Learning system and learning method

Abstract

To provide a learning system and a learning method capable of creating learning behavior data following an actual condition of a behavior pattern of an object person.SOLUTION: A learning system includes a power sensor 110 which can detect behaviors of an object person P1 by enabling the continuous detection of a use state of equipment provided in a dwelling house 1 used by the object person P1, and a server 120 for creating learning behavior data related to the behaviors of the object person P1 by learning measurement data by the power sensor 110, and setting a condition to the creation of the learning behavior data such that the learning behavior data is not separated from an actual condition of the behavior pattern of the object person P1.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technology for a learning system and a learning method for learning the results of detecting the behavior of a subject. [Background technology]

[0002] Conventionally, technologies for a learning system and a learning method for learning the detection results of the behavior of subjects residing in a building have been publicly known, as described in Patent Document 1, for example.

[0003] Patent Document 1 describes a lifestyle pattern management system that detects changes in the lifestyle patterns (behavior) of residents using the amount of energy used in a building.

[0004] When detecting a resident's lifestyle pattern using energy usage, as in the invention described in Patent Document 1, even if energy usage data is acquired, the resident's lifestyle cannot be effectively detected when the resident's lifestyle is not stable, for example, when the resident first moves in. As a result, unnecessary data may be acquired until the resident's lifestyle becomes stable, and there is a risk that a lifestyle pattern that reflects the resident's actual situation will not be detected. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2016-48503 A Summary of the Invention [Problem to be solved by the invention]

[0006] The present invention has been made in consideration of the above-mentioned circumstances, and the problem it aims to solve is to provide a learning system and a learning method that can create learning behavior data that is in line with the actual behavior patterns of the subject. [Means for solving the problem]

[0007] The problem to be solved by the present invention is as described above, and the means for solving this problem will now be described.

[0008] That is, in claim 1, the system includes a behavior detection unit capable of detecting the behavior of the subject by continuously detecting the usage status of equipment installed in a building used by the subject, a data creation unit that creates learned behavior data regarding the behavior of the subject by learning the detection results by the behavior detection unit, and a condition setting unit that sets conditions for creation of the learned behavior data by the data creation unit so that the learned behavior data does not deviate from the actual behavior pattern of the subject. The data creation unit is capable of creating active behavior data regarding the behavior of the subject based on the detection result by the behavior detection unit, evaluating a comparison result of the active behavior data with the learned behavior data, and evaluating the comparison result of the active behavior data with the learned behavior data for at least two or more multiple periods having different periods, calculating an average value regarding the use of the equipment for each period, and performing evaluation for each period among the multiple periods in which the calculated average value satisfies a predetermined threshold. It is something.

[0009] In claim 2, the condition setting section is configured to cause the data creating section to start learning when the behavior detecting section detects use of the equipment for the first time, as one of the conditions.

[0010] In claim 3, before When the comparison result is evaluated as being outside a predetermined acceptable range as one of the conditions, the condition setting unit executes a learning necessity determination process to determine whether or not learning is necessary for the corresponding detection result, which is the detection result corresponding to the executive movement data.

[0011] In claim 4, the condition setting unit, in the learning necessity determination process, notifies a predetermined notification unit of a request for feedback regarding the need for learning of the correspondence detection result, and determines whether or not the correspondence detection result needs to be learned based on the obtained feedback.

[0012] In claim 5, the condition setting unit determines whether or not to execute the learning necessity determination process when, in the learning necessity determination process, the corresponding detection result indicates that learning is not necessary, and the next time a detection result with the same content as the corresponding detection result is detected.

[0013] In claim 6, The facility includes a plurality of home appliances, and the condition setting unit sets the condition for each of the plurality of home appliances. It is something. [Effects of the Invention]

[0016] The present invention has the following effects.

[0017] In the present invention, it is possible to create learning behavior data that is in line with the actual behavioral patterns of a subject. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a schematic diagram showing the configuration of a lifestyle pattern determination system according to an embodiment of the present invention; [Figure 2] FIG. 1 is a diagram showing an overview of a series of processes performed by a lifestyle pattern determination system. [Figure 3] 10A to 10C are diagrams showing examples of learning results, detection results in daily processing, and determination results. [Figure 4] 10 is a flowchart showing the contents of a learning start determination process. [Figure 5] 10 is a flowchart showing the contents of a home appliance use count evaluation process. [Figure 6] 10 is a flowchart showing the contents of a learning data update necessity determination process. [Figure 7] 10 is a flowchart showing the contents of an evaluation period determination process. DETAILED DESCRIPTION OF THE INVENTION

[0019] The configuration of a lifestyle pattern determination system 100 according to one embodiment of the present invention will be described below with reference to FIG.

[0020] The lifestyle pattern determination system 100 learns the lifestyle (behavioral) patterns of a subject P1 and determines whether or not there are any abnormalities in the lifestyle patterns based on the learning results. In this embodiment, as an example, the subject P1 is an elderly person residing in a house 1, and it is assumed that the presence or absence of abnormalities in the lifestyle patterns of the subject P1 (and therefore the presence or absence of abnormalities in the cognitive functions of the subject P1) is to be determined. The lifestyle pattern determination system 100 mainly includes a power sensor 110, a server 120, and a terminal 130.

[0021] The power sensor 110 detects the power consumption of various facilities used by the subject P1 (particularly facilities used in daily life). The power sensor 110 is provided in the distribution board 2 of the house 1 where the subject P1 resides. The power sensor 110 can detect the power of each branch circuit of the distribution board 2. This allows the power sensor 110 to detect the usage status (whether or not the facility is being used) of the facility connected to each branch circuit. By detecting the usage status of the facility, it is possible to indirectly detect the behavior of the subject P1 (which facility is being used). The power sensor 110 is installed in the house 1, for example, when the lifestyle pattern determination system 100 is introduced, and thereafter performs detection at all times (continuously).

[0022] In this embodiment, examples of equipment whose power consumption is detected by the power sensor 110 include home appliances such as cooking appliances (e.g., induction cooker, microwave oven), refrigerators, televisions, hair dryers, vacuum cleaners, washing machines, air conditioners, heaters, and lighting. For example, when use of a cooking appliance is detected, it is indirectly detected that the subject P1 has used the cooking appliance (and thus eaten a meal). When use of a television is detected, it is indirectly detected that the subject P1 has watched television.

[0023] The method for detecting the usage status of various pieces of equipment is not limited to detecting the power of each branch circuit using the power sensor 110, and various other methods can be used. For example, it is possible to detect the power (main power) of the main circuit of the distribution board 2 and analyze the waveform of that power to identify and understand the equipment being used. Also, instead of detecting the power of the distribution board 2, it is also possible to directly detect the operating status of each piece of equipment itself (such as whether the power of each piece of equipment is on or off, the power of the outlets to which each piece of equipment is connected, etc.). Furthermore, if the house 1 is equipped with a system (such as a Home Energy Management System (HEMS)) that monitors (manages) the usage status of each piece of equipment, it is also possible to use information monitored by that system.

[0024] The server 120 performs various processes based on the detection results of the power sensor 110. The server 120 is configured, for example, as a virtual server (cloud server) installed on the cloud. The server 120 can grasp the usage status of various facilities by acquiring information from the power sensor 110. The server 120 can learn the usage status (measurement data) of various facilities and generate a lifestyle pattern (learned behavior pattern) of the subject P1 after the introduction of the present system. The server 120 can also generate a lifestyle pattern (actual behavior data) of the subject P1 on the evaluation date based on newly acquired measurement data. In this way, the server 120 can determine whether or not there is an abnormality in the lifestyle pattern of the subject P1 (and therefore an abnormality in cognitive function) by comparing the generated learned behavior pattern with the actual behavior data. The server 120 can also transmit and receive various information to and from the terminal 130, which will be described later.

[0025] The terminal 130 is capable of displaying various types of information. The terminal 130 is carried by a person (for example, a family member or relative of the subject P1) who should know whether there is an abnormality in the lifestyle pattern of the subject P1. In this embodiment, it is assumed that a family member P2 of the subject P1 carries the terminal 130. The terminal 130 is configured, for example, by a device (for example, a smartphone or tablet terminal) that can be carried by the family member P2 of the subject P1. The terminal 130 can notify the family member P2 of the subject P1 of information from the server 120 by an appropriate method (for example, display on an LCD screen, audio, etc.).

[0026] By using the lifestyle pattern determination system 100 configured as described above, it is possible to discover signs or onset of dementia in the subject P1 according to changes in the subject P1's lifestyle pattern.

[0027] For example, symptoms of dementia may include memory impairment, disorientation, executive dysfunction, and a reversal of day and night cycles.

[0028] "Memory impairment" is a disorder that causes symptoms such as being unable to remember new things and losing memories that were previously remembered. When subject P1 develops "memory impairment," it is expected that behavioral changes (abnormalities) will occur, such as forgetting that they have eaten and eating again, or forgetting that they have cleaned and cleaning again.

[0029] "Disorientation" is a disorder in which one is unable to grasp the situation one is in, such as "when, where, who," etc. If subject P1 develops "disorientation," it is expected that behavioral changes (abnormalities) will occur, such as turning on the heater even though it is summer, becoming unable to find one's place in the house and being unable to go to the toilet or bathroom, or being unable to return home once one has gone out.

[0030] "Executive dysfunction" is a disorder that makes it difficult to plan and carry out things in an orderly manner. If subject P1 were to develop "executive dysfunction," it is expected that behavioral changes (abnormalities) would occur, such as being unable to prepare meals or not knowing how to use electrical appliances.

[0031] "Day-night reversal" is a disorder in which the sleep-wake rhythm is disrupted and day and night are reversed. When subject P1 develops "day-night reversal," it is expected that behavioral changes (abnormalities) will occur, such as being active during the time when they should be sleeping (in the middle of the night).

[0032] Therefore, the lifestyle pattern determination system 100 of this embodiment detects changes in the behavior (lifestyle pattern) of the subject P1 as described above, and determines whether or not the subject P1 has an abnormality in cognitive function based on this change in behavior. Then, as necessary, the family P2 of the subject P1 is notified of the abnormality in cognitive function of the subject P1. This allows the family P2 of the subject P1 to recognize the signs and onset of dementia in the subject P1, and to take appropriate measures (treatment, etc.) at an early stage.

[0033] An outline of a series of processes performed by this lifestyle pattern determination system 100 will be described below.

[0034] 2, the server 120 stores various types of equipment installed in the house 1. In this embodiment, the server 120 stores a plurality of home appliances such as cooking appliances (IH, microwave), refrigerators, televisions, hair dryers, vacuum cleaners, washing machines, and seasonal home appliances (air conditioners, heating appliances) as various types of equipment. The server 120 performs appropriate processing for each of these home appliances to determine whether or not the subject P1 has an abnormality in cognitive function, and notifies the subject P1's family member P2 of the abnormality in cognitive function as necessary.

[0035] Specifically, the server 120 detects the usage status (and thus the behavior of the subject P1) for each day (every day), and performs a process of determining whether or not there is an abnormality in the cognitive function of the subject P1 based on the detection results. Hereinafter, this process will be referred to as "daily processing." In the daily processing, the server 120 stores the behavior to be determined, the presence or absence of an abnormality, and the reason for the determination, in association with each other.

[0036] The server 120 also detects the usage status (and thus the behavior of the subject P1) on a weekly (weekly) basis, and performs a process to determine whether or not the subject P1 has an abnormality in cognitive function based on the detection results. This process is hereinafter referred to as "weekly processing." In the weekly processing, the server 120 stores the behavior to be determined, the presence or absence of an abnormality, and the reason for the determination, in association with each other.

[0037] The server 120 also detects the usage status (and thus the behavior of the subject P1) every month (weekly) and performs a process to determine whether or not there is an abnormality in the cognitive function of the subject P1 based on the detection results. This process is hereinafter referred to as "monthly processing." In the monthly processing, the server 120 stores the behavior to be determined, the presence or absence of an abnormality, and the reason for the determination, in association with each other.

[0038] The server 120 also calculates the number of times an abnormality is detected for each behavior during the week through the daily processing. Then, for behaviors for which an abnormality is detected a predetermined number of times or more, an alert (warning) is issued using the terminal 130. Hereinafter, this processing will be referred to as "weekly result notification." The weekly result notification allows the family member P2 of the subject P1 who owns the terminal 130 to understand that an abnormality has occurred in a predetermined behavior of the subject P1, and thus that there is a possibility that the subject P1's cognitive function may be declining.

[0039] The server 120 also calculates the number of times that an abnormality is detected for each behavior during the month through the weekly and monthly processing. Then, for behaviors for which an abnormality is detected a predetermined number of times or more, an alert is issued using the terminal 130. Hereinafter, this process will be referred to as "monthly result notification." This allows the family member P2 of the subject P1, who owns the terminal 130, to understand that an abnormality has occurred in the subject P1's behavior and, ultimately, that his / her cognitive function may be declining.

[0040] In this way, the lifestyle pattern determination system 100 performs each process for each target home appliance (target home appliance) to determine whether or not there is an abnormality in the cognitive function of the target person P1 and can issue an alert to the family P2 of the target person P1. Whether daily, weekly, or monthly processing is performed for each target home appliance is determined by executing an evaluation period determination process, which will be described later.

[0041] As a prerequisite for the process of determining whether or not the subject P1 has an abnormality in cognitive function, the server 120 detects the usage status of various facilities in the house 1 over a predetermined period of time and stores the detected status in a predetermined storage area. Thus, the server 120 acquires the detection results (measurement data) of the power sensor 110 and, by executing a data management process described below, appropriately learns the acquired measurement data (i.e., the subject P1's behavioral tendencies) and generates the learning results (learned behavior data). As a result, the server 120 detects the behaviors and time periods that the subject P1 performs throughout the day and understands the behaviors that the subject P1 performs for each time period. That is, the learned behavior data includes the time periods and the number of times each day that the subject P1 performs the behaviors since the system was introduced. The "learning results" in the table of FIG. 3 shows an example of learned behavior data.

[0042] For example, when the server 120 detects that a cooking appliance (IH, microwave) has been used, it learns the time period during which it was used. This is repeated for a predetermined period of time to understand the behavior of the subject P1, such as the time period during which the subject P1 usually uses the cooking appliance. The server 120 also indirectly detects that the subject P1 has gone to bed by, for example, turning off the lights in the house 1, and learns the sleeping hours of the subject P1.

[0043] The behavior of the subject P1 changes depending on the season, such as air conditioners and heaters being used only in the seasons when they are needed (summer and winter). Therefore, the server 120 learns the behavioral trends of the subject P1 for each season, and when performing the daily processing described below, it is possible to use the learning results according to the season at that time.

[0044] Furthermore, during the period that is the target (target) of processing (e.g., daily processing) such as the above, the server 120 constantly detects the usage status of various facilities in the house 1 and stores the detected status in a predetermined storage area. In this way, the server 120 acquires the detection results (measurement data) of the power sensor 110 and generates the usage status of various facilities in the house 1 (i.e., the subject P1's actual behavior data) based on the acquired measurement data. That is, the actual behavior data includes the time periods of the activities performed by the subject P1 during the target period of evaluation, the number of times per predetermined period, etc. The server 120 can also update the learned behavior data as appropriate based on the actual behavior data (or newly acquired measurement data). The "detection results" in the table of FIG. 3 shows an example of the actual behavior data.

[0045] In this way, the server 120 can grasp the criteria (time period, number of times, etc.) of the behavior that is the target (target of judgment) for judging the presence or absence of abnormality from the learned behavior data. The server 120 then compares the reference learned behavior data with the actual behavior data for the period to be judged, thereby judging the presence or absence of abnormality in the lifestyle pattern of the subject P1 (and thus the presence or absence of abnormality in cognitive function).

[0046] For example, when determining whether or not there is an abnormality based on the number of times a target home appliance is used per day, server 120 determines (sets) an acceptable range for the number of times the target home appliance is used from the learned behavior data using a predetermined probability distribution. Next, server 120 determines whether the number of times the target home appliance is used, included in the execution behavior data, is within an acceptable range (a predetermined threshold), and determines that the number of times the target home appliance is used is normal (performs a normal determination) if the number of times is within the acceptable range, and determines that there is an abnormality if the number of times is outside the acceptable range (performs an abnormality determination).

[0047] Furthermore, when determining whether or not there is an abnormality based on the time period of the target behavior, the server 120 determines whether or not the use time period of the target appliance in the detection result (actual behavior data) matches the use time period of the target appliance in the learning result (learned behavior pattern), as shown in Fig. 3. In this way, the server 120 determines that there is an abnormality if the use time period of the target appliance in the detection result (actual behavior data) matches the use time period of the target appliance in the learning result (learned behavior pattern), and determines that there is an abnormality if they do not match.

[0048] The data management process performed by the server 120 will be described below.

[0049] The data management process appropriately manages the acquired measurement data so that the created learning behavior data does not deviate from the actual life pattern of the subject P1. The data management process includes a learning start determination process, a frequency evaluation / update necessity determination process, and an evaluation period determination process.

[0050] First, the learning start determination process by the server 120 will be described below with reference to FIG.

[0051] Here, for example, when subject P1 moves into house 1, all of the target equipment (various types of equipment) may not be installed. In such a case, if learning is started using measurement data acquired immediately after subject P1 moves in, the learning behavior data will be generated based on measurement data obtained when the target home appliance (target home appliance) is not present. In this way, the target home appliance installed some time after subject P1 moves in will be determined to be a target home appliance with a low usage frequency at the time of installation, regardless of its actual usage frequency, which creates a problem in that the learning behavior data may not match the actual situation.

[0052] Therefore, in the lifestyle pattern determination system 100, a learning start determination process is executed, and the timing to start learning is determined by the server 120 rather than at the time of moving in, thereby preventing the occurrence of the above-mentioned problems. The learning start determination process is executed, for example, once a day (for example, at midnight), based on measurement data for the previous 24 hours.

[0053] Server 120 repeats the processes from step S101 to step S106 for each target home appliance of each type of equipment in the learning start determination process as shown in Fig. 4. Each process from step S101 to step S106 will be described below.

[0054] First, in step S101, the server 120 reads 24 hours' worth of measurement data for the target home appliance stored in a predetermined storage area. Next, in step S102, the server 120 determines whether the detection flag for the target home appliance is OFF.

[0055] Here, the detection flag indicates information on whether or not the power consumption of the target home appliance has been detected in the past (i.e., after the lifestyle pattern determination system 100 was installed in the house 1). In other words, when the detection flag is ON, it indicates that the power consumption of the target home appliance has been detected in the past. When the detection flag is OFF, it indicates that the power consumption of the target home appliance has not been detected in the past. The detection flag is set by the server 120 for each target home appliance.

[0056] If the detection flag is OFF (YES in step S102), server 120 proceeds to step S103. Note that if the detection flag is OFF, the power consumption of the target home appliance has never been detected in the past, and therefore the target home appliance may not yet be installed in house 1. On the other hand, if the detection flag is ON (NO in step S102), server 120 ends the learning start determination process for the target home appliance because the power consumption of the target home appliance has been detected in the past (that is, because learning has already started for the target home appliance).

[0057] In step S103, server 120 determines whether the power consumption of the target appliance is detected in the measurement data (measurement data read in step S101). If server 120 determines that the power consumption of the target appliance is detected in the measurement data (YES in step S103), it proceeds to step S104. On the other hand, if server 120 determines that the power consumption of the target appliance is not detected in the measurement data (NO in step S103), it does not start learning for the target appliance and therefore ends the learning start determination process for the target appliance.

[0058] In step S104, the server 120 sets the detection flag of the target home appliance from OFF to ON. Next, in step S105, the server 120 sets measurement data acquired thereafter, including the measurement data, for the target home appliance as the learning target. In this way, the server 120 uses measurement data acquired thereafter for the target home appliance to generate learning behavior data from the timing of the next learning (for example, the following Sunday).

[0059] Next, in step S106, server 120 notifies terminal 130 that it has detected the power consumption of the target home appliance (i.e., that the target home appliance has been used). Specifically, server 120 adds a text indication such as "IH use has started" to the content of the weekly result notification sent using terminal 130, for example.

[0060] In this way, by executing the learning start determination process, learning begins when use of a target appliance is detected for the first time, so that learned behavior data is generated for appliances that have been used at least once in the past. In this way, it is possible to prevent, for each target appliance, the generation of learned behavior data based on measurement data acquired when, for example, the target appliance is not installed (when the target appliance is not present). In other words, learning can be started at the appropriate time for each target appliance, and it is possible to prevent the learned behavior data from becoming inconsistent (diverging) with the actual situation.

[0061] Next, the process of evaluating the number of times and determining whether or not an update is necessary, performed by the server 120, will be described with reference to FIGS.

[0062] For example, seasonal appliances such as air conditioners and heaters are not used during the off-season, resulting in variations in usage frequency throughout the year. Furthermore, for example, broken appliances (broken appliances) cannot be used even if one wishes to. Thus, if measurement data from periods when seasonal appliances or broken appliances are not used is learned, the learned behavior data will not match the actual situation, such as an abnormality being detected despite the subject P1's normal (normal) lifestyle patterns, and so learning should not be performed.

[0063] On the other hand, if an abnormality is determined to be due to a change in the lifestyle pattern of the subject P1, for example, the measurement data for which the abnormality was determined should be learned (reflected in the learned behavior data). In this way, even for measurement data for which the same abnormality was determined, there is a mixture of data that should be learned and data that should not be learned (measurement data from periods when the appliance is not in use, such as seasonal appliances or faulty appliances), which makes it difficult to determine whether the measurement data needs to be learned.

[0064] Therefore, in the lifestyle pattern determination system 100, a process for evaluating the number of times and determining whether an update is necessary is executed, and while providing feedback from the subject P1, family P2, etc., the measurement data for which an abnormality is determined is one that should be learned, thereby preventing the occurrence of the above-mentioned problems. The process for evaluating the number of times and determining whether an update is necessary targets target home appliances for which the detection flag is determined to be ON in the learning start determination process.

[0065] The frequency evaluation and update necessity determination process includes a home appliance usage frequency evaluation process and a learning data update necessity determination process. Specifically, for a target home appliance whose detection flag is determined to be ON in the learning start determination process, the home appliance usage frequency evaluation process is first executed, and then the learning data update necessity determination process is executed as necessary.

[0066] First, the home appliance usage count evaluation process, which is part of the frequency evaluation and update necessity determination process, will be described with reference to FIG.

[0067] Server 120 repeats the processes from step S201 to step S210 for each target home appliance of each type of equipment in the home appliance use count evaluation process as shown in Fig. 5. Each process from step S201 to step S210 will be described below.

[0068] First, in step S201, the server 120 reads 24 hours' worth of measurement data for the target home appliance stored in a predetermined storage area. Next, in step S202, the server 120 determines whether the interruption flag for the target home appliance is OFF.

[0069] Here, the suspend flag indicates information on whether the measurement data is to be learned (reflected in the learned behavior data). That is, when the suspend flag is ON, it indicates that the measurement data is not to be learned (reflected in the learned behavior data). When the suspend flag is OFF, it indicates that the measurement data is to be learned (reflected in the learned behavior data). The suspend flag is set by the server 120 for each target home appliance.

[0070] If the interruption flag is OFF (YES in step S202), the server 120 proceeds to step S206. On the other hand, if the interruption flag is ON (NO in step S202), the server 120 proceeds to step S203.

[0071] In step S203, server 120 determines whether the target appliance has been used. That is, server 120 determines whether the power consumption of the target appliance has been detected in the measurement data. If the power consumption of the target appliance has been detected, server 120 determines that the target appliance has been used and proceeds to step S204.

[0072] On the other hand, if the power consumption of the target home appliance has not been detected, server 120 determines that the target home appliance has not been used and ends the home appliance use count evaluation process for the target home appliance. That is, if the interruption flag is ON (NO in step S202) (i.e., a period when the target home appliance is not being used, for example, a seasonal home appliance or a broken appliance) and the target home appliance has not been used (NO in step S203), it is determined that the period when the appliance is not being used continues, and the home appliance use count evaluation process ends.

[0073] In step S204, server 120 sets the interruption flag of the target home appliance from ON to OFF. Next, in step S205, server 120 notifies terminal 130 that it has redetected the power consumption of the target home appliance (i.e., that use of the target home appliance has resumed). Specifically, server 120 adds a text indication such as "Use of induction heater has resumed" to the content of the weekly result notification sent using terminal 130, for example.

[0074] In step S206, the server 120 evaluates the number of times the target appliance is used. Specifically, as described above, the server 120 sets an allowable range for the number of times the target appliance is used from the learned behavior data, and then determines whether the number of times the target appliance is used, included in the performance behavior data, is within the allowable range. In this way, the server 120 evaluates the comparison result of the performance behavior data with the learned behavior data.

[0075] Specifically, if the number of uses of the target appliance included in the execution behavior data is within the allowable range (if the comparison result is within the allowable range), server 120 performs a normal determination. On the other hand, if the number of uses of the target appliance included in the execution behavior data is outside the allowable range (if the comparison result is outside the allowable range), server 120 performs an abnormal determination. Note that when step S206 is transitioned from step S205, the learned behavior data of the target appliance used for the determination is the data before the interruption.

[0076] The method for evaluating the comparison result of the active behavior data is not limited to the above, and various methods can be adopted as long as they can evaluate the degree of difference between the active behavior data and the learned behavior data and make an abnormal or normal judgment.

[0077] Next, in step S207, the server 120 notifies the terminal 130 of the evaluation result (abnormal determination or normal determination) in step S206.

[0078] Next, in step S208, server 120 determines whether the evaluation result in step S206 is an abnormality judgment. If server 120 determines that the evaluation result in step S206 is an abnormality judgment (YES in step S208), it proceeds to step S209. On the other hand, if server 120 determines that the evaluation result in step S206 is a normal judgment (NO in step S208), it proceeds to step S210.

[0079] In step S209, the server 120 sets the measurement data for which an abnormality has been determined as unlearned data. Here, unlearned data refers to data for which it has not yet been determined whether it should be learned or not. That is, the server 120 temporarily suspends the determination of whether to learn the measurement data for which an abnormality has been determined, and terminates the home appliance usage frequency evaluation process. At this time, the server 120 temporarily stores the unlearned data in a predetermined storage area. Meanwhile, in step S210, the server 120 reflects the measurement data for which a normality has been determined as being something that should be learned in the learned behavior data. That is, the server 120 updates the learned behavior data.

[0080] Next, the learning data update necessity determination process, which is part of the frequency evaluation and update necessity determination process, will be described with reference to FIG.

[0081] The process of determining whether or not the learned data needs to be updated is executed for the target home appliance from which the unlearned data was acquired when the unlearned data was temporarily stored in a predetermined storage area in the home appliance usage count evaluation process.

[0082] In step S301, the server 120 uses the terminal 130 to notify, for example, a device portable by family member P2, that an abnormality has been determined, and requests feedback regarding whether or not the measurement data for which an abnormality has been determined is problematic (and ultimately, whether or not the measurement data needs to be learned).

[0083] Specifically, the server 120 displays on the notification app installed in the device one of the following four options to prompt the user to select and respond: (a) "There is a problem (notify again if a similar abnormality occurs)", (b) "No problem (it just happened to be different from usual. Notify again if a similar abnormality occurs)", (c) "No problem (no problem as lifestyle patterns have changed)", or (d) "No problem (temporarily not in use due to seasonal appliance or broken appliance)". In this way, the server 120 can receive feedback through the operation of the notification app by family member P2.

[0084] The feedback period (period for accepting responses) is set, for example, until the next update date of the learned behavior pattern. That is, if the learned behavior pattern is updated once a week (for example, on Sunday), the server 120 will accept feedback until the next update date (Sunday). If the server 120 does not receive feedback by the set date, it can discard the unlearned data stored in a specified area.

[0085] In step S302, server 120 determines, based on the received feedback response, whether the abnormality determination is due to the fact that the target appliance is currently not being used. Specifically, server 120 determines whether the feedback response is (d) or any one of (a), (b), and (c).

[0086] Thus, if the feedback answer is (d), server 120 determines that the abnormality determination is due to the period during which the target appliance was not in use (YES in step S302), and proceeds to step S303. On the other hand, if the feedback answer is any one of (a), (b), and (c), server 120 determines that the abnormality determination is not due to the period during which the target appliance was not in use (it was not a period during which the target appliance was not in use) (NO in step S302), and proceeds to step S305.

[0087] In step S303, server 120 discards the unlearned data stored in a predetermined area. Note that server 120 continues to hold the current learned behavior data (learning results up to now) for the target home appliance in a predetermined storage area, in order to use it when the interruption ends and judgment is resumed (after the end of the non-use period).

[0088] In step S304, the server 120 sets the interruption flag of the target home appliance from OFF to ON. After step S304, the server 120 thus ends the learning data update necessity determination process for the target home appliance.

[0089] In step S305, to which the server 120 proceeds after determining that it is not a non-use period (NO in step S302), the server 120 determines whether or not to perform an abnormality determination again when data having the same content as the measurement data for which the abnormality determination was performed is acquired next time or later. Specifically, if the feedback response is either (a) or (b), the server 120 determines to perform an abnormality determination again (YES in step S305), and proceeds to step S306. On the other hand, if the feedback response is (c), the server 120 determines not to perform an abnormality determination again (NO in step S305), and proceeds to step S307.

[0090] In step S306, server 120 discards the unlearned data stored in the predetermined area, and then ends the process of determining whether or not the learned data needs to be updated for the target home appliance.

[0091] In step S307, the server 120 reflects the measurement data for which an abnormality has been determined to be present in the learned behavior data because the measurement data should be learned. That is, the server 120 updates the learned behavior data. The server 120 then terminates the process for determining whether or not the learned data needs to be updated for the target home appliance.

[0092] In this way, by executing the frequency evaluation and update necessity determination process, even if the measurement data has been determined to be the same abnormality, it is possible to distinguish between what should be learned (for example, the measurement data in the case of the above option (c)) and what should not be learned (for example, the measurement data in the cases of the above options (a), (b), and (d)), and the measurement data can be learned based on this distinction. In this way, the accuracy of the learning behavior data can be improved.

[0093] Similarly, even if measurement data is determined not to be learned, the next time the same measurement data is acquired, it is possible to distinguish between data that will be re-determined as abnormal and data that will not be re-determined as abnormal. This reduces the need to repeatedly request feedback from the family P2 of the subject P1, thereby reducing the burden on the family P2.

[0094] For example, if subject P1 has a visitor, an abnormality may be detected by using an electric home appliance such as an induction heater at a different time than usual. Since such abnormality detection does not occur continuously, a family member P2 who provides feedback can choose to perform an abnormality detection (give feedback) the next time the same measurement data is acquired.

[0095] Next, the evaluation period determination process performed by the server 120 will be described with reference to FIG.

[0096] Here, the frequency of use of the target home appliances varies depending on the target person and the type of target home appliance. For example, as shown in Figure 3, among the target home appliances, a microwave oven is used three times a day, while a vacuum cleaner (not shown) is often used two or three times a week. Furthermore, even for the same target home appliance (e.g., an air conditioner), the frequency of use varies depending on the target person. Therefore, if the processing (evaluation) cycle for determining whether or not there is an abnormality in the lifestyle pattern is set uniformly, there is a problem in that the accuracy of the determination results may be low.

[0097] Therefore, the lifestyle pattern determination system 100 prevents the above-mentioned problems from occurring by executing an evaluation period determination process. Specifically, by executing the evaluation period determination process, it is possible to determine the evaluation period (the timing at which evaluation is performed) for each subject person and each subject home appliance. In this embodiment, as described above, evaluation can be performed at three types of periods: daily processing, weekly processing, and monthly processing. In other words, in this embodiment, the three types of evaluation periods that can be determined are daily (day), weekly (week), and monthly (month).

[0098] Note that the server 120 is not able to determine the evaluation period in the initial stage (when measurement data has not been accumulated to an extent that allows learning, such as immediately after the introduction of this system), and is therefore set in advance to perform daily processing (to perform evaluation every day). The evaluation period determination process is executed for each subject (subject P1 in this embodiment), each subject home appliance, and each set evaluation period after measurement data has been accumulated to an extent that allows learning.

[0099] In step S401, server 120 calculates (updates) the average value related to the use of the target home appliance in each evaluation cycle. Specifically, server 120 calculates the average values ​​(daily average value and weekly average value) of the number of times the target home appliance is used for each day and week at the current time, excluding the longest evaluation cycle (monthly). In this way, server 120 calculates the daily average value and weekly average value of the number of times the target home appliance is used. Note that the average value related to use may not be the average value of the number of times of use as described above, but may be an average value of other criteria related to use, such as the amount of time used.

[0100] Next, in step S402, the server 120 determines whether the updated daily average value is less than the minimum standard. Here, the minimum standard is a threshold for determining whether to perform daily processing. In this embodiment, the minimum standard is set to 1. If the updated daily average value is less than the minimum standard (YES in step S402), the server 120 proceeds to step S403. On the other hand, if the updated daily average value is equal to or greater than the minimum standard (NO in step S402), the server 120 proceeds to step S406.

[0101] In step S403, the server 120 determines whether the updated weekly average value is less than the minimum standard. Here, the minimum standard is a threshold for determining whether or not to perform weekly processing. In this embodiment, as in step S402, the minimum standard is set to 1. If the updated weekly average value is less than the minimum standard (YES in step S403), the server 120 proceeds to step S404. On the other hand, if the updated weekly average value is equal to or greater than the minimum standard (YES in step S403), the server 120 proceeds to step S405.

[0102] In step S404, server 120 determines to perform only monthly processing of the target home appliance among daily processing, weekly processing, and monthly processing. That is, monthly (month) is set as the evaluation period. In this way, if the updated daily average value is below the minimum standard and the updated weekly average value is below the minimum standard (YES in step S402, YES in step S403), that is, if the average values ​​of the number of times of use per day and per week are less than 1, it is determined that it is difficult to perform daily and weekly evaluation, and therefore only monthly processing is performed. After executing step S404, server 120 terminates the evaluation period determination process.

[0103] In step S405, server 120 determines to perform weekly processing and monthly processing for the target home appliance out of daily processing, weekly processing, and monthly processing. That is, weekly (week) and monthly (month) are set as the evaluation cycle. In this way, if the updated daily average value is less than the minimum standard and the updated weekly average value is equal to or greater than the minimum standard (YES in step S402, NO in step S403), that is, if the average number of times of use per day is less than 1 but the average number of times of use per week is 1 or greater, it is determined that it is difficult to perform daily evaluation, but it is possible to perform weekly and monthly evaluation, and therefore weekly processing and monthly processing are performed. After executing step S405, server 120 terminates the evaluation cycle determination process.

[0104] In step S406, server 120 determines to perform all of the processes, i.e., daily processing, weekly processing, and monthly processing, for the target home appliance. That is, daily (day), weekly (week), and monthly (month) are set as the evaluation periods. In this way, if the updated daily average value is equal to or greater than the minimum standard (NO in step S402), that is, if the average value of the number of times of use per day is 1 or more, it is determined that daily evaluation, which is the shortest evaluation period, is possible, and all of the processes (daily processing, weekly processing, and monthly processing) are performed. After executing step S406, server 120 terminates the evaluation period determination process.

[0105] In this way, by executing the evaluation period determination process, it is possible to determine the evaluation period (when to perform evaluation) for each target person and target home appliance, thereby improving the accuracy of the determination results. Also, for example, as shown in step S404 or step S405, if it is determined that evaluation will be performed at some of the multiple evaluation periods, there is no need to perform processing at periods in which evaluation is not performed, thereby reducing the load.

[0106] Furthermore, the server 120 can determine the timing of learning in accordance with the determined evaluation cycle. In this way, for example, if it is determined that only monthly processing is to be performed, learning can be prevented from being performed daily or weekly even though evaluation is performed monthly, thereby reducing the load.

[0107] Furthermore, in the initial stage, daily processing, which is the shortest evaluation period, is set to be performed. Here, for example, if weekly or monthly processing is set to be performed in the initial stage, if it is decided to perform daily processing after the initial stage, it may be impossible to create data for the daily processing from data for the weekly or monthly processing. However, in this embodiment, since daily processing is set to be performed in the initial stage as described above, even if it is decided to perform weekly or monthly processing after the initial stage, data to be used for weekly or monthly processing can be easily created.

[0108] Here, in the evaluation period determination process according to this embodiment, in order to determine that evaluation of at least one period out of the multiple evaluation periods (monthly processing, which is the longest evaluation period), calculation of the average number of times the target home appliance is used per month is omitted in step S401. However, it is also possible to determine, for example, whether or not the updated monthly average value is equal to or greater than a minimum standard, and to determine whether or not to perform monthly processing depending on the determination result.

[0109] In this embodiment, the minimum standard is set to 1, but any value can be used without being limited to this. Also, the minimum standards for the daily average value and the weekly average value do not have to use the same value, but different values ​​can be used.

[0110] As described above, in the lifestyle pattern determination system 100 according to this embodiment, A power sensor 110 (behavior detection unit) capable of continuously detecting the usage status of equipment installed in a house 1 (building) used by a subject P1, and thereby detecting the behavior of the subject P1; a server 120 (data creation unit) that creates learned behavior data related to the behavior of the subject P1 by learning measurement data (detection results) from the power sensor 110 (behavior detection unit); a server 120 (condition setting unit) that sets conditions for the creation of the learned behavior data by the server 120 (data creation unit) so that the learned behavior data does not deviate from the actual behavior pattern of the subject P1; It is equipped with the following.

[0111] In addition, a behavior detection step of detecting the behavior of the subject P1 by continuously detecting the usage status of the equipment installed in the house 1 (building) used by the subject P1; a data creation process for creating learned behavior data related to the behavior of the subject P1 by learning the measurement data (detection results) in the behavior detection process; a condition setting step of setting conditions for creating the learning behavior data in the data creation step so that the learning behavior data does not deviate from the actual behavior pattern of the subject P1; It is equipped with the following.

[0112] With this configuration, it is possible to create learning behavior data that is in line with the actual behavior patterns of the subject P1.

[0113] Furthermore, in the lifestyle pattern determination system 100, The server 120 (condition setting unit) One of the conditions is: When the power sensor 110 (behavior detection unit) detects the use of the equipment for the first time, the server 120 (data creation unit) starts learning (step S105).

[0114] With this configuration, learning can be started at an appropriate timing for each target home appliance, and learning behavior data can be created that matches the actual behavior patterns of the target person P1.

[0115] Furthermore, in the lifestyle pattern determination system 100, The server 120 (data creation unit) Based on the measurement data (detection results) from the power sensor 110 (behavior detection unit), it is possible to create actual behavior data regarding the behavior of the subject P1, and to evaluate the comparison result of the actual behavior data with the learned behavior data (step S206). The server 120 (condition setting unit) One of the conditions is: If the comparison result is evaluated to be outside the predetermined acceptable range, a learning necessity determination process is executed to determine whether or not the corresponding detection result (unlearned data), which is the detection result corresponding to the execution behavior data, needs to be learned (steps S209 and S301).

[0116] With this configuration, it is possible to prevent measurement data that should not be learned from being learned, and to create learned behavior data that is in line with the actual behavior pattern of the subject P1.

[0117] Furthermore, in the lifestyle pattern determination system 100, The server 120 (condition setting unit) In the process of determining whether or not the child needs to study, a request for feedback regarding whether or not the child needs to study the corresponding detection result is sent to a predetermined notification unit (for example, a device portable by family member P2), and a decision is made as to whether or not the child needs to study the corresponding detection result based on the received feedback (steps S302, S303, and S307).

[0118] With this configuration, it is possible to learn the measurement data in response to feedback, and to create learned behavior data that matches the actual behavior patterns of the subject P1.

[0119] Furthermore, in the lifestyle pattern determination system 100, The server 120 (condition setting unit) In the learning necessity determination process, if the corresponding detection result indicates that learning is not necessary, a determination is made as to whether the learning necessity determination process should be executed the next time a detection result with the same content as the corresponding detection result is detected (step S305).

[0120] With this configuration, it is possible to prevent repeated requests for feedback on measurement data that does not require confirmation of the need for learning from family member P2, for example.

[0121] Furthermore, in the lifestyle pattern determination system 100, The server 120 (data creation unit) The comparison result of the executive behavior data with the learning behavior data can be evaluated for at least two or more periods (daily, weekly, and monthly) that are different from each other; An average value relating to the use of the target home appliance (equipment) is calculated for each period, and evaluation is performed for each period among the multiple periods in which the calculated average value satisfies a predetermined threshold value.

[0122] With this configuration, it is possible to determine the evaluation period (the timing at which evaluation is performed), thereby improving the accuracy of the determination results.

[0123] Furthermore, in the lifestyle pattern determination system 100, The facility includes a plurality of home appliances; The server 120 (condition setting unit) sets the conditions for each of the plurality of home appliances.

[0124] With this configuration, it is possible to create more accurate learning behavior data that is in line with the actual behavior patterns of the subject P1.

[0125] The lifestyle pattern determination system 100 according to this embodiment is one embodiment of a learning system. The house 1 according to this embodiment is one embodiment of a building according to the present invention. The power sensor 110 according to this embodiment is an embodiment of a behavior detection unit according to the present invention. The server 120 according to this embodiment is an embodiment of a data creation unit and a condition setting unit according to the present invention.

[0126] For example, the lifestyle pattern determination system 100 according to this embodiment has been described with reference to an example in which an elderly person is the subject P1, but the present invention is not limited to elderly people, and various people can be the subject P1.

[0127] Furthermore, in this embodiment, the power sensor 110 (behavior detection unit) is installed in the residence 1, but the present invention is not limited to this, and the power sensor 110 (behavior detection unit) can be installed in various buildings used by the subject P1. In other words, it is possible to detect abnormalities in cognitive function not only in the residence 1, but also in various other buildings, facilities, etc. Furthermore, the behavior detection unit is not limited to a power sensor, and various sensors capable of detecting human behavior can be used. Specifically, the behavior detection unit can be a human presence sensor, a recognition means capable of recognizing human behavior from captured images, or the like.

[0128] In this embodiment, the server 120 (such as a virtual server on a cloud) performs various processes, but the present invention is not limited to this, and the entity that performs the various processes can be changed as desired. For example, the processes can be performed by a home server, a personal computer, a portable terminal, or the like, installed in the house 1.

[0129] Furthermore, in the present embodiment, an example has been shown in which, when an abnormality in the cognitive function of the subject P1 is detected, the terminal 130 is notified of this fact, but it is also possible to configure the family member P2 or the like to confirm the abnormality and, if they determine that there is no problem (that there is no abnormality), to communicate this fact to the server 120 using the terminal 130 or the like. In this way, by the family member P2 or the like confirming the presence or absence of an abnormality and providing feedback to the server 120, the server 120 can learn the behavior of the subject P1 more accurately. This allows for more accurate detection of abnormalities in cognitive function.

[0130] Furthermore, the period covered by each process (daily process, weekly process, monthly process, weekly result notification, and monthly result notification) exemplified in this embodiment can be changed arbitrarily.

[0131] In addition, although the present embodiment is intended to detect the presence or absence of abnormalities in cognitive function, the present invention is not limited to this and can also detect the presence or absence of abnormalities in lifestyle patterns. For example, when the device is installed in the home of a person who is away from their family, such as a person who is working away from home or a student living alone, it can detect the presence or absence of abnormalities in the lifestyle patterns of distant family members. [Explanation of symbols]

[0132] 100 Lifestyle Pattern Judgment System 110 Power Sensor 120 servers 130 terminals

Claims

1. a behavior detection unit that can continuously detect the usage status of equipment installed in a building used by a subject person, thereby detecting the behavior of the subject person; a data creation unit that creates learned behavior data related to the behavior of the subject by learning the detection result by the behavior detection unit; a condition setting unit that sets conditions for the creation of the learning behavior data by the data creation unit so that the learning behavior data does not deviate from the actual behavior pattern of the subject; Equipped with The data creation unit The action detection unit is capable of generating action data relating to the action of the subject based on the detection result, and is capable of evaluating a comparison result of the action data with the learned action data; a comparison result between the active behavior data and the learned behavior data can be evaluated for at least two or more periods having different durations; calculating an average value for the use of the equipment in each period, and performing an evaluation for each period among the plurality of periods in which the calculated average value satisfies a predetermined threshold value; Learning system.

2. The condition setting unit One of the conditions is: when the behavior detection unit detects use of the facility for the first time, the data creation unit starts learning. The learning system of claim 1 .

3. The condition setting unit: One of the conditions is: If the comparison result is evaluated to be outside a predetermined allowable range, a learning necessity determination process is executed to determine whether learning is necessary for the corresponding detection result, which is the detection result corresponding to the executive movement data. The learning system according to claim 1 or 2.

4. The condition setting unit In the learning necessity determination process, a request for feedback regarding the learning necessity of the correspondence detection result is notified to a predetermined notification unit, and the learning necessity of the correspondence detection result is determined according to the obtained feedback. The learning system according to claim 3 .

5. The condition setting unit In the learning necessity determination process, if the correspondence detection result indicates that learning is not necessary, a determination is made as to whether the learning necessity determination process should be executed when a detection result having the same content as the correspondence detection result is detected next time. The learning system according to claim 3 or 4.

6. The equipment includes a plurality of home appliances, the condition setting unit sets the condition for each of the plurality of home appliances. A learning system according to any one of claims 1 to 5.

Images