures respectively represent the electrical signal obtained during power-up of a coffee maker and that obtained during the power off of the coffee maker.

These signals have, when comparing their high frequency components, enough differences between them for an identification of the device and the action that triggered the signal is possible from a recording of these signals. Such signals therefore constitute an electromagnetic signature of the device and the action that triggered the signal. Therefore, the electrical equipment that is powered on or off, is identifiable by analyzing the electrical signal generated on the network at power on / off.

Simple electrical appliances, such as a light bulb, often have only two signatures, a power-on signature and a power off signature.

A more complex electrical apparatus such as a washing machine typically operates in a cyclic process. Such an apparatus can therefore present during the same cycle of use (prewash, wash, rinse, drain, spin, etc.) a different electromagnetic signature depending on the phases of this cycle, in particular because of the various electrical elements present and active in the device at each phase.

In the case of an electrical appliance of the freezer or refrigerator type, it is not detected that the appliance itself is switched on or off, but that of the interior lighting system which is activated by opening or closing the appliance. door of the device. In this case indeed, the interesting action for the activity measurement is the opening or closing of the door, respectively the power on or off of the interior lighting system. The electrical signals caused by the starting or stopping of the cold control system of such devices are not relevant for the analysis of activity as envisaged in the context of the invention.

According to an exemplary embodiment, the detection module 115 is made from an ammeter clamp for measuring RF electrical signals, coupled with an electronic circuit for digitizing and recording the high frequency electrical signal measured via the ammeter clamp. .

An exemplary embodiment of such a detection module is described in the patent document FR 2 806 806 . This module, made in the form of a housing, requires a simple electrical connection to the power supply network, for example at the electrical meter of the building. It is therefore particularly discreet and does not give an impression of intrusion to the person who will be followed. Finally, it is no longer necessary to set up a plurality of sensors since, through this single housing, it is possible to detect the operation, and therefore the use, of all the electrical equipment of the building.

The detection module 115 is also adapted to record, for each detected electrical signal, date and time information relating to the time of detection.

• la date et l'heure de la détection du signal électrique,
• des données d'identification de l'équipement électrique ayant produit le signal électrique,
• des données de caractérisation du changement d'état électrique de fonctionnement qui a déclenché le signal électrique.

Returning to Figure 1, the detection device 110 further comprises a data processing module 116, designed for example around a microprocessor. The means 116 for data processing are adapted to analyzing the HF electrical signal and generating, following the detection and acquisition of the aforementioned high frequency signal, tracking data comprising:

• the date and time of the detection of the electrical signal,
• identification data of the electrical equipment having produced the electrical signal,
• characterization data of the electrical operating state change that triggered the electrical signal.

According to an alternative embodiment, the monitoring data also comprise a confidence score, that is to say a numerical value indicating the degree of confidence in the identification of the equipment obtained through the identification data.

The date and time of the detection of the electrical signal are for example obtained from a clock signal present in the detection device, the recording of the date and time being triggered by the detection of the electrical signal.

The characterization data make it possible to characterize the change of electrical state by an indication relating to the action on the electrical equipment which is at the origin of the electrical signal. This action can be the power on or off of the electrical equipment or the power on or off of an electrical subassembly of the electrical equipment. In this case, the characterization data indicates whether a power up or a power off has been identified by analysis of said electrical signal.

The identification data of the electrical apparatus and the identification of the action that triggered the electrical signal are obtained by comparison between the detected high frequency signal, previously digitized and filtered by means of a high-pass filter, with a corresponding reference signal, which has been pre-recorded during a learning phase of the detection device 110.

A reference signal is thus pre-recorded during the learning phase for each action causing an electrical signal and each of the electrical equipment considered. In particular, for each equipment, are prerecorded at least two reference signals respectively corresponding to the power on and off of the equipment or an electrical subassembly of this equipment.

According to an exemplary embodiment, the comparison of the detected signal with the pre-recorded reference signals is performed by means of an algorithm of signal correlation. In this way, by seeking the maximum correlation, one can determine firstly the electrical equipment concerned by the detection and secondly the action (power on or off) that triggered the signal.

The aforementioned confidence score that can be included in the tracking data, for example is defined from the correlation level obtained between the detected electrical signal and the reference signal for which the correlation is the best. Indeed, a low correlation level, corresponding to a low correlation, indicates that there is a doubt about the identification of the electrical device.

As mentioned above, the detection device 110 comprises communication means 117 which are used to transmit to the processing server 150 the tracking data obtained following a detection. The latter then analyzes the data received.

Deporting the analysis of the monitoring data on the processing server 150 allows on the one hand to lighten the detection device 110, set up in the person to follow, and on the other hand, allows to implement implement more powerful data processing means, deported in the processing server 150.

In addition, the processing server may, depending on its processing capacity, be in communication via the communication network 50 with a plurality of detection devices 110 each placed in a different person.

As a variant, the generation of part of the tracking data is performed not in the detection device but in the processing server itself. In this case, the detection device transmits to the processing server at each detection only the digitized electrical signal and the date and time of detection. The identification data of the equipment as well as the data characterizing the use that is made of it by a type of action, can then be determined by the processing server if it has reference signals from each device and from each device. action to detect.

The processing server 150 comprises, in addition to the communication means 152, data processing means 151, typically one or more calculation processors, and data recording means 153, typically one or more computer hard drives.

The processing server 150 is in functional communication with the operating terminal 180. The operating terminal 180 comprises, in addition to the communication means 181, 183 data processing means, typically one or more computing processors and data display means 182, typically a display screen.

• la première phase ou phase de détection et d'acquisition de données de suivi, correspondant au étapes S210 et S220, et
• la deuxième phase ou phase d'analyse et d'exploitation des données de suivi, correspondant aux étapes S230 à S260.

With reference to FIG. 3 , a method according to the invention for monitoring the activity of a person will now be described. As shown in the flowchart of Fig. 3, the tracking method begins with an initialization step S200, and then continues with steps S210 through S260. The process comprises two distinct phases that can be executed independently of each other, and cyclically:

• the first phase or phase of tracking data acquisition and acquisition, corresponding to steps S210 and S220, and
• the second phase or phase of analysis and exploitation of the monitoring data, corresponding to steps S230 to S260.

For the same cycle of implementation of the method, the first phase may be repeated several times before the execution of the second phase, and the execution of the second phase assumes at least one execution of the first phase.

Preferably, the second phase is executed periodically, for example every hour from the tracking data generated during the period considered, while the first phase is triggered by the detection of an electrical signal on the network of distribution of electricity, and can be executed at any time and in parallel with one of the stages of the second phase.

The two aforementioned phases are preferably performed by two independent devices and distributed around the network 50, namely the detection device 110 on the one hand, and the processing server 150 on the other hand.

In step S210, the detection device 110 detects a high frequency electrical signal on the electricity distribution network 105.

• des données (date et heure) relatives au moment de la détection effectuée,
• des données d'identification de l'appareil ayant déclenché le signal électrique, ainsi que
• des données de caractérisation de l'action sur qui a déclenché le signal électrique.

In the following step S220, the detection device 110 generates, by analysis of the detected electrical signal, tracking data comprising:

• data (date and time) relating to the time of the detection carried out,
• identification data of the device that triggered the electrical signal, as well as
• characterization data of the action on which triggered the electrical signal.

The tracking data generated by the detection device 110 is then transmitted via the communication network 50 to the processing server 150 which records them. The set of tracking data stored in the processing server constitutes a history of the different detections that took place in a period of time. given time.

The following table provides an example of recorded tracking data for a given time period, in this example from 12:50 to 16:55. It thus includes for each recording, a date and time, an identification of the identified electrical device and the operating state of the device (on or off) resulting from the power on or off of the device. dated Hour Apparatus Action / State 05/07/2004 12:50:05 Coffee maker alight 05/07/2004 12:50:40 coffee maker off 05/07/2004 12:50:58 lamp 1 alight 05/07/2004 12:51:17 lamp 1 off 05/07/2004 1:36:52 p.m. lamp 2 alight 05/07/2004 1:36:53 p.m. lamp 2 off 05/07/2004 1:38:58 p.m. hair dryer alight 05/07/2004 1:39:08 p.m. hair dryer off 05/07/2004 1:39:27 p.m. coffee maker alight 05/07/2004 1:39:41 p.m. coffee maker off 05/07/2004 1:39:49 p.m. lamp 1 alight 05/07/2004 4:54:21 p.m. lamp 2 alight 05/07/2004 4:54:38 p.m. lamp 1 off 05/07/2004 4:55:09 p.m. lamp 2 Off

The second phase of the method, corresponding to the steps S230-S260 of analysis and exploitation of the monitoring data, is preferably triggered periodically, even in the absence of detected data, so as in particular to enable an alarm trigger in such a situation.

However, since the time distribution of a person's activities is subject to fluctuations, it is necessary to adjust the period of execution of this second phase of the process to a value which remains greater than a predetermined threshold value, for example. example greater than 15 minutes (min), value below which the analysis of the monitoring data relating to this single period is not significant.

Optionally, the analysis of the data can be performed at shorter time intervals but on a sliding window in time, whose width is predefined, for example fixed at 1 hour (h), 6h or 24h. As a variant, the analysis of the data can be performed on several sliding windows over time, for example on a window of 1 h, on a window of 6 h and on a window of 24 h. In this way, it is possible to detect both momentary fluctuations in the activity (for example, the person did not get up at the usual time or no detection took place in the last hour) and average fluctuations. on a day (for example, the person has only been fed once in the last 24 hours or has hardly moved in the last 24 hours).

In step S230, the processing server 150 determines, from the tracking data, activity indicators relating to different types of activities of the person. These activity indicators are preferably indicators used in the medical setting, for example an ADL indicator ( "Activity of Daily Living", activity of daily living) according to the Katz scale or an IADL indicator ("Instrumental Activity"). of Daily Living ", instrumental activity of daily life) according to the Lawton scale. ADL indicators refer to different types of basic activity: washing, dressing, going to the bathroom, moving around, being a continent, eating. The IADL indicators relate to types of complementary activities that are: telephone, shopping, preparing a meal, cleaning, washing clothes, using transportation, taking medication, keeping a budget. For each of these indicators, it is distinguished according to need between 3 and 7 levels characterizing the degree of autonomy or dependence of the person for each of these types of activity.

According to one embodiment, the determination of the indicators is performed according to a predetermined set of parameters representative of association rules 232 and weighting criteria 231. These parameters are personalized for a given person according to the level of equipment. electric of its habitat and / or according to its habits.

The habits of the person are determined during a preliminary interview, conducted for example by a doctor. The level of electrical equipment is determined during the installation of the detection device and after identifying the different devices that will be taken into account during the detection. These parameters are preferably determined prior to the initialization of the process, and then recorded for reuse at each iteration of the process.

The purpose of association rules is to define whether electrical equipment is representative of a given type of activity. With each detectable electrical equipment, One or more activity indicators are thus associated, depending on the nature of the equipment and / or on its location in the building. Activity indicators associated with electrical equipment are those for which the probability, the type of activity for which this indicator of activity is representative, is achieved when using the electrical equipment, is significant or simply non-zero. .

According to an alternative embodiment, each electrical equipment is associated with the room of the building in which it is located. Then, each piece is associated with one or more activity indicators depending on the nature of the activity to which this piece is dedicated. For example, all electrical equipment belonging to the kitchen will be associated by this method to the kitchen and therefore the activity "to feed" or "prepare a meal". Thus even electrical equipment, usually insignificant for a given activity, is taken into account when determining the activity indicator for this activity. For example, lighting a lamp in the kitchen does not mean that the person is or is eating. However, lighting a lamp in the kitchen, if it is simultaneous with lighting an electric plate, increases the likelihood that the person is going or is eating.

The table below is an example of a definition of associations between electrical appliances, rooms in the home or building, and activity indicators. In this example the activity "to feed" or "cook" is associated with the kitchen and the list of electrical equipment of this kitchen. The "getting dressed" activity is associated with the room and the list of electrical equipment in this room. The "cleaning" activity is associated with all the parts and the list of equipment including the vacuum cleaner and the iron. The activity "to move" is associated with all the parts and the electrical equipment of all the parts, in particular with the bulbs of the electric lamps of all the parts. Activity indicators Rooms Electrical appliances concerned To eat Cooked Bulbs, lamps, extractor hood, heating, hob, oven, microwave, kettle, coffee maker, toaster, blender, dishwasher, washing machine, fridge, freezer, food processor, radio To cook Get dressed Bedroom Light bulbs, bedside lamp, heating, television, radio, cd player, electric shutters Wash yourself Bathroom Light bulbs, mirror lighting, heating, hair dryer, razor, electric toothbrush, washing machine, tumble dryer, water heater Wash your clothes Go to the toilet WC Bulbs, electric heating Move All the pieces Bulbs, appliances in each room Do housework All the pieces Vacuum cleaner, iron, Call Corridor Bulbs, Telephone Other Dining room TV, VCR, light bulbs, radio, computer, lamps, fan

The advantage of such association rules is that it is not necessary to make an exact plan of the location of the electrical equipment. Only their assignment to a part is recorded, which greatly simplifies the parameterization work of the device.

The use of such tables of data makes it possible to store in memory in the processing server 150 the associations that are defined for a given piece of equipment, for a given piece or for a given activity indicator. These associations are recorded for example by means of tables or by means of relational databases in which the list of available electrical equipment, the list of parts, the list of activity indicators and the association relations between these are recorded. different entities. Any other form of recording is also possible.

When the house or building comprises a single room (case of a studio), it is possible to define "virtual" rooms, corresponding to areas of the building that are used in place of the usual rooms. For example, in a studio, the room "kitchen" can be defined as the space of the building that is occupied by the kitchenette or the "kitchen area" that is arranged in the studio. The notion of room in the context of the invention therefore does not necessarily imply a limitation by walls or partitions of the part of the building in question, but corresponds to a part of the building that is assigned to a given feature.

From the predefined association rules, weighting values are determined prior to execution of step S230 of the method according to the invention. For each detectable electrical equipment and for each activity indicator with which this electrical equipment is associated, a value of representative weighting of the probability that the type of activity, for which this indicator of activity is representative, is achieved when using this equipment. In other words, the more the use of the device makes it possible to confirm that the person performs an activity of a given type and the weighting value associated with this device for this activity will be important.

For example, for the indicator of activity "to feed", which is characterized by the piece "kitchen", the equipment "electric plate" will have a weighting value higher than the equipment "bulb" of the kitchen. Indeed, it is more likely that a person will feed when using the electric plate than when it lights the kitchen light.

• le moment de la journée,
• le nombre total d'équipements électriques associés au type d'activité,
• le nombre total d'équipements électriques détectés et associés au type d'activité,
• la durée pendant laquelle l'équipement est resté sous tension,
• le nombre de fois que l'équipement a été mis hors ou sous tension,
• la température extérieure,
• la saison,
• le jour de la semaine,
• le degré de confiance dans les données d'identification,
• les habitudes de la personne,
• le nombre d'équipements électriques associés au même type d'activité et mis sous tension peu avant ou peu après l'équipement.

Preferably, the weighting value relative to a given piece of equipment and to a given type of activity is weighted according to at least one criterion selected from the group comprising

• the time of the day,
• the total number of electrical equipment associated with the type of activity,
• the total number of electrical equipment detected and associated with the type of activity,
• the duration during which the equipment has remained energized,
• the number of times the equipment has been turned off or on,
• the outside temperature,
• the season,
• the day of the week,
• the degree of confidence in the identification data,
• the habits of the person,
• the number of electrical equipment associated with the same type of activity and powered up shortly before or shortly after the equipment.

The time of day is a weighting criterion used to characterize the normal hours of completion of a type of activity. When the use of the device is within the normal time range, the activity indicator and the weight value assigned to said device will be higher than when the usage is outside this range. For example, if the electric plate is lit between 11:30 and 14:30 or between 18:00 and 21:00, then the indicator of activity "to feed" will be more important than if it is lit at 4am.

The activity indicator also depends on the status (on or off) of other devices listed in the same room. Indeed if some are lit at the same time, the probability of the person performing the corresponding type of activity is greater and the activity indicator is higher. For example, if the fume hood is fired at the same time as the hotplate, the probability of completing the "feed" activity is greater than if there had been only the fume hood. A given activity indicator is therefore preferably determined from all the weighting values assigned to the devices associated with this indicator.

In addition, since the number and type of devices varies according to each building, the activity indicator must be able to be calculated according to different weighting values. For example, if a person A is only equipped with an electric plate in his kitchen, and if a person B is equipped with 10 electrical appliances, the calculation of the activity indicator must take into account the number of appliances. Indeed, if we assign the same weighting values to the equipment of the two persons, then the person A will never have an indicator of activity high enough to validate the accomplishment of the activity "to feed" while it will have indeed achieved.

Moreover, the activity indicator may vary according to the ignition time of the device, in the sense that the ignition of the device is only relevant from a certain minimum time of use that we will have defined beforehand. For example, if an oven is turned on for 30 minutes, it will enter the calculation of the activity indicator. But if it has been on for one minute then off, this use is not taken into account for the calculation of the activity (zero weighting value) or is taken into account only with a weighting value more low.

If the number of times a device is turned on and off corresponds to a normal use of that device, then the weighting value associated with that device, and therefore the indicator that is derived from it, will be the same. higher.

It is also relevant that the weighting value associated with a device takes into account, in addition to the season, the climate and the outside temperature, without the addition of an additional sensor. For example, in the middle of summer, at noon on a sunny day, a person may cook and eat in his kitchen without turning on the light because it is light enough in the room. The date of the detection of the actuation of a device is used to modulate the weighting values of the luminaires, either according to the hours of the sunrise and sunset or the sunshine, or according to the season or the estimated average temperature for the season.

The weighting value associated with a device, and therefore the indicator derived therefrom, also depends on the confidence score of the detection performed. If there is uncertainty about the detected device, its operation is not taken into account for the calculation of the activity or is taken into account only with a lower weighting value.

Preferably, the different weighting values are determined by taking into account the information known by the doctor about the habits of the person to be followed and / or according to a learning phase previously performed in the patient and which gives references to his lifestyle, for example, the number of his trips, his meal times, the rooms most often occupied, unused electrical appliances, the days of the week with different schedules, etc.

The activity indicator can also be refined according to the devices used not only simultaneously, but also those used immediately after or just before another device belonging to the same room, or those used during a defined time slot. For example, if the oven is turned off after turning off the plate, the probability of being eaten is greater than if there had been only the oven.

The table below gives an example of taking into account the time of day in the weighting assigned to a given piece of equipment. In this example, when determining the activity indicator "feed", the predefined list of equipment considered includes: bulbs, plates, microwave, kettle, coffee maker, toaster, freezer, extractor hood and fridge. If the detection of power on the toaster occurs in the time slot from 5am to 9am, the weighting value will be higher than if this detection occurs in another time slot. Similarly, if the detection of the use of the freezer occurs in the time slot from 11 am to 14h, the weighting value will be higher than if this detection occurs in another time slot. The time period considered may also vary depending on the day of the week. Time of the day Time interval Weighting value of the device according to the time of day Breakfast [5h - 9h] bulbs 1 plates 3 microwave 3 kettle 3 coffee maker 3 toaster 3 freezer 0 extractor hood 1 fridge two Lunch [11h-14h] bulbs 1 plates 3 microwave 3 kettle 3 coffee maker 3 toaster 0 freezer two extractor hood 3 fridge two

The table below gives an example of taking into account, in the weighting assigned to a given piece of equipment, another weighting criterion which is the duration of use. For each electrical equipment, a relevant minimum duration of use is defined below which the detection of the use of an electrical equipment is not taken into account for a given activity. These minimum data are for example chosen as follows; Apparatus minimum relevant duration kettle 1 mn Coffee maker 2 minutes Plate 5 minutes Oven 10 minutes Microwaves 5s Toaster 30s Mixer 3s Fridge 3s Freezer 3s

The influence of the different weighting criteria on the weighting values or the calculation of the activity indicators can be taken into account in a manner similar to what has been described for the ignition time or the time slot of use.

In general, the weighting values associated with criteria that are independent of the detections made (for example, criteria related to the habits of the person, the time slot, the season, the level of electrical equipment of the building,. ..) are preferably predetermined by tables. The other weighting values, which are dependent on the detections made (for example, criteria relating to the number of devices detected, the confidence rating of the detection, the ignition time of the device), are in turn determined. dynamically from the recorded tracking data.

For taking into account a plurality of weighting criteria, several methods are possible.

According to a first method, a representative global weighting value is determined according to these criteria of the relevance of the use of the equipment in the determination of a given activity indicator. This global weighting value is obtained for example by weighted average or multiplication of weighting values (in the case where they are normalized between 0 and 1) obtained according to each of the criteria considered individually.

According to an implementation variant of this first method, the weighting values associated with different time slots, given days of the week or different calendar periods, are stored in different tables, a table corresponding each time to a time slot. , at a given day of the week and at a given calendar period.

• parmi les données de suivi enregistrées, on ne retient que celles pour les appareils ayant été détectés dans cette plage horaire,
• parmi les appareils sélectionnés, on ne retient que ceux qui sont pertinents pour l'activité "se nourrir", c'est-à-dire ceux associés à la pièce "cuisine",
• parmi ceux-ci on ne retient que ceux dont la durée d'utilisation est supérieure à la durée minimale d'utilisation.

According to a second method, successive iterations are carried out for the application of the various weighting criteria. For example, for the determination of the activity indicator "to feed", relative to the period from 5am to 9am (breakfast), the following steps are carried out:

• among the recorded tracking data, only those for the devices detected in this time range are retained,
• among the selected devices, only those that are relevant to the "eating" activity, ie those associated with the "kitchen" part, are retained.
• among these we only retain those whose duration of use is greater than the minimum duration of use.

• a) si un des appareils au moins a une valeur de pondération de 3, l'indicateur d'activité est de 75% au moins;
• b) sinon, si un des appareils au moins a une valeur de pondération de 2, l'indicateur d'activité est de 60% au moins;
• c) sinon, on considère qu'il y a seulement indication de présence dans la cuisine et l'indicateur est mis à une valeur entre 0 et 60%, la pondération entre la valeur 0% et la valeur 60% étant fonction du pourcentage d'appareil détectés ayant une valeur de pondération de 1 parmi les appareils associés à cet indicateur et à cette plage horaire.

The selected devices have a predefined weighting value which is fixed for example between 1 and 3, the weighting value of 3 corresponding to the level of highest probability. Three cases then arise:

• (a) if at least one of the apparatuses has a weighting value of 3, the activity indicator is at least 75%;
• b) otherwise, if at least one of the devices has a weighting value of 2, the activity indicator is at least 60%;
• c) otherwise, it is considered that there is only indication of presence in the kitchen and the indicator is set to a value between 0 and 60%, the weighting between the value 0% and the value 60% being a function of the percentage of detected device with a weighting value of 1 among the devices associated with this indicator and time slot.

In the case a), the value of the indicator will be between 75% and 100%, the value of 100% corresponding to the detection of all the devices associated with this indicator and this time slot. The weighting between the 75% value and the 100% value depends on the number of devices detected for that indicator and range, and their respective weighting values. The remaining 25% between 75% and 100% are preferably distributed in proportion to the weighting values of the electrical devices associated with this indicator, other than the one having been detected at a weighting value of 3 in step a). So if the devices considered for the remaining 25% are 3 in number, two of which have a weighting value of 2 and one has a weighting value of 1, the first two each represent a probability of 10% each and the last one probability of 5% (2 * 10% + 1 * 5% = 25%). It is assumed for this purpose that the probability assigned to a device of weighting value of 2 is twice that of a device of weighting value of 1.

If therefore in case a) a single apparatus with a weighting value of 2 is detected, the activity indicator finally obtained is: $$75\%+10\%=85\%\mathrm{.}$$

If a device with a weighting value of 2 and a device with a weighting value of 1 are detected, the activity indicator obtained in the end is: $$75\%+10\%+5\%=90\%\mathrm{.}$$

In case b), the value of the indicator will be between 60% and 75%, the value of 75% corresponding to the detection of all the devices associated with this indicator and this time slot, except those with a value of weighting 3. The weighting between 60% and 75% depends on the number of devices detected for that indicator and range, and the respective weighting values of those devices. The remaining 15% between 60% and 75% is preferably prorata weighting values of electrical equipment associated with this indicator, other than the one having been detected at a weighting value of 2 in step b) and other than those having a weighting value of 3.

The general principle of using weighting values allows not only integration into the calculation of activity indicators of a succession of weighting criteria, but also allows great flexibility in the customization of the determination of activity indicators. . The weighting values are in fact adaptable to the lifestyle of the person to be followed and to the level of electrical equipment of their habitat, which allows a completely personalized determination of the various indicators of activity.

In step S230 of FIG. 3, the processing server 150 determines each activity indicator relative to a given period of time, from the weighting values determined for the electrical equipment that has been detected in this period and which are associated with this activity indicator. The activity indicator thus determined is in fact a probability of performing the type of activity for which this indicator is representative. The value of this indicator is preferably defined according to a predefined scale, for example between 0 and 100%, between 0 and 10, between 0 and 1 or on any other scale.

• le nombre de déplacements réalisés entre deux pièces données dudit environnement,
• le nombre total de déplacements entre deux pièces quelconques,
• la durée d'occupation d'une pièce donnée.

According to an alternative embodiment, an activity indicator for the "moving" activity is determined from at least one value chosen from the group comprising

• the number of displacements made between two given pieces of said environment,
• the total number of displacements between any two parts,
• the duration of occupation of a given room.

The activity "to move" is indeed a particular activity whose indicator requires a suitable method of determination. Whenever the power on or off of an electrical equipment is detected, it is possible to determine if a displacement between two parts has taken place by comparing the room where the equipment which has just been detected is located. the room where the previously detected equipment is located. For example, the detection of the powering up of an electric lamp in the kitchen, followed by the powering up of the electric shaver in the bathroom, leads to the conclusion that a trip has taken place between the kitchen and the bathroom. bath, this trip having for starting point the kitchen. If the pieces of arrival and departure are identical, one does not record any displacement. In the opposite case, a displacement counter is incremented for each pair of pieces.

Introducing, in the context of the invention, the notion of type of displacement which corresponds to a displacement between given starting part and a given end piece, the two parts being distinct. Each room pair, therefore corresponds to a type of displacement.

For the activity indicator "to move", one associates with each fixed equipment the room where this equipment is located, and with each pair of pieces, a type of displacement. The associations that are defined between the equipment and the parts for the determination of the other indicators of activity, are thus also used for the accounting of the number of displacement by type of displacement.

The number of displacements detected over a given period of time is recorded in an array, for example in the form of a matrix giving the number of displacements for each type of displacement. The table below is an example of such a record. \ Arrival departure \ Cooked Bedroom Dining room Bathroom WC Total Cooked X 0 5 0 1 6 Bedroom 1 X 1 1 1 4 Dining room 3 1 X 1 3 8 Bathroom 1 1 0 X 1 3 WC 1 two two 1 X 6 Total 6 4 8 3 6 27

• la chambre P1,
• la salle de bain P2,
• la cuisine P3,
• la salle à manger P4,
• les WC P5,
• etc.

According to one variant, the occupation time of each piece is measured correlatively with the measurement of the number of displacements. The correlation between these two measurements is illustrated in Figures 4a and 4b. Figure 4a shows an example of a chronogram of occupation of the rooms during a day. Each room (bedroom, toilet, bathroom, kitchen, dining room) is identified by a rectangle with a type of pattern or hatching determined, according to the legend of this figure. The occupied rooms are, in chronological order:

• room P1,
• the bathroom P2,
• the kitchen P3,
• the dining room P4,
• the toilet P5,
• etc.

• déplacement de la chambre vers la salle de bain d1,
• déplacement de la salle de bain vers la cuisine d2,
• déplacement de la cuisine vers la salle à manger d3,
• déplacement de la salle à manger vers les WC d4,
• etc.

The detected displacements are also represented, as a function of time, in FIG. 4b, each displacement being marked on the temporal axis by a vertical line. The displacements effected, corresponding to the successively occupied parts that have been described in FIG. 4a, are, in chronological order:

• moving the room to the bathroom d1,
• moving the bathroom to the kitchen d2,
• moving from the kitchen to the dining room d3,
• moving from the dining room to the toilet d4,
• etc.

According to one variant, only the displacements that are coherent with respect to the time slot in question and with respect to the activity that normally takes place therein are used for the measurement of the activity indicator "to move".

From the detection of movements and their date and time, it is easy to deduce the occupation time of each part as well as the temporal distribution of the occupation of the parts. Preferably, each room is assigned a minimum occupancy time below which it is considered that there has been no occupation of the room. In this case, the occupation is not memorized, and neither does the displacement that took place correlatively occur.

The global activity indicator "to move" is determined for example by determining the total number of displacements. According to a variant, this value is weighted according to the average duration of occupation of each of the pieces. Indeed, the shorter this duration, the higher the frequency of movements, which is indicative of greater mobility.

The operating data, including the activity indicators and other quantities relating to movement or occupation of the parts, are then compared to step S240 of FIG. 3 with a set of reference or reference data 241 to determine in step S250 an overall relative indicator representative of the normal character of the activity of the person in his environment when it is examined over a given period of time. This global information makes it possible, in the event of an anomaly, to trigger in step S260 an alert or the sending of a message via the communication network 50 to the persons likely to intervene: emergency service, doctor, family member, etc.

The global relative indicator determined by the processing server 150 is transmitted to the operating terminal 180. The operating terminal 180 determines from this indicator whether an alert should be triggered. According to an alternative embodiment, the operating data are displayed on display means 182 of the operating terminal and it is a natural person, for example a doctor 190, who is assigned to the monitoring of the indicators and assesses whether a alert must be triggered in view of the displayed operating data.

• les différents indicateurs d'activités, qui ont été décrits;
• le nombre de déplacements effectués pour chaque type de déplacement;
• le nombre total de déplacements;
• la durée d'occupation de chaque pièce;
• la ou les plages horaires d'occupation de chaque pièce;
• la répartition temporelle des déplacements et des activités;
• la répartition temporelle de l'occupation des différentes pièces;
• la répartition temporelle des mises sous tension ou mises hors tension pour chaque équipement;
• la répartition temporelle des mises sous tension ou mises hors tension tous équipements confondus.

The reference used in step S240 consists of reference values, preferably corresponding to average values of different quantities corresponding to operating data obtained over a given period of time (for 24h, for 1h, a given time slot ), which is identical to that for which the values of the current quantities are determined. These quantities include, for example:

• the various activity indicators, which have been described;
• the number of trips made for each type of trip;
• the total number of trips;
• the duration of occupation of each room;
• the time slot or hours of occupation of each room;
• the temporal distribution of travel and activities;
• the temporal distribution of the occupation of the different rooms;
• temporal distribution of energized or de-energized for each equipment;
• the temporal distribution of the energized or de-energized all equipment.

• défaut ou baisse d'occupation d'une pièce;
• nombre de déplacements en baisse ou en hausse;
• nombre de déplacement anormalement dans une plage horaire donnée;
• indicateur d'activité en baisse ou anormalement bas.

From such a repository, it is possible to detect a certain number of abnormal situations of the type:

• defect or decrease of occupation of a room;
• number of trips down or up;
• number of abnormal trips within a given time period;
• activity indicator down or abnormally low.

For a given person, the average activity indicator may be low without this being abnormal for the person in question. By creating a repository, we give a measure of what is "normal" for the person being followed, that is, what corresponds to a statistical average. The repository is best obtained in calculating not only an average value of each magnitude of the frame of reference, but also a standard deviation of the distribution of this magnitude. It is considered that the situation becomes abnormal when the total number of trips determined for the period considered is less than the average value of the frame of reference to which a value has been subtracted proportional to the corresponding standard deviation, for example twice the difference type.

The same principle of detection of abnormal character is applicable to the other quantities of the reference system, for example to the number of displacement for a given type of displacement, to the average hourly period of occupation of a part, to the value of an indicator of activity, etc.

Preferably the average values obtained by measurement are supplemented by an interview with the person to follow in order to know his habits and to possibly weight the data of the reference system according to these habits. This interview also aims to determine if the person is away from home at certain times during the week or in the day, so as not to trigger an alert if there is no detection at these times. Preferably a distinction is made in the repository between the values of the quantities relating to different days in the week. The weighting values that are predetermined are also adjustable according to the results of such maintenance as has already been described.

Preferably, the repository is updated cyclically, for example every month, every 6 months, or with another periodicity, according to new average values detected. As a result, there is a permanent automatic readjustment which makes it possible to follow the evolutions of the activity of the person and to distinguish between what is a normal evolution of the person's activity over time and what results from an abnormal abnormal variation of its activity.

For this purpose, the global relative indicator is determined by amplifying any difference between the value of an estimated quantity and the value of the corresponding reference quantity. Any variation, even small compared to the normal character defined by the repository, is amplified. For example, if a benchmark has an average value of 75% and a standard deviation of 10%, and the estimated indicator is only 50%, the difference between this estimated indicator and the normality threshold is: $$\left(75\mathrm{\%}-\mathrm{two}*10\mathrm{\%}\right)-50\mathrm{\%}=5\mathrm{\%}.$$

This difference is magnified to give a relative overall indicator not 100% (relative indicator representative of the normal character) but an overall relative indicator decreased by at least 5%, for example an overall relative indicator of 80%. If moreover several other indicators have abnormal values, the global relative indicator will fall very quickly. The lower it is and close to 0%, and the more the abnormal character is underlined.

Generating a global relative indicator in the form of a single measurement makes it possible to automatically track a large number of people from the same operating terminal in so far as the latter collects data determined for all These persons. This triggers alerts based on the value of this global indicator.

• une valeur d'indicateur relatif global inférieure à une valeur de seuil de 80% donne lieu à un premier niveau d'alerte, qui implique par exemple à envoyer un message électronique ou message téléphonique à un proche de la personne suivie;
• une valeur d'indicateur relatif global inférieure à une valeur de seuil de 50% donne lieu à un deuxième niveau d'alerte, qui implique par exemple à prévenir le médecin traitant;
• une valeur d'indicateur relatif global inférieure à une valeur de seuil de 20% donne lieu à un troisième niveau d'alerte, qui implique par exemple à prévenir les services de secours d'urgence;

Threshold values are thus defined for this global relative indicator, each corresponding to an alert level. For example:

• a global relative indicator value less than a threshold value of 80% gives rise to a first alert level, which for example involves sending an electronic message or telephone message to a relative of the person being followed;
• an overall relative indicator value less than a threshold value of 50% gives rise to a second level of alert, which for example involves informing the treating physician;
• an overall relative indicator value below a threshold value of 20% gives rise to a third level of alert, which for example involves warning emergency services;

• indicateur "s'habiller" A1 de valeur 92%,
• indicateur "aller aux toilettes" A2 de valeur 92%,
• indicateur "se laver" A3 de valeur 99%,
• indicateur "se nourrir" A4 de valeur 34%.

Optionally, the operating data is transmitted in their entirety to the operating terminal 180 so that a person 190 assigned to the exploitation of these data, can very quickly see what an anomaly indicated by the user is. global relative indicator, and in particular to note which are the indicators of abnormally low activity. These operating data are preferably displayed on the operating terminal 180 in visual form, similar to that of the representations of FIGS. 4a to 4c, so as to facilitate the rapid interpretation of the operating data. Figures 4a and 4b have already been described. Figure 4c is an example of a visual representation of the values determined for the different activity indicators:

• indicator "dressing" A1 of 92% value,
• indicator "go to the bathroom" A2 with 92% value,
• "wash" indicator A3 with 99% value,
• indicator "feed" A4 worth 34%.

In conclusion, the invention allows a remote monitoring of the activity of a person from an electrical signal generated on the building's electricity distribution network and without requiring the installation of many sensors. The tracking information recorded following the detections made, are used by comparison with reference data representative of the normal character of the activity of the person to follow. The activity indicators are estimated according to the detected equipment and from the statistical knowledge of the activity of the person (the repository, the habits of the person), rules associating a device to an activity, weighting criteria allowing the algorithm of determination to be adapted to the equipment level of the person, to his habits, to the conditions of detection, etc. The invention thus makes it possible, starting from very simple means of detection and a method proceeding by weighting values, to reach a high degree of precision and reliability in the monitoring of the person. In addition, the invention is adapted for the simultaneous monitoring of a multitude of people, by determining a global relative indicator on the basis of which prevention measures can be triggered fully automatically.

Finally the invention applies to the measurement of activity to any type of building, whether for private or professional use. The invention therefore has applications in the field of remote monitoring, especially for business premises. It can be applied to the measurement of the activity of several people operating within a building insofar as a global measure for all persons - and not individual - is sufficient for the application concerned.

Claims (10)

A method of remotely monitoring the activity of at least one person (112) in a building (100), the method being characterized by including, - A step of obtaining, a detection device capable of detecting on the electricity distribution network of the building at least one predefined electrical signal produced by an electrical equipment of the building when a change of electrical operating state occurs. produced in said electrical equipment, tracking data relating to at least one detected electrical signal, the tracking data including, - information relating to a detection date of the detected electrical signal, - identification data of the electrical equipment having produced the detected electrical signal, data relating to the change of electrical operating state at the origin of the detected electrical signal, a step of determining, from monitoring data generated over a predefined period of time, at least one estimate of the activity exerted by said person. The method of claim 1, wherein said activity estimate is determined as at least one activity indicator representative of the probability of performing at least one type of activity by said person during said period of time . Method according to claim 2, characterized in that it further comprises the steps of - associate at least one electrical equipment with each activity indicator, assigning, to each electrical equipment associated with an activity indicator, a weighting value that is representative of the probability of performing the type of activity for which this indicator is representative when an action causing a change of electrical state of equipment is performed by the person on the equipment, - determining an activity indicator from the weighting values determined for the electrical equipment associated with this activity indicator. A method according to claim 2 characterized in that it further comprises the steps of determining at least one relative activity indicator which is representative of the normal character of the activity of the person in said building over a period of time by comparing a given activity indicator for that period of time with a reference activity indicator for the same period of time . A method according to claim 4 characterized in that it further comprises triggering an alert conditional on the value of said at least one relative activity indicator. Method according to any one of Claims 3 to 5, characterized in that the weighting value relative to a given piece of equipment and to a given activity indicator is modulated as a function of at least one criterion chosen from the group comprising - the time of the day, - the total number of electrical equipment associated with the activity indicator, - the total number of electrical equipment detected and associated with the activity indicator, - the duration during which the equipment has remained energized, - the number of times the equipment has been switched off or on, - the outside temperature, - the season, - the day of the week, - the degree of confidence in the identification data, - the habits of the person, - the number of electrical equipment associated with the same activity indicator and switched on shortly before or shortly after the equipment. A method as claimed in any one of the preceding claims comprising determining a displacement indicator from at least one value selected from the group consisting of the number of displacements made between two given pieces of said environment, - the total number of displacements between any two parts, - the duration of occupation of a given room. A method as claimed in any one of the preceding claims, wherein a change of electrical state of an electrical equipment is produced as a result of an action performed by the person on the equipment,
said action belonging to the group of actions including powering up and de-energizing the equipment or a subset thereof;
said tracking data indicating the nature of the action causing the change of electrical state of the equipment in question. Data processing device (150) for remotely monitoring the activity of at least one person in a building (100), the device being characterized by including, means (152, 153) for obtaining, from a detection device capable of detecting on the building's electricity distribution network at least one predefined electrical signal produced by an electrical equipment of the building when a change of state electrical operation occurs in said electrical equipment, tracking data relating to at least one detected electrical signal, the tracking data including, - information relating to a detection date of the detected electrical signal, - identification data of the electrical equipment having produced the detected electrical signal, data relating to the change of electrical operating state at the origin of the detected electrical signal, means (151) for processing data making it possible to determine, from monitoring data generated during a predefined period of time, at least one estimate of the activity exerted by the person. Device for remotely monitoring the activity of at least one person in a building comprising, a detection module (115) for detecting, on the building's electricity distribution network, predefined electrical signals, each of which is generated by an electrical equipment of the building when a change of electrical operating state occurs in said electrical equipment; analysis means (116) for generating, by analysis of at least one of the detected electrical signals, tracking data including - information relating to a detection date of the detected electrical signal, - identification data of the electrical equipment having produced the detected electrical signal, data relating to the change of electrical operating state at the origin of the detected electrical signal, means (151) for processing data making it possible to determine, from monitoring data generated during a predefined period of time, at least one estimate of the activity exerted by the person.

Images