Human life traceability device and improvement proposal support method

Abstract

To provide a human life traceability device and an improvement plan proposal support device that propose an improvement plan such as for improving a health state, such as a living behavior of a person to be analyzed.SOLUTION: A human life traceability device 10 for analyzing a behavior of a person 2 to be analyzed includes: a storage unit 19 that stores living behavior information that is time-series data indicating a living behavior of the person to be analyzed, and activity amount information that is time-series data indicating an activity amount of the person 2 to be analyzed both based on sensor data for the person 2 to be analyzed; a detection unit 14 that detects an activity change satisfying a predetermined condition on the basis of the activity amount information; a comparison unit 15 that, when the activity change is detected, compares pieces of information on a living behavior corresponding to the living behavior information in a period having a predetermined relationship with timing at which the activity change occurs, and identifies information on a living behavior in which a change in living behavior satisfying the prescribed condition occurs; and an improvement plan estimation unit 17 that estimates an improvement plan for a living behavior on the basis of the identified information on the living behavior.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] This invention relates to human life traceability, which manages and analyzes human behavior and activities. In particular, it relates to technology for managing human health conditions. [Background technology]

[0002] In recent years, advances in communication and sensor technologies have made it possible to measure human behavior and activity levels in daily life for the purpose of health management. For example, Patent Document 1 discloses a technology for determining whether or not there is a change in a life pattern based on walking data indicating the amount of activity. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-184168 A Summary of the Invention [Problem to be solved by the invention]

[0004] For health management, it is effective to detect changes in daily activities, including life patterns, but unlike activity levels, it is difficult to directly detect these changes using sensors, etc. For example, even if the amount or timing of meals changes, it may not be due to health reasons such as seasonal factors.

[0005] In addition, in Patent Document 1, the presence or absence of changes in lifestyle patterns is judged, but the changes are not fully analyzed. In human life traceability, including health management, detailed analysis of human activities such as daily activities can provide improvement proposals for improving health conditions, etc.

[0006] Here, an object of the present invention is to provide a technique that can analyze human activities in more detail. [Means for solving the problem]

[0007] In order to solve the above problem, the present invention detects a change in the amount of activity of a person to be analyzed, identifies a change in daily living behavior in, for example, a nearby period that corresponds to the detected change in the amount of activity, and estimates an improvement plan for the identified change in daily living behavior. More specifically, a human life traceability device that manages and analyzes the activities and behavior of a person to be analyzed includes a storage unit that stores daily living behavior information, which is time-series data showing the daily living behavior of the person to be analyzed, and activity amount information, which is time-series data showing the amount of activity of the person to be analyzed, based on sensor data of the person to be analyzed from a sensor, a detection unit that detects an activity change that satisfies a predetermined condition based on the activity amount information, and, when the activity change is detected, a timing that has a predetermined relationship with the timing at which the activity change occurred. subject period and a comparison period, and The present invention has a comparison unit that compares information on living activities corresponding to the living activity information and identifies information on living activities in which a living activity change that satisfies a predetermined condition has occurred as a result of the comparison, an improvement plan estimation unit that estimates an improvement plan for the living activity based on the identified information on the living activity, a change factor estimation unit that estimates a factor of the living activity change according to the identified information on the living activity, an activity feature amount calculation unit that calculates an activity feature amount indicating a feature of the activity amount information, and a living activity feature amount calculation unit that calculates a living activity feature amount indicating a feature of the living activity information, wherein the improvement plan estimation unit estimates an improvement plan for the living activity corresponding to the estimated factor of the living activity change, the detection unit detects an activity change in the activity feature amount, and the comparison unit detects the activity change in the activity feature amount. subject period and the comparison period This is a human life traceability device that compares daily activity features. The present invention also includes a method for supporting improvement proposals executed by the human life traceability device. Furthermore, the present invention also includes a program for causing the human life traceability device to function as a computer and a storage medium for storing the program. Effect of the Invention

[0008] According to the present invention, the activities of a person to be analyzed can be analyzed in more detail, thereby enabling more appropriate health management. [Brief description of the drawings]

[0009] [Figure 1] 1 is a block diagram showing the configuration of a human life traceability system in one embodiment of the present invention. FIG. [Diagram 2] This is a hardware configuration diagram of a human life traceability device in one embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram showing living activity information used in an embodiment of the present invention. [Figure 4] FIG. 11 is a diagram showing activity amount information used in one embodiment of the present invention. [Diagram 5] FIG. 2 is a diagram showing daily activity feature amounts used in an embodiment of the present invention. [Figure 6] FIG. 11 is a diagram showing an activity feature used in an embodiment of the present invention. [Figure 7] FIG. 13 is a diagram showing an index value correspondence table used in one embodiment of the present invention. [Figure 8] 1 is a flowchart showing a process flow in an embodiment of the present invention. [Figure 9] FIG. 13 is a diagram showing a display example according to an embodiment of the present invention. [Figure 10] FIG. 13 is a diagram for explaining the concept of processing according to a modified example of an embodiment of the present invention. [Figure 11] 13 is a flowchart showing the process flow of steps S6 and S7 in a modified example of the embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] An embodiment of the present invention will be described in detail below with reference to the drawings. However, the present invention is not limited to the following embodiment, and various modifications and application examples within the technical concept of the present invention are also included in its scope. <Configuration> Prior to the configuration of this embodiment, the applicable services and participants in this embodiment will be described. In this embodiment, the activities and behaviors of the subject of analysis 2 are detected regardless of whether they are inside the home 20 or outside the home, and the activities are analyzed based on the detection results. For this reason, in this embodiment, health-related services are available from insurance companies, day care providers, and the like. Health-related services include health management services and monitoring services by those who wish to be monitored or by relatives, and are services that analyze the activities and behaviors of the subject of analysis 2.

[0011] The subject of analysis 2 lives mainly in a home 20, such as his or her own home or workplace. Sensors are installed inside and outside the home 20, and the activities and behavior of the subject of analysis 2 are detected.

[0012] It is also desirable for the subject 2 to have a user terminal 23 that is used when receiving the above-mentioned services. It is also desirable for related parties such as relatives of the subject 2 to use the user terminals 31 and 32.

[0013] Furthermore, insurance companies and day care service providers are assumed to be providers of the services in this embodiment, and each of them will use a server for providing the services. Furthermore, a human life traceability device 10 is provided for the above-mentioned services.

[0014] The configuration of this embodiment will be described below. Fig. 1 is a block diagram showing the configuration of the human life traceability system in this embodiment. In this embodiment, a human life traceability device 10, an insurance company server 41 of an insurance company, and a day service provider server 51 of a day service provider are connected to each other via a network 60 such as the Internet. In addition, sensors and user terminals (23, 31, 32) that cooperate with these various devices are also connected to the network 60.

[0015] First, as described above, the sensors are installed inside and outside the house 20. Here, the sensors 21 can be classified into activity amount sensors 21-1 and 21-2 that detect the amount of activity of the subject 2, and daily living behavior sensors 22-1 and 22-2 that identify the daily living behavior of the subject 2.

[0016] The activity amount sensors 21-1, 21-2 can be realized by an activity meter or a camera using millimeter wave radar or microwaves. In other words, the activity amount sensors 21-1, 21-2 only need to be able to detect or identify the amount of activity of the subject 2, such as the moving speed, acceleration, and energy consumption, as sensor data (activity sensor data). The living behavior sensors 22-1, 22-2 can be realized by a human sensor, a sensor provided in a home appliance, or the like. In other words, the living behavior sensors 22-1, 22-2 only need to be able to detect sensor data (living behavior sensor data) that can identify the living behavior of the subject 2, such as sleeping, going out, eating, and housework.

[0017] The number of sensors is not limited to the number shown in the figure, and the types of sensors are not limited to those described above.

[0018] The human life traceability device 10 is a device that executes the main processing of this embodiment. Here, Fig. 1 shows the functional blocks of the human life traceability device 10. This human life traceability device 10 has, as each functional block, a behavior estimation unit 11, a behavior feature amount calculation unit 12, an activity feature amount calculation unit 13, a detection unit 14, a comparison unit 15, a change factor estimation unit 16, an improvement plan estimation unit 17, an input / output unit 18, and a memory unit 19.

[0019] First, the activity inferrer 11 creates living activity information 101 indicating the living activity of the analysis subject 2 based on the living activity sensor data. The living activity information 101 will be described in the "Information and Data" section. The activity inferrer 11 may create the living activity information 101 from information obtained by performing digital conversion or the like on the living activity sensor data, or may create the living activity information 101 from the living activity sensor data.

[0020] Moreover, the activity feature calculation unit 12 creates living activity feature 103 indicating features of the living activity information 101. The living activity feature 103 will also be described in the "information and data" section.

[0021] Furthermore, the activity feature amount calculation unit 13 creates an activity feature amount 104 indicating the feature of the activity amount information 102 indicating the activity amount of the analysis subject 2, which is the activity amount sensor data of the activity amount sensors 21-1 and 21-2. The activity amount information 102 and the activity feature amount 104 will also be described in the section "Information and Data". In this embodiment, the activity amount information 102 is the same in content as the activity amount sensor data. In other words, the activity amount information 102 is the activity amount sensor data converted into a digital value or the like. However, the activity amount information 102 may be the activity amount sensor data itself.

[0022] Moreover, the detection unit 14 detects whether a change (activity change) that satisfies a predetermined condition has occurred in the activity feature amount 104 or the activity amount information 102. Here, it is preferable that the detection unit 14 detects whether a change has occurred by comparing the activity feature amounts 104 with each other. Here, the activity change can be detected by comparing the activity feature amounts 104 for each predetermined period with each other and determining whether the difference is equal to or greater than a threshold. In addition, it is also possible to assume that the activity change is such that the amount of change per unit time is equal to or greater than a threshold, that the value is equal to or greater than a set value or less than a set value, and that the trend of the amount of change is unique. Here, it is assumed that the trend of the amount of change is unique, for example, that it is different from the average trend of change. Furthermore, the activity feature amount 104 may be used by aggregating the amount of activity into a plurality of categories. Then, the detection unit 14 specifies the time when the activity change has occurred.

[0023] Furthermore, the comparison unit 15 identifies the living activity feature 103 that has undergone a change (living activity change) that satisfies a predetermined condition among the living activity feature 103 corresponding to the change detected by the detection unit 14. For this purpose, the comparison unit 15 identifies a period that has a predetermined relationship with the time when the change detected by the detection unit 14 occurred. Next, the comparison unit 15 identifies the occurrence of a living activity change that satisfies a predetermined condition in the activity feature 104 or the activity amount information 102 during the identified period. Note that the living activity change can be assumed to be an amount of change per unit time that is equal to or greater than a threshold, that the value is equal to or greater than a set value or less, or that the tendency of the amount of change is unique. Here, it is assumed that the tendency of the amount of change is unique, for example, that it is different from an average tendency of change. Then, the comparison unit 15 identifies the living activity feature 103 in which the living activity change has occurred.

[0024] Moreover, the change factor estimation unit 16 estimates factors of changes in the daily living activities of the analysis subject 2 according to the daily living activity feature amount 103 identified by the comparison unit 15. For this purpose, the change factor estimation unit 16 uses an index value correspondence table 105. The index value correspondence table 105 will be described in the section "Information and Data".

[0025] Moreover, the improvement plan estimation unit 17 estimates an improvement plan for the living activity based on the living activity feature amount 103 identified by the comparison unit 15. For this purpose, it is preferable that the improvement plan estimation unit 17 uses the factors of the change in the living activity estimated by the change factor estimation unit 16. At this time, the improvement plan estimation unit 17 also uses the index value correspondence table 105.

[0026] The input / output unit 18 also has a function of connecting to the network 60 and the terminal devices 100-1 and 100-2. Here, the terminal devices 100-1 and 100-2 have an input / output function for the human life traceability device 10. As the input / output function, the terminal devices 100-1 and 100-2 output processing results, receive instructions from an administrator, and notify the human life traceability device 10. Although two terminal devices 100-1 and 100-2 are shown in FIG. 1, the number of terminal devices is not limited. The human life traceability device 10 and the terminal devices 100-1 and 100-2 may be connected via an intranet, or may be directly connected via a cable or the like. The terminal devices 100-1 and 100-2 may not be present, or these functions may be provided in the human life traceability device 10. The terminal devices 100-1 and 100-2 can be realized by computers such as PCs, tablets, and smartphones.

[0027] In addition, the memory unit 19 stores the various information and computer programs described above used in the processing of the human life traceability device 10.

[0028] Here, the human life traceability device 10 can be realized by a computer. An example of this implementation is shown in FIG. 2. FIG. 2 is a hardware configuration diagram of the human life traceability device 10 in this embodiment. In FIG. 2, the human life traceability device 10 includes a processing device 110, a network interface 181, an interface 182, a memory 191, and a storage device 192, which are connected to each other via a communication path such as a bus.

[0029] Here, the processing device 110 can be realized by a processor such as a CPU. The processing device 110 executes the processes in the above-mentioned functional blocks, the behavior estimation unit 11, the behavior feature amount calculation unit 12, the activity feature amount calculation unit 13, the detection unit 14, the comparison unit 15, the change factor estimation unit 16, and the improvement plan estimation unit 17, in accordance with various programs deployed in the memory 191. Details of this process will be explained in the "Processing Flow" section. In the hardware configuration of Fig. 2, each functional block is realized by a program, which is software, but it may be realized by dedicated hardware or an FPGA (Field-Programmable Gate Array).

[0030] 1. That is, network interface 181 is connected to network 60. Interface 182 is connected to terminal devices 100-1 and 100-2.

[0031] 1. In addition, the memory 191 and the storage device 192 correspond to the storage unit in Fig. 1. In addition, various information and programs used for processing in the processing device 110 are loaded in the memory 191. In Fig. 2, the programs are loaded in the memory 191, namely, a behavior estimation program 111, a behavior feature amount calculation program 112, an activity feature amount calculation program 113, a detection program 114, a comparison program 115, a change factor estimation program 116, and an improvement plan estimation program 117, and the processing device 110 executes processing in accordance with these programs. Note that each of these programs is stored in a storage medium such as the storage device 192, and is loaded from there into the memory 191.

[0032] The correspondence between each program and the functions of each part shown in Figure 1 is as follows: Behavior estimation program 111: Behavior estimation unit 11 Behavioral feature amount calculation program 112: Behavioral feature amount calculation unit 12 Activity feature amount calculation program 113: Activity feature amount calculation unit 13 Detection program 114: detection unit 14 Comparison program 115: Comparison section 15 Change factor estimation program 116: Change factor estimation unit 16 Improvement plan estimation program 117: Improvement plan estimation part 17 Moreover, the storage device 192 stores various information in addition to the above-mentioned programs. These information include the above-mentioned living behavior information 101, activity amount information 102, living behavior feature amount 103, activity feature amount 104, and index value correspondence table 105. Moreover, it can be realized by a storage such as a hard disk drive. Moreover, the storage device 192 may be realized in a separate housing from the human life traceability device 10, such as a file server. This concludes the explanation of the human life traceability device 10, and returning to FIG. 1, the insurance company server 41 and the day service provider server 51 will be explained.

[0033] Insurance company server 41 is operated by an insurance company and is realized by a computer. In other words, it has a storage device 411 and a processing device 412, which are general components of a computer. Here, insurance company server 41 executes processes for developing insurance products, managing customers, and managing the health of policyholders related to this embodiment. In addition, insurance company server 41 is connected to terminal device 42 similar to terminal devices 100-1 and 100-2.

[0034] In this embodiment, the day service provider server 51 is operated by a day service provider and is realized by a computer similar to the insurance company server 41. That is, it has a storage device 511 and a processing device 512, which are general configurations of a computer. Here, the day service provider server 51 executes processes for facility operation management, user management, and user health management related to this embodiment. Similarly to the insurance company server 41, the day service provider server 51 is connected to a terminal device 52.

[0035] Furthermore, user terminals 31 and 32 can be realized by computers used by related parties such as relatives of analysis subject 2. These can be realized by PCs, smartphones, tablets, etc., and can obtain and display analysis results for analysis subject 2 from human life traceability device 10. It is also desirable to be able to output instructions regarding the analysis results to human life traceability device 10 and user terminal 23 of analysis subject 2. This concludes the explanation of the configuration of this embodiment. <Information and Data> Next, various information and data used in this embodiment will be described. First, FIG. 3 is a diagram showing living activity information 101 used in this embodiment. As shown in FIG. 3, the living activity information 101 is time-series data in which living activity items indicating types of living activities are associated with their times. The living activity information 101 is created by the activity estimation unit 11 based on living activity sensor data. Furthermore, the living activity information 101 is created for each analysis subject 2 and stored in the storage device 192 in FIG. 2.

[0036] Next, FIG. 4 is a diagram showing the activity amount information 102 used in this embodiment. As shown in FIG. 4, the daily behavior information 101 is time-series data in which the instantaneous value of the activity amount is associated with the time. Here, the activity amount information 102 can use activity amount sensor data. Also, as the instantaneous value of the activity amount, the speed and acceleration related to the movement of the subject 2 at that time can be used. Furthermore, as the activity amount information 102, the energy consumption of the subject 2 created from the activity amount sensor data, etc. can be used. Furthermore, the activity amount information 102 is managed for each subject 2. That is, it is stored in the storage device 192 in FIG. 2.

[0037] Next, FIG. 5 is a diagram showing the living activity feature amount 103 used in this embodiment. As shown in FIG. 5, the living activity feature amount 103 is data in which the living activity items are associated with index values ​​of the time and number of times performed during a period. The living activity feature amount 103 is created from the living activity information 101 by the activity feature amount calculation unit 12. The index value is a total value related to the time or number of times performed, and indicates a representative value such as an average value of a unit period of time or number of times that the analysis subject 2 performed a living activity item during a period such as one week. The unit period can be one day, for example. In addition, this index value is an index indicating the characteristics of the living activity feature amount 103. In other words, the living activity feature amount 103 indicates an index value for each living activity item. In addition, the living activity items are totaled for each index value item such as time and number of times.

[0038] The living activity feature amount 103 records the time when the corresponding sensor data was detected as a "period." In this example, a specific week of "5 / 2-5 / 8" is recorded, but other units such as a specific date, a day of the week, or a month may be used. This "period" can be specified based on the time of the living activity information 101.

[0039] Furthermore, in this embodiment, it is possible to use a plurality of types of living activity feature amounts 103. Hereinafter, the contents of first to third living activity feature amounts, which are an example of the plurality of living activity feature amounts 103, will be described.

[0040] First, the first living activity feature is information indicating an integral value (index value) of each living activity item per day. Next, the second living activity feature is information indicating an integral value (index value) of each living activity item per week. For this purpose, the activity feature calculation unit 12 calculates, as the second living activity feature, an average of integral values ​​of each living activity item per day from the first living activity feature for one week.

[0041] Next, the third living activity feature is information indicating the respective proportions of clusters for each living activity item, which are represented by integral values, created based on the first living activity feature or the second living activity feature. For this purpose, the behavior feature calculation unit 12 generates a cluster group including a plurality of clusters. Here, the clusters correspond to the activeness of the living activity items, which are influenced by the day of the week, the weather, etc. In other words, the clusters are clustered according to the living activities of the subject 2 to be analyzed, depending on how active they are.

[0042] These first to third living activity feature amounts are generated by the activity feature amount calculation unit 12 and stored in the storage device 192 of Fig. 2. How these are used will be described later in the section "Processing flow".

[0043] Next, FIG. 6 is a diagram showing the activity feature 104 used in this embodiment. As shown in FIG. 6, the activity feature 104 is data in which activity amounts such as moving speed, acceleration, and energy are associated with integral values ​​of the time (m:min) during which the activity amount values ​​were detected during a predetermined period. In particular, it is desirable to aggregate the integral values ​​into a plurality of sections. In FIG. 6, moving speed is divided into sections such as 1-5 and 5-10. The activity feature 104 is created from the activity amount information 102 by the activity feature calculation unit 13. Note that, in this embodiment, a plurality of activity amounts are used, but the number is not limited. Here, the activity feature 104 records the time when the sensor data was detected as a "period". In this example, "5 / 2-5 / 8" is written, which is the same value as the living behavior feature 103. For this reason, other units such as a specific day, a day of the week, or a month may be used. Note that this "period" can be specified based on the time of the activity amount information 102.

[0044] Furthermore, in this embodiment, it is possible to use a plurality of types of activity feature amounts 104. Hereinafter, the contents of first to fourth activity feature amounts, which are an example of the plurality of activity feature amounts 104, will be described.

[0045] First, the first activity feature is information indicating an integral value of the amount of activity per day. Next, the second activity feature is information indicating an integral value of the amount of activity per week. For this purpose, the activity feature calculation unit 13 calculates, as the second activity feature, an average of the integral values ​​of the amount of activity per day from the first activity feature for one week.

[0046] Next, the third activity feature is information indicating the respective proportions of clusters of activity features represented by integral values, which are created based on the first activity feature or the second activity feature. For this purpose, the activity feature calculation unit 13 generates a cluster group including a plurality of clusters. Here, the clusters correspond to the activity state of the activity feature, which is influenced by the day of the week, the weather, etc. In other words, the clusters are clustered according to the level of activity of the analysis subject 2.

[0047] Next, the fourth activity feature is information indicating an integral value of the activity feature per month. For this purpose, the behavior feature calculation unit 12 calculates, as the fourth activity feature, an average of the integral value of the second activity feature for one month or the amount of activity per day from the second activity feature.

[0048] These first to fourth activity feature amounts are also generated by the activity feature amount calculation unit 13 and stored in the storage device 192 in Fig. 2. How these are used will also be described later in the section "Processing flow".

[0049] In the present embodiment, the first to third living behavior feature amounts and the first to fourth activity feature amounts are used as a predetermined period of a week or a month, but these are merely examples and are not limited thereto. Also, although an average is used as a feature amount, other representative values ​​may be used.

[0050] Finally, the index value correspondence table 105 will be described. Fig. 7 is a diagram showing the index value correspondence table 105 used in this embodiment. The index value correspondence table 105 is used by the comparison unit 15 and the improvement plan estimation unit 17 to identify the living activity information 101 in which a living activity change that satisfies a predetermined condition has occurred and to estimate an improvement plan. Furthermore, the index value correspondence table 105 is preferably used by the change factor estimation unit 16 to estimate a change factor.

[0051] For this reason, in the index value correspondence table 105, a change factor is set for each daily activity item together with its index value (item). This change factor indicates a criterion for the index value (item) for identifying the daily activity information 101 in the comparison unit 15. For example, for "Going out behavior" of the "daily activity item" of the first record in Fig. 7, when the "time" of the "index value (item)" is "decreased by 10%", the comparison unit 15 determines that a daily activity change has occurred.

[0052] Furthermore, the index value correspondence table 105 also associates improvement proposals with each daily behavior item. Therefore, the improvement proposal estimation unit 17 can estimate the improvement proposal using the index value correspondence table 105. For example, if the "change factor" is "reduced time spent outside (reduced by 10%)", it can be specified that the time spent outside should be increased. In other words, it can be specified that the message to the analysis subject 2 is "You are spending more time at home. Try to increase your opportunities to go outside."

[0053] In this embodiment, the change factors include criteria for index values ​​(items), but these criteria may be set as improvement plans or other items. In this case, the comparison unit 15 uses the improvement plans or other items to determine the occurrence of a change in daily living behavior. Also, the index value correspondence table 105 is not limited to the use of the index value correspondence table 105 shown in FIG. 7, as long as it can estimate an improvement plan based on the daily living behavior information 101 in which a change in daily living behavior has occurred.

[0054] This concludes the explanation of the information and data used in this embodiment, and the processing flow of this embodiment will now be explained. <Processing flow> Next, the processing flow of this embodiment will be described. Fig. 8 is a flowchart showing the processing flow in this embodiment. Fig. 8 will be described below mainly with respect to each configuration (functional block) shown in Fig. 1.

[0055] First, in step S1, the input / output unit 18 receives sensor data from the sensors. Here, the input / output unit 18 converts the sensor data. As a result, the activity amount sensor data is converted into activity amount information 102. Note that the input / output unit 18 desirably stores the converted sensor data in the storage unit 19. Note that the activity amount information 102 has already been described with reference to FIG. 4.

[0056] Next, in step S2, the input / output unit 18 divides the received sensor data into activity amount sensor data and daily behavior sensor data. Note that steps S1 and S2 may be realized by receiving the activity amount sensor data and the daily behavior sensor data in separate receiving units, and step S2 may be executed by a configuration separate from the input / output unit 18.

[0057] As a result of step S2, if the activity amount sensor data is received, the process proceeds to step S3, whereas if the living behavior sensor data is received, the process proceeds to step S4.

[0058] Next, in step S3, the activity feature amount calculation unit 13 creates an activity feature amount 104 indicating the feature from the activity amount information 102. Moreover, it is preferable that the activity feature amount calculation unit 13 stores the activity feature amount 104 in the storage unit 19. The activity feature amount 104 has already been described with reference to FIG. 6. Here, an example in which one type of activity feature amount 104 is created will be described, and the process of using the above-mentioned first to fourth activity feature amounts will be described later.

[0059] In step S4, the behavior feature amount calculation unit 12 creates the living behavior information 101 from the converted living behavior sensor data. Note that the living behavior information 101 has already been described with reference to FIG.

[0060] Next, in step S5, the behavior feature amount calculation unit 12 creates a living activity feature amount 103 indicating a feature of the living activity information 101. Moreover, it is preferable that the behavior feature amount calculation unit 12 stores the living activity feature amount 103 in the storage unit 19. The living activity feature amount 103 has already been described with reference to FIG. 5. Moreover, an example in which one type of living activity feature amount 103 is created will be described here, and the process of using the above-mentioned first to third living activity feature amounts will be described later.

[0061] Next, in step S6, the detection unit 14 detects an activity change in the activity feature 104 and the time of occurrence thereof. To this end, the detection unit 14 extracts the activity feature 104 for each predetermined period. The detection unit 14 then compares the extracted activity feature 104 for each predetermined period and determines whether the difference is equal to or greater than a threshold. As a result, if the difference is equal to or greater than the threshold, the detection unit 14 determines that an activity change has occurred and detects the time of occurrence thereof.

[0062] For example, in step S6, if the predetermined period is a "month", the process is as follows. First, the detection unit 14 extracts the activity feature 104 for the month to be analyzed. In the case of the activity feature 104 shown in Fig. 6, one week is created as one record, so the detection unit 14 extracts activity feature 104 for one month = 4 weeks (4 records).

[0063] Furthermore, the detection unit 14 extracts activity feature amounts 104 from at least the month before the analysis target month as activity feature amounts to be compared. For example, when the analysis target month is May, the detection unit 14 extracts activity feature amounts 104 from April as activity feature amounts to be compared. In this case, the detection unit 14 may calculate a representative value such as an average value of activity feature amounts 104 for multiple months and use this as activity feature amounts to be compared.

[0064] Next, the detection unit 14 compares the activity feature 104 of the analysis target month with the comparison target activity feature. When the detection unit 14 detects an activity change because the comparison result is equal to or greater than a threshold, it identifies the time of occurrence. The time of occurrence can be "week," "day," "day of the week," "date and time," etc., but it is preferable that the specified period be in units shorter than "one month." In particular, it is preferable that the number of records of the activity feature 104 is equal to one week. Note that in this step, it is sufficient to detect an activity change based on the activity amount information 102, and the use of the activity feature 104 is one example.

[0065] As a result of step S6, if a change in activity is detected (YES), the process proceeds to step S7, whereas if a change in activity is not detected (NO), the process proceeds to step S1.

[0066] Next, in step S7, the comparison unit 15 compares the living activity feature amounts 103 corresponding to the activity change detected in step S6 to detect the occurrence of a living activity change. To this end, first, the comparison unit 15 identifies a target period having a predetermined relationship with the occurrence time of the activity change detected in step S6. Next, the comparison unit 15 identifies a comparison period such as a period preceding the target period. Then, the comparison unit 15 compares the living activity feature amounts 103 of the target period and the comparison period for each living activity item. As a result, if the difference satisfies a predetermined condition, the comparison unit 15 determines that a living activity change has occurred and identifies the living activity item.

[0067] Here, the target period is preferably a certain period including the time when the activity change occurs, and in particular, a period before the time of occurrence. The reason for specifying the time before the time of occurrence is that the change in daily behavior occurs due to a change in the amount of activity. However, since these causal relationships vary, the target period may include the time after the time of occurrence or both, or may be common to the time of occurrence (period). In this way, the target period and the comparison period are preferably periods close to each other within a specified range.

[0068] Whether the difference satisfies a predetermined condition is determined using the index value correspondence table 105 shown in Fig. 7. For example, when the "daily life behavior item" is "going out," if the time during the target period is compared with the comparison period and the time is "decreased by 10%," it is determined that the difference satisfies the predetermined condition.

[0069] In step S7, the comparison unit 15 may detect the occurrence of a living activity change by comparing the living activity information 101 corresponding to the activity change detected in step S6. Thus, in this step, it is sufficient to detect a living activity change based on the living activity information 101, and one example is to use the living activity feature amount 103. In other words, it is sufficient to compare information on living activities in this step.

[0070] Next, in step S8, the comparison unit 15 judges whether the process of step S7, that is, the comparison of the living activity feature 103, for each living activity item is completed. For this purpose, the comparison unit 15 uses the living activity items of the living activity feature 103 shown in Fig. 5. As a result, if the process is completed for each living activity item of the living activity feature 103 (YES), the process proceeds to step S9. If the process is not completed (NO), the process proceeds to step S7, and the process is executed for each remaining living activity item.

[0071] Next, in step S9, the change factor estimation unit 16 estimates the change factor for the daily living action item identified in step S7. To this end, the change factor estimation unit 16 searches for a change factor corresponding to the identified daily living action item from the index value correspondence table 105. When the above-mentioned "daily living action item" is "going out", the change factor is estimated to be "reduced time going out".

[0072] Next, in step S10, the improvement plan estimation unit 17 estimates an improvement plan according to the daily life behavior item identified in step S7 and / or the change factor estimated in step S9. For this purpose, the improvement plan estimation unit 17 uses the index value correspondence table 105. For example, when the "daily life behavior item" is "going out" and / or the "change factor" is "reducing the time spent going out", the improvement plan estimation unit 17 estimates "You are spending more time at home. Let's increase the opportunities to go out." as an improvement plan. In this way, in this embodiment, information for improving daily life behavior is output as an improvement plan. Note that in this embodiment, one index value correspondence table 105 is used in steps S7, S9, and S10, but this may be provided separately for each function.

[0073] Here, the estimation of the improvement plan by the improvement plan estimation unit 17 may be performed as follows. (1) The improvement plan estimation unit 17 estimates an improvement plan according to a change factor based on data analysis using AI (artificial intelligence). (2) The improvement plan estimation unit 17 estimates an improvement plan corresponding to the change factor, which is a condition, by an approach based on an IF-THEN rule or the like. (3) The improvement plan estimation unit 17 selects from a plurality of improvement plans by a filtering process according to the amount of difference, which is the comparison result of the living activity feature amount 103 in step S7.

[0074] In this embodiment, an improvement plan may be estimated by using the index value correspondence table 105 or by combining (1) to (3).

[0075] Then, the improvement proposal estimation unit 17 outputs the improvement proposal to the terminal devices 100-1 and 100-2 and the network 60 via the input / output unit 18. As a result, the user terminals (23, 31, 32), the insurance company server 41, the terminal device 42, the day service provider server 51, and the terminal device 52 receive the improvement proposal. As a result, the improvement proposal can be displayed on the terminal devices 100-1 and 100-2, the terminal device 42, and the terminal device 52. The improvement proposal estimation unit 17 may also be configured to output the change factor and display the change factor on each device.

[0076] Here, Fig. 9 is a diagram showing a display example in this embodiment. This display may be common to terminal devices 100-1 and 100-2, user terminals (23, 31, 32), terminal device 42, and terminal device 52, or may be customized. In Fig. 9, the following information is displayed on display screen 200. This information may be created by improvement plan estimation unit 17, or may be created on the terminal side using information from improvement plan estimation unit 17.

[0077] The display screen 200 clearly indicates that the subject is an analysis subject 2 (Mr. XX), and includes a change factor and improvement plan column 201, a period column 202, an activity amount display column 203, a daily behavior comparison result display column 204, and a graph display column 205.

[0078] First, the change factors and improvement proposals estimated in steps S9 and S10 are displayed. Furthermore, the period column 202 indicates the analysis target period, that is, the detection period by the sensor, and the period compared by the comparison unit 15 is indicated by a triangle. In this figure, April (fourth week) and May (first week) are compared. Here, May (first week) is the target period, and April (fourth week) is the comparison period.

[0079] The activity amount display section 203 also displays information in the form of a graph of the activity amount information 102. Here, a bar graph different from that in Fig. 4 is used for display, but other forms such as a line graph may also be used.

[0080] Furthermore, the living activity comparison result display field 204 displays "living activity item," "index value (item)," "living activity change (amount of change)," and the living activity feature amount 103 for the target period and the comparison period. Here, "living activity change (amount of change)" indicates the difference that is the comparison result by the comparison unit 15 in the target period and the comparison period.

[0081] Furthermore, the graph display field 205 displays information such as a graph of the comparison results of the daily activity feature amount 103.

[0082] Note that display screen 200 is merely an example, and various customizations are possible. In particular, health care businesses may display personal information in a confidential manner, omit the position column, or change its display position. In particular, the change factor and improvement plan column 201 may be configured to display either the change factor or the improvement plan.

[0083] As a result, the relevant parties can confirm improvement proposals for the analysis subject 2 and consider revising their daily activities. Furthermore, in health-related services, each server can be used to manage subscribers and propose new services.

[0084] This concludes the explanation of the processing flow of this embodiment, and a modification of the feature amount will now be explained. <Modification> As described above, in this embodiment, the first to third living activity feature amounts can be used as the living activity feature amount 103, and the first to fourth activity feature amounts can be used as the activity feature amount 104. The processing of modified examples related to these (steps S3, S5, S6, and S7) will be described below.

[0085] Fig. 10 is a diagram for explaining the concept of the processing of the modified example in this embodiment. Fig. 10(a) shows the concept of generating the first to fourth activity feature amounts related to the activity amount information 102 (step S3). The activity feature amount calculation unit 13 acquires and stores the activity amount information 102 as information for each time. Then, the activity feature amount calculation unit 13 generates a first activity feature amount, which is an integral value per day, from this. That is, a first activity feature amount in daily units is generated.

[0086] As a result, a first activity feature amount for each day of the week is calculated as shown in the second row of Fig. 10(a). The activity feature amount calculation unit 13 then generates a second activity feature amount as the average value for each week. As a result, a second activity feature amount for each week is calculated as shown in the third row of Fig. 10(a).

[0087] In addition, the activity feature calculation unit 13 creates clusters according to the activity amount from the first activity feature for each day of the week. This corresponds to classification into "clusters with high activity amount" and "clusters with low activity amount" in FIG. 10(a). This allows classification according to the day of the week, weather, season, and influence. As a result of the above, the activity feature calculation unit 13 creates a third activity feature indicating the cluster ratio for each week.

[0088] Then, the activity feature amount calculation unit 13 generates a fourth activity feature amount as an average value of the second activity feature amounts for each week, that is, a fourth activity feature amount for each month is generated.

[0089] Next, Fig. 10(b) shows a concept of generating the first to third living activity feature amounts as the living activity feature amount 103 (step S5). The activity feature amount calculation unit 12 generates the first living activity feature amount, which is an integral value of each activity (each living activity item) per day, from the living activity information 101 for each time. That is, the first living activity feature amount in daily units is generated.

[0090] As a result, the first living activity feature amount for each day of the week is calculated as shown in the second row of Fig. 10(b). Then, the activity feature amount calculation unit 12 generates the second living activity feature amount as the average value for each week.

[0091] In addition, the behavior feature calculation unit 12 creates cluster groups according to the activity amounts from the first activity feature amounts for each day of the week. This results in classification into "cluster with a lot of sleep," "cluster with little sleep," "cluster with a lot of housework," and "cluster with little housework" in FIG. 10(b). This results in classification according to the influence of the day of the week, weather, and season. As a result, the second daily living behavior feature amounts for each week are obtained as shown in the third row of FIG. 10(b).

[0092] Then, the activity feature calculation unit 12 creates a third activity feature indicating a cluster ratio by week and by activity from the second living activity feature. Thus, the first to third living activity feature and the first to fourth living activity feature are created in steps S3 and S5. The first to third living activity feature and the first to fourth activity feature are stored in the storage unit 19.

[0093] Next, the processes in steps S6 and S7 will be described. Fig. 11 is a flowchart showing the process flow of steps S6 and S7 in this modified example. Here, steps S61 to S64 correspond to step S6, and steps S71 to S74 correspond to step S7.

[0094] First, in step S61, the detection unit 14 detects an activity change of the fourth activity feature amount and its occurrence time. This detection method is similar to the content explained in Fig. 8. As a result, if an activity change is detected (YES), the process proceeds to step S71. On the other hand, if an activity change is not detected (NO), the process proceeds to step S62.

[0095] Next, in step S71, the comparison unit 15 compares the third living activity feature amounts corresponding to the activity changes detected in step S61 to detect the occurrence of a living activity change. This detection method is the same as that described in Fig. 8. Then, this process ends and the process proceeds to step S8.

[0096] In step S62, the detection unit 14 detects an activity change of the third activity feature and its occurrence time. This detection method is the same as that in step S61, and is also the same in steps S63 and S64. As a result, if an activity change is detected (YES), the process proceeds to step S72. In addition, if an activity change is not detected (NO), the process proceeds to step S63.

[0097] Next, in step S72, the comparison unit 15 compares the second living activity feature amounts corresponding to the activity changes detected in step S62 to detect the occurrence of a living activity change. This detection method is the same as that in step S71, and is also the same in steps S63 and S64. Then, this process ends and the process proceeds to step S8.

[0098] In step S63, the detection unit 14 detects an activity change of the second activity feature and its occurrence time. As a result, if an activity change is detected (YES), the process proceeds to step S73. If an activity change is not detected (NO), the process proceeds to step S64.

[0099] Next, in step S73, the comparison unit 15 compares the first living activity feature amounts corresponding to the activity change detected in step S63 to detect the occurrence of a living activity change. Then, this process ends and the process proceeds to step S8.

[0100] In step S64, the detection unit 14 detects an activity change in the first activity feature and its occurrence time. As a result, if an activity change is detected (YES), the process proceeds to step S74. If an activity change is not detected (NO), the process ends. The processes from step 8 onwards can be omitted.

[0101] Next, in step S74, the comparison unit 15 compares the living activity feature amount information 101 corresponding to the activity change detected in step S64 to detect the occurrence of a living activity change. Then, this process ends, and the process proceeds to step S8.

[0102] As described above, in this embodiment, a plurality of feature amounts with different target periods are created, and the processes of steps S6 and S7 are executed in multiple stages in order of the longest period. In particular, the comparison process is executed in the comparison unit 15 according to the result in the detection unit 14. By executing the process in this manner, it is possible to detect changes in the subject of analysis from a long-term perspective. Note that the periods (days, weeks, months) of the first to third living activity feature amounts and the first to fourth living activity feature amounts are merely examples, and are not limited to these. Furthermore, the number of these feature amounts is not limited to the number exemplified.

[0103] This concludes the description of this embodiment, but the present invention is not limited to this embodiment and can be customized in various ways. For example, the human life traceability device 10 may be configured as a standalone device so that the relevant person can check the processing results of the human life traceability device 10. Furthermore, the activity amount information 102 and the activity feature amount 104 may be specified by combining multiple activity amounts. In this case, in addition to combining different types of activity amounts such as speed and acceleration, different activity amounts of the same type (speeds) may be combined. Furthermore, when an improvement proposal is output, it is desirable for the human life traceability device 10 to periodically check the change (change in daily life behavior) in the life behavior item for which the improvement proposal was output before and after the output. [Explanation of symbols]

[0104] 10: Human life traceability device 11: Behavior estimation section 12: Behavioral feature calculation unit 13: Activity feature calculation unit 14: Detection unit 15: Comparison section 16: Change factor estimation section 17: Improvement plan estimation department 18: Input / output section 19: Storage part 2: Subjects of analysis 20: Inside the house 21-1, 21-2: Activity sensor 22-1, 22-2: Daily Life Activity Sensor 23, 31, 32: User terminal 41: Insurance company server 411: Storage device 412: Processing device 42: Terminal device 51: Day service provider server 511: Storage device 512: Processing device 52: Terminal device 60: Network

Claims

1. A human life traceability device that manages and analyzes the activities and behavior of subjects of analysis, a storage unit that stores daily living behavior information, which is time-series data showing daily living behavior of the subject of analysis, and activity amount information, which is time-series data showing an activity amount of the subject of analysis, based on sensor data of the subject of analysis from a sensor; A detection unit that detects an activity change that satisfies a predetermined condition based on the activity amount information; When the activity change is detected, a target period and a comparison period having a predetermined relationship with the timing of the activity change are identified; comparing information on living activities corresponding to the living activity information during the target period and the comparison period; a comparison unit that identifies information about a living activity in which a living activity change that satisfies a predetermined condition has occurred as a result of the comparison; an improvement plan estimation unit that estimates an improvement plan for a living activity based on information about the identified living activity; a change factor estimation unit that estimates a factor of the change in the living activity according to information on the specified living activity; an activity feature amount calculation unit that calculates an activity feature amount indicating a feature of the activity amount information, and a living activity feature amount calculation unit that calculates a living activity feature amount indicating a feature of the living activity information, the improvement plan estimation unit estimates an improvement plan for the living activity corresponding to a cause of the estimated change in the living activity; The detection unit detects an activity change in the activity feature amount, The comparison unit is a human life traceability device that compares behavioral features of the target period and the comparison period.

2. The human life traceability device according to claim 1, Further, an activity inference unit that creates the living activity information in which a living activity item indicating a type of living activity and a time of the living activity are associated with each other from the sensor data, the storage unit stores, as the living activity information, living activity items of the analysis subject and times of the living activities; the living activity feature amount calculation unit calculates the living activity feature amount having the living activity items and index values ​​of the living activities; the comparison unit identifies, as the living activity change, a living activity item of the living activity feature amount and a difference between index values ​​thereof; The change factor estimation unit is a human life traceability device that estimates an improvement plan for the identified daily behavior item and the daily behavior corresponding to a difference between the index values ​​thereof.

3. 3. The human life traceability device according to claim 2, The activity feature amount calculation unit is Calculate an integral value of the daily activity amount as a first activity feature amount; calculating an average value of the amount of activity per week from the first activity feature amount as a second activity feature amount; generating a cluster group from the first activity feature amount, and calculating a day and a ratio belonging to the generated cluster group as a third activity feature amount; calculating a monthly integral value of the second activity feature amount as a fourth activity feature amount; The living activity feature amount calculation unit is A time integral value for each daily living activity item is calculated as a first living activity feature amount; calculating a time integral value for each living activity item on a weekly basis from the first living activity feature amount as a second living activity feature amount; generating clusters for each living activity item from the first living activity feature amount, and calculating days and proportions belonging to the generated cluster groups as third living activity feature amounts; The detection unit is comparing the fourth activity feature amount for the target period and the comparison period to detect the presence or absence of the activity change; When the activity change is not detected, the target third activity feature amounts are compared with each other to detect the presence or absence of the activity change; If the activity change is not detected, the second activity feature amounts are compared to detect the presence or absence of the activity change; If the activity change is not detected, the first activity feature amounts are compared to detect the presence or absence of the activity change; The comparison unit performs a comparison between the third activity features, between the second activity features, or between the first activity features, depending on a detection result of an activity change by the detection unit.

4. A method for supporting improvement proposals implemented by a human life traceability device that manages and analyzes the activities and behavior of an analysis subject, a storage unit stores, based on sensor data of the subject, living behavior information which is time-series data showing the living behavior of the subject and activity amount information which is time-series data showing the amount of activity of the subject, A detection unit detects an activity change that satisfies a predetermined condition based on the activity amount information, The comparison section is When the activity change is detected, a target period and a comparison period having a predetermined relationship with the timing of the activity change are identified; comparing information on living activities corresponding to the living activity information during the target period and the comparison period; Identifying information about a lifestyle activity that has undergone a lifestyle activity change that satisfies a predetermined condition as a result of the comparison; an improvement plan estimation unit estimates an improvement plan for the living activity based on the identified information about the living activity; a change factor estimation unit estimating a factor of the change in the living activity according to the information on the identified living activity; the improvement plan estimation unit estimates an improvement plan for the living activity corresponding to a cause of the estimated change in the living activity; an activity feature amount calculation unit calculates an activity feature amount indicating a feature of the activity amount information; a living activity feature amount calculation unit calculates a living activity feature amount indicating a feature of the living activity information; The detection unit detects an activity change in the activity feature amount, The improvement plan proposal support method, in which the comparison unit compares daily activity feature amounts of the target period and the comparison period.

5. The improvement proposal support method according to claim 4, Furthermore, the activity inference unit creates the living activity information in which living activity items indicating types of living activities and times of the living activities are associated with each other from the sensor data; storing, in the storage unit, living activity items of the subject of analysis and times of the living activities as the living activity information; the living activity feature amount calculation unit calculates the living activity feature amount having the living activity item and an index value of the living activity; the comparison unit identifies, as the living activity change, a living activity item of the living activity feature amount and a difference between index values ​​thereof; The improvement plan proposal support method, in which the change factor estimating unit estimates an improvement plan for the identified daily living activity item and an improvement plan for the daily living activity corresponding to a difference between index values ​​of the identified daily living activity item and an improvement plan for the daily living activity.

6. 6. The improvement proposal support method according to claim 5, The activity feature amount calculation unit, Calculate an integral value of the daily activity amount as a first activity feature amount; calculating an average value of the amount of activity per week from the first activity feature amount as a second activity feature amount; generating a cluster group from the first activity feature amount, and calculating a day and a ratio belonging to the generated cluster group as a third activity feature amount; calculating a monthly integral value of the second activity feature amount as a fourth activity feature amount; The living activity feature amount calculation unit, A time integral value for each daily living activity item is calculated as a first living activity feature amount; calculating a time integral value for each living activity item on a weekly basis from the first living activity feature amount as a second living activity feature amount; generating clusters for each living activity item from the first living activity feature amount, and calculating days and proportions belonging to the generated cluster groups as third living activity feature amounts; The detection unit, comparing the fourth activity feature amount for the target period and the comparison period to detect the presence or absence of the activity change; When the activity change is not detected, the target third activity feature amounts are compared with each other to detect the presence or absence of the activity change; If the activity change is not detected, the second activity feature amounts are compared to detect the presence or absence of the activity change; If the activity change is not detected, the first activity feature amounts are compared to detect the presence or absence of the activity change; The comparison unit performs a comparison between the third activity features, between the second activity features, or between the first activity features, depending on a detection result of an activity change by the detection unit.

Images