JP7085750B2 - Lifestyle analysis system, lifestyle analysis method and program - Google Patents

Description

This disclosure relates to a lifestyle-related analysis system, a lifestyle-related analysis method and a program.

In recent years, the lonely death of the elderly has become a problem in Japan. In order to prevent such lonely death, long-term care service providers and their families are required to watch over whether there are any abnormalities in the lives of the elderly. In addition, families who are worried about the lives of college students living alone are required to watch over whether there are any abnormalities in the lives of the college students.

In order to meet such demands, a monitoring support system has been proposed that can monitor the safety and lifestyle of a person living alone from a remote location. For example, in Patent Document 1, the monitoring device installed in the management center acquires the power consumption consumed by the entire electric equipment used in the consumer's home, and the usage status of each electric equipment is obtained from the power consumption. It is disclosed to presume and monitor the living conditions of consumers.

Japanese Unexamined Patent Publication No. 2012-678774

The monitoring support system disclosed in Patent Document 1 monitors the living conditions of consumers only from the amount of electricity consumed. However, in order to comprehensively monitor the living conditions, activities not related to power consumption should be considered. In that case, it is necessary to acquire measurement data other than the electric energy, but such a configuration complicates the processing and system configuration because various measurement data are mixed.

In this respect, even if the sensor data for grasping the living situation is various measurement data, it is possible to increase the versatility by standardizing and using them. It should be noted that standardization can be realized, for example, by unifying the unit and format of the sensor data.

Therefore, in view of such circumstances, it is an object of the present disclosure to provide a lifestyle-related analysis system or the like capable of standardizing sensor data for grasping a living situation and improving versatility.

In order to achieve the above object, the lifestyle analysis system according to the first aspect of the present disclosure includes an information transmission device arranged in a living space and a server device that communicates with the information transmission device via a network. In the lifestyle analysis system, the sensor data acquisition unit that acquires time-series sensor data and the timing when the amount of change in the sensor data is greater than or equal to a predetermined value are recognized as event occurrences based on user behavior, and the timing of event occurrence A binarized data generator that generates binarized data that indicates whether or not it is before and after time, and a reference data generator that generates reference data that aggregates the binarized data over a predetermined number of days. , It is characterized by providing.

Further, in order to achieve the above object, the lifestyle analysis method according to the second aspect of the present disclosure includes a sensor data acquisition step for acquiring time-series sensor data and a timing at which the amount of change in the sensor data is equal to or greater than a predetermined value. Is recognized as an event occurrence based on user behavior, and a binarized data generation step for generating binarized data indicating whether or not the time is before or after the event occurrence timing and the binarized data are predetermined. It is characterized by including a reference data generation step for generating reference data aggregated over the number of days.

Further, in order to achieve the above object, the program according to the third aspect of the present disclosure sets the computer as a sensor data acquisition means for acquiring time-series sensor data, and a timing at which the amount of change in the sensor data is equal to or more than a predetermined value. A binarized data generation means that recognizes an event occurrence based on user behavior and generates binarized data that indicates whether or not it is the time before or after the event occurrence timing, and the binarized data for a predetermined number of days. It functions as a reference data generation means for generating reference data aggregated over the crossing.

According to the present disclosure, it is possible to provide a lifestyle-related analysis system or the like capable of standardizing sensor data for grasping a living situation and improving versatility.

It is a block diagram which shows the structural example of the lifestyle analysis system which concerns on embodiment. It is a block diagram which shows the structural example of the information transmission apparatus which concerns on embodiment. It is a block diagram which shows the configuration example of the server apparatus which concerns on embodiment. It is a conceptual diagram which shows an example of the generation method of binarized data. It is a conceptual diagram which shows an example of the generation method of a reference data. It is a figure which shows the 1st example of the output lifestyle-related graph. It is a figure which shows the 2nd example of the output lifestyle-related graph. It is a conceptual diagram which shows an example of the method of abnormality discrimination. It is a figure which shows an example of the abnormality discrimination result at the time of discriminating by time zone. It is a figure which shows the 1st example of the abnormality discrimination result in the case of discriminating in a single time. It is a figure which shows the 2nd example of the abnormality discrimination result at the time of discrimination in a single time. It is a flowchart which shows an example of the operation of the lifestyle-related analysis system which concerns on embodiment.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The embodiments described below do not unreasonably limit the contents of the present disclosure described in the claims. Also, not all of the components shown in the embodiments are essential components of the present disclosure.

(Embodiment)
As shown in FIG. 1, the lifestyle analysis system 1 according to the present embodiment is a server device that communicates with one or more information transmission devices 100 arranged in a living space and an information transmission device 100 via a network NW. It is equipped with 200. The network NW is composed of WAN (World Area Network), LAN (Local Area Network) and the like.

The lifestyle-related analysis system 1 provides a service for analyzing the lifestyle-related habits of consumers living in a living space and determining whether or not there is an abnormality in the living conditions of the consumers. The living space is, for example, a space within the range of living activities in a house where a consumer lives, a facility where a consumer lives, a hospital where a consumer is hospitalized, and the like.

The information transmission device 100 is arranged for each living space. The information transmission device 100 acquires sensor data from various sensors arranged in the living space. The sensor data may be, for example, a measured value of electric power, temperature, humidity, brightness, or the like, or may be an output signal of a motion sensor, a door sensor, or the like. The sensor data may be any data that can be used to grasp the living situation.

The information transmission device 100 transmits information based on the acquired sensor data to the server device 200. In the present embodiment, the information based on the acquired sensor data is the sensor data itself. However, the information based on the acquired sensor data may be binarized data or reference data. The binarization data and the reference data will be described later.

The information transmission device 100 communicates using the unique identification information set in the own device. As a result, the server device 200 identifies each of the one or more information transmission devices 100.

The server device 200 is managed by a business operator that provides a service for monitoring the living conditions of consumers. The business operator that provides this service may be, for example, a business operator that provides a long-term care service that monitors the life of an elderly person living alone, or a business operator that provides a service that monitors the life of a student living alone. It may be. The business operator that provides this service may be a service provider or a facility manager who watches over the lives of the residents of the facility.

<Configuration of information transmission device>
Hereinafter, the configuration of the information transmission device 100 will be described in detail. As shown in FIG. 2, the information transmission device 100 includes a communication unit 110 that communicates with other devices, a storage unit 120 that stores various data, and a control unit 130 that controls the entire device. These components are interconnected by a bus line BL.

The communication unit 110 is a communication interface including a NIC (Network Interface Card controller) for performing wired communication or wireless communication. The communication unit 110 communicates with the server device 200 via the network NW and transmits sensor data. Further, the communication unit 110 communicates with various sensors arranged in the living space and receives the sensor data.

The storage unit 120 is composed of a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. The storage unit 120 stores programs, various data, and the like for executing various control processes.

The control unit 130 is composed of a CPU (Central Processing Unit) and the like. The control unit 130 controls the overall operation of the information transmission device 100 by executing the program stored in the storage unit 120.

Hereinafter, the functional configuration of the control unit 130 will be described. The control unit 130 functions as a sensor data acquisition unit 131, a binarized data generation unit 232, and an information transmission unit 132.

The sensor data acquisition unit 131 acquires time-series sensor data from various sensors via the communication unit 110.

The information transmission unit 132 transmits information based on the acquired sensor data to the server device 200 via the communication unit 110. In this embodiment, the information based on the acquired sensor data is the sensor data.

<Server device configuration>
Hereinafter, the configuration of the server device 200 will be described in detail. As shown in FIG. 3, the server device 200 includes a communication unit 210 that communicates with other devices, a storage unit 220 that stores various data, and a control unit 230 that controls the entire device. These components are interconnected by a bus line BL.

The communication unit 210 is a communication interface including a NIC for performing wired communication or wireless communication. The communication unit 210 communicates with the information transmission device 100 via the network NW.

The storage unit 220 is composed of a RAM, a ROM, and the like. The storage unit 220 stores programs, various data, and the like for executing various control processes.

The control unit 230 is composed of a CPU and the like. The control unit 230 controls the overall operation of the server device 200 by executing the program stored in the storage unit 220.

Hereinafter, the functional configuration of the control unit 230 will be described. The control unit 230 functions as an information receiving unit 231, a binarized data generation unit 232, a reference data generation unit 233, a graph output unit 234, and an abnormality determination unit 235.

The information receiving unit 231 receives information (sensor data) based on sensor data from the information transmitting device 100 via the communication unit 210.

The binarized data generation unit 232 recognizes the timing at which the change amount of the sensor data received by the information receiving unit 231 is equal to or greater than a predetermined value as an event occurrence based on the user behavior. The predetermined value is, for example, 300 W if the sensor data is a measured value of electric power. The binarized data generation unit 232 generates binarized data indicating whether or not the time is before or after the recognized event occurrence timing.

For example, the binarized data is time series data indicating 1 or 0. However, the binarized data may be data that indicates whether or not the time is before or after the recognized event occurrence timing. Therefore, the binary value may be another value. For example, the binarized data may be time-series data indicating 5 or 0, or may be binary number or encoded time-series data.

The reference data generation unit 233 generates the reference data obtained by aggregating the binarization data generated by the binarization data generation unit 232 over a predetermined number of days. The reference data is, for example, data normalized by integrating (adding) binarized data for a predetermined number of days and dividing by the predetermined number of days. The predetermined number of days is set to, for example, about 2 to 4 weeks. It should be noted that the predetermined number of days may be set longer or shorter as long as the number of days is such that the lifestyle can be grasped.

The graph output unit 234 outputs a lifestyle-related graph based on the reference data generated by the reference data generation unit 233. The output lifestyle-related graph may be displayed on the display device via the communication unit 110, or may be distributed to the communication terminal of the user (for example, the family of the consumer). The lifestyle graph may be analyzed by the user or by the service provider. By displaying the lifestyle habit graph in this way, it is possible to visualize the lifestyle habit.

The abnormality determination unit 235 determines an abnormality in the life of a consumer in the living space. The sensor data acquisition unit 131 of the information transmission device 100 acquires new sensor data after the reference data generation unit 233 of the server device 200 generates the reference data. The information transmission unit 132 transmits information based on this new sensor data to the server device 200. The information receiving unit 231 of the server device 200 receives this.

The abnormality determination unit 235 determines an abnormality by comparing the information based on the new sensor data with the reference data generated by the reference data generation unit 233. In the present embodiment, the information based on the new sensor data is the new binarized data received from the information transmission device 100. However, the information based on the new sensor data may be the new sensor data received from the information transmission device 100, or may be the time before and after the event occurrence timing recognized based on the new sensor data. good. A specific example of the abnormality determination method will be described later.

<Specific examples of binarization data and reference data>
Hereinafter, specific examples of binarization data and reference data will be described.

FIG. 4 is a conceptual diagram showing an example of a method of generating binarized data. In this example, the sensor data is a measured value of power every minute. The binarization data generation unit 232 recognizes the timing at which the amount of change in these measured values is 300 W or more as compared with the immediately preceding measured value as an event occurrence based on the user behavior.

As shown in FIG. 4, the data recognized as an event occurrence is flagged as 1. Centering on the data for which the flag of 1 is set, the flag of 1 is also set for the data for 45 minutes (before and after time) before and after (see FIG. 5 to be described later). By such processing, binarization data is generated. For example, when the data of 8:48, 8:49, and 9:02 are flagged as the event occurrence timing as shown in FIG. 4, 1 hour and 44 minutes from 8:03 to 9:47 is the front-back time. ..

FIG. 5 is a conceptual diagram showing an example of a method for generating reference data. The reference data generation unit 233 adds, for example, binarized data for two weeks. As a result, as shown in FIG. 5, time-series data for one day is generated with a value in the range of 0 to 14. The reference data generation unit 233 generates reference data by normalizing such data by dividing it by the number of days to be added (that is, 14 days). In this case, the reference data is one day's worth of time series data represented by a value in the range of 0 to 1. In FIG. 5, for convenience of illustration, the sensor data is displayed at 5-minute intervals, but the sensor data is actually at 1-minute intervals.

FIG. 6 is a diagram showing a first example of the output lifestyle-related graph. This example is a graph of the reference data generated by the reference data generation unit 233 when the sensor data is a measured value of electric power. In this lifestyle graph, the horizontal axis is time and the vertical axis is the value of the reference data.

FIG. 7 is a diagram showing a second example of the output lifestyle-related graph. This example is a graph of the reference data generated by the reference data generation unit 233 when the sensor data is not a measured value of electric power but a detection result of a motion sensor or a door sensor. In this lifestyle graph, the horizontal axis is time and the vertical axis is the value of the reference data. The method of generating the reference data in this example is basically the same as in the case of the first example.

For example, the binarization data generation unit 232 recognizes the on / off switching timing of the detection signal of the motion sensor or the door sensor as an event occurrence based on the user behavior. The reference data generation unit 233 generates the reference data by adding the binarized data for a predetermined number of days (for example, for two weeks) and dividing by the number of days. The graph output unit 234 outputs the lifestyle-related graph shown in FIG. 7 by graphing the reference data.

<Specific example of abnormality discrimination method>
Hereinafter, a specific example of the abnormality determination method using the reference data by the abnormality determination unit 235 will be described. There are two methods for determining an abnormality.

The first method is a method of discriminating based on the difference between the reference data and the binarized data based on the new sensor data at the same time as the reference data. For example, in the lifestyle graph shown in FIG. 6, the value of the reference data is 0 at 5:00. If the binarized data based on the new sensor data at this timing is 1, it can be determined as an abnormality at that time. That is, it is determined as an abnormality at the timing when there is a large difference between the reference data and the new binarized data. A predetermined reference value (for example, 0.5) is set as a criterion for discriminating a large difference between the reference data and the binarized data.

The second method is a method of determining an abnormality by taking a bird's-eye view of the entire fixed time after a certain period of time has elapsed. In this method, the reference data is integrated according to a predetermined condition, and the abnormality is discriminated from the integration result. Hereinafter, a specific example of the second method will be described in detail.

FIG. 8 is a conceptual diagram showing an example of a method for determining an abnormality. In the lifestyle graph, the abnormality determination unit 235 sets the difference between the reference data and one of the binary values along the time in the time before and after the event occurrence timing recognized from the new sensor data (for example, 45 minutes before and after). To integrate. In this embodiment, one of the binary values is 0.

The abnormality determination unit 235 integrates the difference between the reference data and the other of the binary values along the time at a time other than the time before and after the new sensor data is recognized in the lifestyle graph. In this embodiment, the other of the binary values is 1. In FIG. 8, the integration result corresponds to the area indicated by the diagonal line between the lifestyle graph and 0 or 1. Section A and section B are time before and after, and section C is time that is not time before and after.

In this way, the value of the reference data is integrated as it is at the time before and after the event occurs, and the difference (absolute value) between the value of the reference data and 1 is integrated at other times. When the sum of the integrated values is smaller than the discrimination reference value, the abnormality discriminating unit 235 determines that there is an abnormality in the life of the consumer as abnormal data not in line with the lifestyle.

The significance of such a discrimination method will be described. First, if there is an event in a time zone where the reference data is large (a time zone close to 1), the area below the reference data becomes large. In this case, it can be said that it is customary because the event usually occurs at a certain time zone.

On the other hand, if there is no event in the time zone where the reference data is large (time zone close to 1), the area above the reference data becomes small. In this case, it can be said that it is abnormal because the event does not usually occur at a certain time zone.

If there is an event in a time zone where the reference data is small (a time zone close to 0), the area below the reference data becomes smaller. In this case, it can be said that it is abnormal because the event usually occurs in the time zone when there is no event.

On the other hand, if there is no event in the time zone where the reference data is small (time zone close to 0), the area above the reference data becomes large. In this case, it can be said that it is customary because the event does not usually occur during the time when there is no event.

In this way, it can be said that the larger the area of the integration result, the more habitual it is. Therefore, it is possible to determine whether or not it is habitual according to the integration result.

The integration range of the reference data may be a short section such as one hour unit or five minute unit instead of one day, or may be a time zone unit of several hours such as a day shift zone or a midnight time zone. The integration result may be calculated by taking an average value and using a value in the range of 0 to 1.

For example, if one day is classified by time zone, there is a unique lifestyle pattern for each time zone. This is because lifestyle-related habits include regularity such as getting up, going out, returning home, going to bed, and eating. Therefore, for example, one day may be classified into six time zones, and the abnormality determination unit 235 may calculate the integration result for each time zone. The six time zones are, for example, midnight from 0 to 4 o'clock, early morning from 4 o'clock to 7 o'clock, morning from 7 o'clock to 12 o'clock, noon from 12 o'clock to 16 o'clock, evening from 16 o'clock to 19 o'clock, 19 o'clock to 19 o'clock. 24:00 may be classified as night.

FIG. 9 is a diagram showing an example of an abnormality discrimination result when discrimination is performed by time zone. In this example, the results of integrating the reference data in the daytime and nighttime zones when classified as described above are averaged and shown as values in the range of 0 to 1. In addition, in order to grasp the tendency for several days, the value of the daily integration result of 1/1 to 1/6 is shown. In this discrimination result, a value close to 1 is close to normal, and a value close to 0 is close to abnormal.

Lifestyles can also be discriminated from such discrimination results. For example, this consumer is usually not at home during the day but is often at home at night. However, at 1/1 and 1/2, the high value is close to normal in the daytime, but the low value is close to abnormal at night. Therefore, in 1/1 and 1/2, it is determined that the consumer is not at home day or night, and is determined to be absent all day. On the other hand, at 1/4 and 1/6, the values are low, which is close to abnormal in the daytime. Therefore, 1/4 and 1/6 are different from normal, and it is determined that they are at home even though it is daytime.

FIG. 10 is a diagram showing a first example of an abnormality discrimination result when discrimination is performed in a single time. In this figure, when the power measurement value is sensor data, the vertical line indicates the event occurrence timing recognized from the newly acquired sensor data for the lifestyle graph generated based on the reference data. Has been done. The reference data is, for example, data aggregated in a period of 1/1 to 1/7, and the newly acquired sensor data is the sensor data acquired in 1/8. A single time is a short time, for example 5 minutes. For example, if there is a vertical line at 3:30, which is the timing when the value of the reference data is close to zero, it is determined to be abnormal.

FIG. 11 is a diagram showing a second example of the abnormality discrimination result in the case of discrimination in a single time (short time). In this figure, when the detection result of the motion sensor is sensor data, the event occurrence timing (person) recognized from the newly acquired sensor data for the lifestyle graph generated based on the reference data. The on / off switching timing of the motion sensor) is indicated by a vertical line. A single time is a short time, for example 5 minutes. For example, if there is a vertical line at 3:30 or 12:05 when the value of the reference data is close to zero, it is determined to be abnormal.

<Processing flow>
Hereinafter, an example of the operation of the lifestyle-related analysis system 1 will be described with reference to FIG. 12. Here, control processing related to generation of reference data and abnormality discrimination will be described.

First, the information transmission device 100 acquires sensor data from various sensors (step S101). The information transmission device 100 transmits information based on the sensor data to the server device 200 (step S102). It should be noted that this information transmission may be repeatedly executed a plurality of times until the reference data is generated, or may be executed once after the binarized data is generated until the period in which the reference data is generated.

The server device 200 receives information (sensor data) based on the sensor data (step S105). The server device 200 generates binarized data based on the acquired sensor data (step S106). The server device 200 generates reference data based on the acquired binarization data (step S107).

The information transmission device 100 acquires new sensor data even after transmitting the sensor data for generating the reference data to the server device 200 (step S103). The information transmission device 100 transmits information based on the new sensor data (new sensor data) to the server device 200 (step S104).

The server device 200 receives information based on the new sensor data (step S108). The server device 200 generates binarized data based on the acquired new sensor data (step S109). The server device 200 performs abnormality determination by comparing the acquired binarized data with the reference data (step S110).

<Explanation of effect>
The lifestyle analysis system 1 according to the present embodiment recognizes the timing at which the amount of change in the sensor data is equal to or greater than a predetermined value as an event occurrence based on the user behavior, and determines whether or not the time is before or after the event occurrence timing as a binary value. Generate the binarized data shown. According to the lifestyle analysis system 1, even if the sensor data for grasping the living situation is various measurement data, the binarized data obtained by binarizing them is used for lifestyle analysis and abnormality discrimination. ..

In this case, since binarized data that does not depend on each unit or format of the sensor data is used, it is possible to increase the versatility. In the lifestyle analysis system 1, the sensor data may be measurement data other than the electric energy amount, and various measurement data can be applied. Since the reference data obtained by aggregating the binarized data is also a value in the range of 0 to 1, it can be used regardless of the unit and format of the sensor data. Therefore, according to the lifestyle-related analysis system 1, it is possible to standardize the sensor data for grasping the living situation and improve the versatility.

This is the end of the description of the embodiment, but the above embodiment is only an example. Therefore, the specific configuration, operation content, and the like of the lifestyle-related analysis system 1 are not limited to those described in the above embodiment. Hereinafter, a modified example of the above embodiment will be described.

(Modification example)
In the above embodiment, the flow of processing has been described as an example. However, the processing flow is not limited to that described in the above embodiment. The order and contents of processing can be changed as appropriate.

In the above embodiment, the information transmission device 100 is configured to transmit the acquired sensor data to the server device 200. In this case, the server device 200 includes the binarization data generation unit 232 and executes the generation of the binarization data based on the received sensor data. However, each function of the lifestyle-related analysis system 1 is not limited to such division.

For example, the information transmission device 100 may be configured to acquire sensor data and generate binarized data. The server device 200 may generate reference data based on the binarized data received from the information transmission device 100, output a lifestyle graph, and execute subsequent abnormality determination.

The information transmission device 100 includes one or more of a binarized data generation unit 232, a reference data generation unit 233, a graph output unit 234, an abnormality determination unit 235, and the like, and the information transmission device 100 executes most of the processing. It may be. For example, the information transmission device 100 may transmit information on the determination result indicating that there is an abnormality in the living condition of the consumer to the server device 200 at the monitoring base and notify the person in charge of the nursing care service or the like. The information transmission device 100 may output a lifestyle-related graph and allow consumers to view it.

In this way, the functions may be concentrated on the information transmission device 100, or the functions may be concentrated on the server device 200. However, in order to reduce the amount of communication between the information transmission device 100 and the server device 200 and the number of communications, the information transmission device 100 is not configured to transmit sensor data (raw data) to the server device 200, but the information transmission device 100 It is preferable to transmit binarized data, reference data, etc. (processed data) to the server device 200. This makes it possible to standardize communication data.

In the above embodiment, the sensor data acquisition unit 131 acquires sensor data from each of the plurality of sensors, and the binarization data generation unit 232 and the reference data generation unit 233 each of the plurality of sensor data are binarized data. And reference data may be generated. The abnormality determination unit 235 may determine an abnormality by combining the binarized data and the reference data of the plurality of sensor data.

The binarized data generation unit 232 may generate binarized data by performing a logical operation on the sensor data acquired from each of the plurality of sensors. In this case, the binarized data generation unit 232 combines a plurality of sensor data and performs logical operations such as AND and OR to generate the binarized data.

For example, when the motion sensor near the washing machine detects a person and then the washing machine is switched on, it may be recognized that an event has occurred and binarized data may be generated. When the opening / closing of the refrigerator or the on / off of the cooking utensil is detected after the motion sensor in the kitchen detects a person, it may be recognized that an event has occurred and binarized data may be generated. The various sensors may be combined with a door open / close sensor, a button sensor, a room illuminance sensor, and the like. As described above, according to the configuration in which a plurality of sensor data are combined and logically calculated, it is possible to detect the living condition of the consumer in detail and improve the accuracy of abnormality discrimination.

Further, the lifestyle-related analysis system according to the present disclosure may realize its function by, for example, a computer executing a program, regardless of the above-mentioned device. The programs for realizing the functions of the lifestyle analysis system are computers such as USB (Universal Serial Bus) memory, CD-ROM (Compact Disc-Read Only Memory), DVD (Digital Versatile Disc), and HDD (Hard Disc Drive). It may be stored on a readable recording medium or downloaded to a computer via a network.

Although the preferred embodiments of the present disclosure have been described above, the present disclosure is not limited to such specific embodiments, and the present disclosure includes the inventions described in the claims and the equivalent scope thereof. Is done. Further, the configurations of the devices described in the above-described embodiments and modifications can be appropriately combined as long as there is no technical contradiction.

1 ... lifestyle analysis system, 100 ... information transmission device, 200 ... server device, 300 ... communication terminal, 110, 210 ... communication unit, 120, 220 ... storage unit, 130, 230 ... control unit, 131 ... sensor data acquisition unit , 132 ... Information transmission unit, 231 ... Information reception unit, 232 ... Binarized data generation unit, 233 ... Reference data generation unit, 234 ... Graph output unit, 235 ... Abnormality determination unit

Claims (8)

Information transmission devices installed in houses and
A server device that communicates with the information transmission device via a network,
It is a lifestyle-related analysis system equipped with
A sensor data acquisition unit that acquires time-series sensor data,
The timing at which the amount of change in the sensor data is equal to or greater than a predetermined value is recognized as an event occurrence based on the user behavior, binarized data indicating the timing of the event occurrence in binary is generated, and the timing of the event occurrence is the center. A binarized data generation unit that generates binarized data having the same value as the timing of the event occurrence for a predetermined time before and after the event .
A reference data generation unit that generates reference data obtained by aggregating the binarized data over a predetermined number of days, and
A lifestyle-related analysis system characterized by being equipped with. It is equipped with an abnormality discriminating unit that discriminates abnormalities in the lives of the residents of the house.
The sensor data acquisition unit is
After generating the reference data, the new sensor data is acquired, and
The abnormality determination unit is
The abnormality is discriminated by comparing the information based on the new sensor data with the reference data.
The lifestyle-related analysis system according to claim 1, wherein the lifestyle-related analysis system is characterized in that. A graph output unit that outputs a lifestyle graph based on the reference data is provided.
The lifestyle-related analysis system according to claim 2, wherein the lifestyle-related analysis system is characterized in that. The abnormality determination unit is
In the time before and after the time recognized from the information based on the new sensor data in the lifestyle graph, the difference between the reference data and one of the two values is integrated over time.
In the lifestyle graph, at a time other than the time before and after the time recognized from the information based on the new sensor data, the difference between the reference data and the other of the binary values is integrated over time.
When the sum of the integrated values is smaller than the discrimination reference value, it is determined that there is an abnormality in the life of the resident as abnormal data not in line with the lifestyle.
The lifestyle-related analysis system according to claim 3, wherein the lifestyle-related analysis system is characterized in that. The sensor data acquisition unit acquires the sensor data from each of the plurality of sensors, and obtains the sensor data.
The binarized data generation unit and the reference data generation unit generate the binarization data and the reference data for each of the plurality of sensor data.
The abnormality discriminating unit discriminates the abnormality by combining the binarized data and the reference data of each of the plurality of sensor data.
The lifestyle-related analysis system according to claim 4, wherein the lifestyle-related analysis system is characterized in that. The binarized data generation unit generates the binarized data by performing a logical operation on the sensor data acquired from each of the plurality of sensors.
The lifestyle-related analysis system according to any one of claims 1 to 5, wherein the lifestyle-related analysis system is characterized in that. It is a lifestyle-related analysis method to be executed by a computer equipped with a control unit and a storage unit.
In the lifestyle-related analysis method, the control unit
Sensor data acquisition step to acquire time series sensor data,
The timing at which the amount of change in the sensor data is equal to or greater than a predetermined value is recognized as an event occurrence based on the user behavior, binarized data indicating the timing of the event occurrence in binary is generated, and the timing of the event occurrence is the center. A binarization data generation step that generates binarized data having the same value as the timing of the event occurrence for a predetermined time before and after the event .
A reference data generation step for generating reference data obtained by aggregating the binarized data over a predetermined number of days, and
A lifestyle-related analysis method characterized by performing steps that include. Computer,
Sensor data acquisition means for acquiring time-series sensor data,
The timing at which the amount of change in the sensor data is equal to or greater than a predetermined value is recognized as an event occurrence based on the user behavior, binarized data indicating the timing of the event occurrence in binary is generated, and the timing of the event occurrence is the center. A binarized data generation means that generates binarized data having the same value as the timing of the event occurrence for a predetermined time before and after the event .
A reference data generation means for generating reference data obtained by aggregating the binarized data over a predetermined number of days.
A program to function as.

Images