Behavior analysis system, behavior analysis method, and program

Abstract

To provide a behavior analysis system, behavior analysis method, and program that can grasp changes in member's behavior with a simple configuration.SOLUTION: A behavior analysis system includes a communication unit, a first database, a processor, and a memory. The communication unit communicates with an entrance / exit management system that manages the entrance / exit of a member. The first database accumulates log data that records entrance / exit performance of the member received from the entrance / exit management system. The processor generates tendency data that indicates behavioral tendencies of the member by analyzing the log data accumulated in the first database. The processor estimates changes in member's behavior by comparing the log data received from the entrance / exit management system with the tendency data. The processor determines a mental health state of the member from the estimated changes in the member's behavior, and generates an alert to encourage mental care of the member based on determination results.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to a behavior analysis system, a behavior analysis method, and a program for analyzing an individual's behavior.

Background Art

[0002] Japanese Patent Application Laid-Open No. 2011-123579 (Patent Document 1) discloses a management system for managing the behavior of employees. This management system is configured to connect various devices such as a PC mouse, a camera, an IP phone used by an employee, and an entrance / exit information reading device provided in the employee terminal to a network, acquire employee behavior data from the devices, and store it in an employee behavior history DB. The management server determines whether the employee behavior history input from the above devices is within the range of the corresponding employee's behavior characteristics stored in the employee behavior characteristic database. When the employee's behavior history is outside the range of the behavior characteristics, the management server sends an alert message to the employee.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the management system described in Patent Document 1, as employee behavior data, biometric data such as the employee's pulse, body temperature, and fingertip humidity measured by a sensor mounted on the PC mouse of the employee terminal, the number of clicks of the PC mouse, the number of smiling faces of the employee imaged by the camera of the employee terminal, the leaving time and the number of leaving times, the call time, the number of calls, and the call duration of the IP phone, and the employee's entrance / exit information from the entrance / exit information reading device are used.

[0005] By adopting a configuration in which the action data of employees is acquired using a plurality of devices connected to the network in this way, it is possible to extract the action characteristics peculiar to employees. However, on the other hand, since the amount of data accumulated in the employee action history DB becomes enormous, a storage device with a large storage capacity is required. In addition, there is a concern that a large load will be imposed on the management server that extracts action characteristics in order to process the enormous amount of data.

[0006] The present disclosure has been made to solve such problems, and an object of the present disclosure is to provide a behavior analysis system, a behavior analysis method, and a program capable of grasping changes in the behavior of members with a simple configuration.

Means for Solving the Problems

[0007] The behavior analysis system according to one embodiment analyzes the behavior of members belonging to an organization. The behavior analysis system includes a communication unit, a first database, a processor, and a memory that stores a program executed by the processor. The communication unit communicates with an entrance / exit management system that manages the entrance and exit of members to a predetermined area used by the members. The first database stores log data in which the actual results of the entrance and exit of members received by the communication unit from the entrance / exit management system are recorded. The processor generates tendency data representing the tendency of the behavior of the members by analyzing the log data stored in the first database according to the program. The processor estimates the change in the behavior of the members by comparing the log data received by the communication unit from the entrance / exit management system with the tendency data. The processor determines the mental health state of the members from the estimated change in the behavior of the members, and generates an alarm prompting care for the mental state of the members based on the determination result of the health state.

Effects of the Invention

[0008] According to the present disclosure, changes in the behavior of a member can be estimated from log data in which the attendance and departure records of the member are recorded. Therefore, it becomes possible to easily grasp changes in the behavior of a member by using an existing entrance / exit management system that manages the entrance and exit of members to a predetermined area.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Modes for Carrying Out the Invention

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals and their description will not be repeated.

[0011] [Embodiment 1] <Application Example of Behavior Analysis System> FIG. 1 is a diagram for explaining an application example of the behavior analysis system according to Embodiment 1. The behavior analysis system according to Embodiment 1 is a system for analyzing the behavior of a person using a predetermined area. This predetermined area is a facility where members (employees, students, etc.) belonging to a specific organization are active, such as an office or a school. The predetermined area may be a partial area within the facility.

[0012] In one aspect, the behavior analysis system according to Embodiment 1 can be used to analyze the behavior of employees working in an office. In another aspect, the behavior analysis system according to Embodiment 1 can be used to analyze the behavior of students attending school. In this specification, as one embodiment, a scenario where the behavior analysis system according to Embodiment 1 is used to analyze the behavior of employees working in an office is assumed.

[0013] A supervisor who oversees a plurality of members is required to grasp the physical and mental health conditions of individual members. However, since the working environment and work styles are diverse, it is not always easy for a supervisor to objectively grasp the mental health condition of an individual. As a result, it may happen that the supervisor does not notice a change in the mental health condition of a member, or notices the change in the mental health condition of a member belatedly. In such a case, a problem occurs that care for restoring the mental health condition of the member is not appropriately provided.

[0014] On the other hand, a change in an individual's mental health condition may appear as a change in the individual's behavior. For example, along with a mental health disorder, changes such as a delay in the arrival time at the office or an increase in the frequency of leaving the office early or being absent from work may appear. Or, a tendency such as an increase in overtime due to a decrease in work efficiency may appear. Therefore, grasping such a change in an individual's behavior can be a clue to noticing a change in the mental health condition of the individual.

[0015] Therefore, the behavior analysis system according to Embodiment 1 accumulates data regarding the record of entry and exit of members to and from the office, analyzes the behavior tendency of the members from the accumulated data, and determines the mental health condition of the members by estimating a change in the behavior of the members based on the analysis result.

[0016] Specifically, as shown in FIG. 1, the behavior analysis system 100 according to Embodiment 1 exchanges various signals and data with an entry / exit management system 200 and communication terminal devices 300 via a communication network NW such as the Internet.

[0017] The entry / exit management system 200 is a system for managing the entry and exit of members working in a target office. The entry / exit management system 200 is realized by a device having a function of communicating with an external device including a card reader 210 installed in the office and an arithmetic function. The entry / exit management system 200 can be realized by, for example, a general server.

[0018] Members entering and leaving the office carry an ID card that can identify an individual. A card reader 210 is installed near the entrance and exit of the office. By having the card reader 210 read the ID card, members can unlock the gate provided at the entrance and exit and enter the office. Also, members can unlock the gate and leave the office by having the card reader 210 read the ID card.

[0019] The card reader 210 corresponds to an embodiment of an "entrance and exit management device". Note that the entrance and exit management device is not limited to the card reader 210. For example, it may be configured to manage the entry and exit of members based on an image captured by a surveillance camera installed near the entrance and exit of the office.

[0020] The entrance and exit management system 200 generates "log data" in which the record of the entry and exit of members to and from the office is recorded based on the information of the ID card read by the card reader 210 and the reading time. The log data includes the ID of the member and data related to the actual record of the entry time (attendance time) and exit time (leaving time) of the member to the office. That is, the log data corresponds to the history of the entry and exit times (attendance and leaving times) of each member. The log data is used to analyze the tendency of the members' actions, as will be described later.

[0021] The entrance and exit management system 200 transmits the generated log data to the behavior analysis system 100 via the communication network NW. For example, the entrance and exit management system 200 transmits the log data generated during the period from the previous transmission timing to the current transmission timing to the behavior analysis system 100 every predetermined period (for example, one week).

[0022] The behavior analysis system 100 accumulates the log data transmitted from the access control system 200 in an internal database. The behavior analysis system 100 analyzes the behavior trends of the members using the log data stored in the database. For example, the behavior analysis system 100 analyzes the behavior trends of the members during a certain period from the log data for that period. Then, the behavior analysis system 100 accumulates "trend data" representing the behavior trends of the members obtained from the analysis in the internal database.

[0023] The behavior analysis system 100 estimates changes in the behavior of the members based on the trend data stored in the database and the log data transmitted from the access control system 200. Then, the behavior analysis system 100 determines the mental health status of the members from the estimated changes in the behavior of the members. When it is determined that the mental health status of the members is abnormal and care is required, the behavior analysis system 100 generates an alarm for prompting care for the mental health of the members and outputs it to the communication terminal device 300.

[0024] The communication terminal device 300 can be operated by a supervisor who supervises the members. The communication terminal device 300 is composed of a terminal device such as a PC (Personal Computer) or PDA (Personal Digital Assistant) that can be connected to the communication network NW. The installation location of the communication terminal device 300 is not particularly limited. The communication terminal device 300 may be a mobile terminal (such as a smartphone or tablet) owned by the supervisor. When the communication terminal device 300 receives an alarm from the behavior analysis system 100, it notifies the supervisor of the alarm by displaying the alarm on the display.

[0025] <Hardware Configuration of the Behavior Analysis System> FIG. 2 is a diagram showing an example of the hardware configuration of the behavior analysis system 100 according to Embodiment 1. As shown in FIG. 2, the behavior analysis system 100 is realized by a device having a function of communicating with external devices including the entry / exit management system 200 and the communication terminal device 300 and an arithmetic function. The behavior analysis system 100 can be realized by, for example, a general server.

[0026] The behavior analysis system 100 includes a CPU (Central Processing Unit) 101, a RAM (Random Access Memory) 102, a ROM (Read Only Memory) 103, an I / F (Interface) device 104, and a storage device 105. The CPU 101, the RAM 102, the ROM 103, the I / F device 104, and the storage device 105 exchange various data through a communication bus 106.

[0027] The CPU 101 expands and executes the program stored in the ROM 103 in the RAM 102. The program stored in the ROM 103 describes the processes executed by the behavior analysis system 100. Note that in FIG. 2, a configuration in which the CPU 101 is singular is illustrated, but the behavior analysis system 100 may have a configuration with a plurality of CPUs.

[0028] The I / F device 104 is an input / output device for exchanging signals and data with external devices including the entry / exit management system 200 and the communication terminal device 300. The I / F device 104 receives log data from the entry / exit management system 200. Further, the I / F device 104 transmits an alarm generated by the CPU 101 to the communication terminal device 300.

[0029] The storage device 105 is a storage that stores various information, and stores various information for estimating the behavior tendencies and behavior changes of members. The various information includes the above-described log data and tendency data.

[0030] <Functional Configuration of Behavior Analysis System> FIG. 3 is a block diagram showing the functional configuration of the behavior analysis system 100 according to Embodiment 1. As shown in FIG. 3, the behavior analysis system 100 includes a communication unit 10, a data management unit 20, a trend analysis unit 30, a behavior change estimation unit 40, and an alarm generation unit 50. Each of these functions is realized, for example, by the CPU 101 executing a program stored in the ROM 103. Note that part or all of these functions may be configured to be realized by hardware.

[0031] The communication unit 10 communicates with the entry / exit management system 200 and the communication terminal device 300. The communication unit 10 receives log data from the entry / exit management system 200 at a predetermined cycle. As described above, the log data includes the member ID and data related to the entry / exit record of the member. The communication unit 10 transfers the received log data to the data management unit 20.

[0032] The data management unit 20 manages data exchanged between the behavior analysis system 100 and external devices, and data generated within the behavior analysis system 100. Specifically, the data management unit 20 includes an entry / exit log DB 21 and a personal behavior DB 22. Log data transmitted from the entry / exit management system 200 at a predetermined cycle is accumulated in the entry / exit log DB 21. The log data accumulated in the entry / exit log DB 21 is sorted for each member. The personal behavior DB 22 stores the trend data of each member generated by the trend analysis unit 30. The trend data is data representing the trend of the member's behavior as described above.

[0033] The trend analysis unit 30 generates member trend data by analyzing the trend of the member's behavior using the log data accumulated in the entry / exit log DB 21. The trend analysis unit 30 stores the generated member trend data in the personal behavior DB 22.

[0034] Figure 4 is a diagram for explaining an example of trend data. The horizontal axis of Figure 4 indicates the date and time, and the vertical axis indicates the time. The black dot in the figure indicates the actual record of a member's entry time. Each point is a plot of the actual record of the entry time included in the member's log data stored in the entry / exit log DB21. Figure 4 shows the actual record of the member's entry time over a two-year period from April 1, 2023 to April 1, 2025.

[0035] The trend analysis unit 30 analyzes the trend of the member's behavior from the actual record of the entry time over these two years. For example, the trend analysis unit 30 obtains the member's entry time range by statistically processing the actual record of the entry time over two years. The square frame in the figure represents the member's entry time range. In the example of Figure 4, the time from 7:40 am to 8:30 am is calculated as the entry time range. The calculated entry time range is stored in the individual behavior DB22 as trend data representing the trend of the member's behavior.

[0036] Note that the trend analysis unit 30 can periodically update the member's trend data by repeatedly analyzing the trend of the member's behavior described above at a predetermined cycle. Alternatively, by analyzing the log data for a predetermined period, the trend data of the member for that period can be obtained as reference data.

[0037] Returning to Figure 3, the behavior change estimation unit 40 estimates the change in the member's behavior based on the trend data stored in the individual behavior DB22 and the log data transmitted from the entry / exit management system 200. Specifically, the behavior change estimation unit 40 estimates whether the actual record of the member's entry and exit times included in the log data deviates from the trend of the member's behavior represented by the trend data.

[0038] FIG. 5 is a diagram for explaining a first example of the processing in the behavior change estimation unit 40. In FIG. 5, the actual entry times (black dots in the figure) of a certain member from April 1, 2023 to November 30, 2023, and the entry time range (square frame in the figure) of the member obtained from the actual entry times are shown. In the example of FIG. 5, the time from 7:50 am to 8:10 am is obtained as the entry time range.

[0039] Assume a situation where the actual entry time of the member included in the log data dated December 1, 2023 is 11:20 am. The white dot in the figure indicates the actual entry time of the member on December 1. As is clear from FIG. 5, the entry time on December 1 deviates significantly from the entry time range of the member. In this case, the behavior change estimation unit 40 estimates that the behavior of the member has changed. The behavior change estimation unit 40 generates "behavior change data" indicating that the behavior of the member has changed, and stores the generated behavior change data in the personal behavior DB 22.

[0040] As described above, in the first example, the behavior change estimation unit 40 is configured to estimate whether the behavior of the member has changed by comparing one piece of log data (the actual entry time on a certain day) with the trend data (the entry time range). Specifically, the behavior change estimation unit 40 estimates that the behavior of the member has changed when the difference between the actual entry time included in the log data and the entry time range included in the trend data exceeds a predetermined threshold. The behavior change estimation unit 40 stores the behavior change data including information regarding the log data for which the behavior of the member is estimated to have changed in the personal behavior DB 22.

[0041] FIG. 6 is a diagram for explaining a second example of the processing in the behavior change estimation unit 40. In FIG. 6, as in FIG. 5, the actual entry times (black dots in the figure) of a certain member from April 1, 2023 to November 30, 2023, and the entry time range (square frame in the figure) of the member obtained from the actual entry times are shown. The entry time range is the time from 7:50 am to 8:10 am.

[0042] In such a situation, assume that the actual record of the member's entry time included in the log data after December 1, 2023 continuously deviates from the entry time range. The white dots in the figure indicate the actual record of the member's entry time after December 1, 2023. In the example of FIG. 6, for approximately two months from December 1, 2023, most of the actual records of the entry time deviate from the entry time range. In this case, the behavior change estimation unit 40 estimates that the member's behavior has changed. The behavior change estimation unit 40 generates behavior change data and stores the generated behavior change data in the personal behavior DB 22.

[0043] Thus, in the second example, the behavior change estimation unit 40 is configured to estimate whether the member's behavior has changed by comparing a plurality of temporally continuous log data (the actual record of the entry time for several days) with the trend data (the entry time range). The behavior change estimation unit 40 compares the actual record of the entry time included in each log data with the entry time range included in the trend data. Then, when the number of times or the period in which the actual record of the entry time deviates from the entry time range exceeds a predetermined threshold, the behavior change estimation unit 40 estimates that the member's behavior has changed. That is, in the second example, the behavior change estimation unit 40 compares the trend of the member's behavior represented by the trend data with the trend of the member's behavior appearing in a plurality of temporally continuous log data, and estimates that the member's behavior has changed when the two are different.

[0044] Note that in the second example, in addition to the above-described processing, the behavior change estimation unit 40 can analyze the trend of the member's behavior appearing in a plurality of temporally continuous log data and store the analysis result in the personal behavior DB 22 as behavior change data. Also, in the present embodiment, the behavior change data is configured to be accumulated in the personal behavior DB 22, but another DB for storing the behavior change data may be provided in the data management unit 20.

[0045] Returning to FIG. 3, the alert generation unit 50 determines the mental health status of the member based on the behavior change data stored in the personal behavior DB 22. Specifically, the alert generation unit 50 determines whether the change in the member's behavior indicated by the behavior change data is due to a mental disorder of the member. When it is determined that the change in the member's behavior is due to a mental disorder of the member, the alert generation unit 50 generates an alert for prompting care for the member's mental state and notifies the communication terminal device 300. Note that the method of notifying the communication terminal device 300 of the alert may be, for example, in the form of an e-mail, or a web page may be generated and transmitted to the communication terminal device 300.

[0046] For the determination of mental disorder by the alert generation unit 50, for example, a plurality of parameters such as the number of times the member's behavior has changed, the period during which the behavior has changed, and the degree of change in the behavior can be used. In one aspect, when at least one of these multiple parameters exceeds a predetermined threshold, the alert generation unit 50 determines that the change in the member's behavior is due to a mental disorder of the member. In another aspect, when all of the multiple parameters exceed a predetermined threshold, the alert generation unit 50 determines that the change in the member's behavior is due to a mental disorder of the member.

[0047] For example, as shown in FIG. 5, in a configuration where the change in the member's behavior is estimated when the actual record of the member's entry time on a certain day deviates from the member's entry time range, the alert generation unit 50 determines that the change in the member's behavior is due to a mental disorder of the member when at least one of the number of times the actual record of the entry time deviates from the entry time range and the degree of deviation exceeds the threshold. On the contrary, when both the number of times the actual record of the entry time deviates from the entry time range and the degree of deviation are less than the threshold, it is determined that the change in the member's behavior is due to a factor other than a mental disorder of the member.

[0048] Alternatively, as shown in FIG. 6, in a configuration where a change in the behavior of a member is estimated when the actual record of the member's entry time continuously deviates from the member's entry time range, the alarm generation unit 50 determines that the change in the member's behavior is due to a mental disorder of the member in response to at least one of the period during which the actual record of the entry time deviates from the entry time range and the degree of the deviation exceeding a threshold value.

[0049] FIG. 7 is a flowchart showing an example of the procedure of processing executed by the behavior analysis system 100 according to Embodiment 1. A series of processes shown in this flowchart are executed when a predetermined condition is satisfied (for example, every predetermined period). Each step is realized by software processing by the CPU 101, but may also be realized by hardware (electric circuit) arranged in the behavior analysis system 100. Hereinafter, the steps are abbreviated as "S".

[0050] As shown in FIG. 7, in S10, the behavior analysis system 100 accumulates the log data transmitted from the entrance / exit management system 200 at a predetermined period in the entrance / exit log DB 21. The log data accumulated in the entrance / exit log DB 21 is sorted for each member.

[0051] In S20, the behavior analysis system 100 analyzes the tendency of the member's behavior using the log data accumulated in the entrance / exit log DB 21. In S20, for example, as shown in FIG. 4, the entry time range of the member is obtained by statistically processing the actual record of the entry time included in the log data. Alternatively, the exit time range of the member is obtained by statistically processing the actual record of the exit time included in the log data.

[0052] In S30, the behavior analysis system 100 stores the generated member trend data in the personal behavior DB 22. When the process of S20 is executed periodically, the member trend data stored in the personal behavior DB 22 is updated periodically. Alternatively, when the process of S20 is executed based on the log data for a predetermined period, the member trend data stored in the personal behavior DB 22 is fixed as reference data.

[0053] In S40, the behavior analysis system 100 estimates the change in the member's behavior based on the trend data stored in the personal behavior DB 22 and the log data transmitted from the entry / exit management system 200. In S40, the behavior analysis system 100 compares the log data with the trend data and determines whether the log data deviates from the trend data. When the log data deviates from the trend data, the behavior analysis system 100 estimates the change in the member's behavior in consideration of the number of deviations, the degree of deviation, and the period of deviation. The behavior analysis system 100 generates behavior change data based on the estimation result and stores the generated behavior change data in the personal behavior DB 22.

[0054] In S50, the behavior analysis system 100 determines whether it is necessary to generate an alarm for prompting the care of the member's mental state based on the behavior change data accumulated in the personal behavior DB 22. In S50, the behavior analysis system 100 uses a plurality of parameters obtained from the behavior change data (the number of times the behavior has changed, the period during which the behavior has changed, the degree of change in the behavior) to determine whether the change in the member's behavior is due to a disorder in the member's mental state.

[0055] When it is determined that the change in the member's behavior is due to a disorder in the member's mental state, the behavior analysis system 100 proceeds to S60 and generates an alarm for prompting the care of the member's mental state. In S70, the behavior analysis system 100 notifies the generated alarm to the communication terminal device 300.

[0056] As described above, according to the behavior analysis system according to Embodiment 1, changes in the behavior of a member (for example, an employee or a student) are estimated from the log data of the member's entry and exit. And when it is determined that the change in the behavior is due to a mental disorder of the member, an alarm for prompting care for the mental state of the member is notified to the supervisor of the member. According to this, by using an existing system called an entrance and exit management system, the supervisor can objectively grasp the changes in the behavior of each member. As a result, without introducing a new system for monitoring the mental health state of the members, it is possible to detect early the mental disorders of each member and appropriately perform care for recovering the mental state of the members.

[0057] [Embodiment 2] In addition to the mental health state of the member, factors that cause changes in the behavior of the member include events that occur accidentally in the environment surrounding the member. There are cases where the behavior of the member is forcibly changed due to the occurrence of an event (external factor) that the member cannot control. In order to accurately grasp the change in behavior due to the mental health state of the member, it is necessary to exclude the change in behavior due to the occurrence of such an event. In Embodiment 2, a behavior analysis system that takes into account the occurrence of events will be described.

[0058] FIG. 8 is a schematic configuration diagram of the behavior analysis system 100 according to Embodiment 2. The behavior analysis system 100 according to Embodiment 2 is different from the behavior analysis system 100 according to Embodiment 1 shown in FIG. 1 in that it is communicatively connected to the communication terminal device 400 and the external server 500 via the communication network NW.

[0059] The communication terminal device 400 can be operated by a member. The communication terminal device 400 is composed of a terminal device such as a PC or a PDA that can be connected to the communication network NW. The installation location of the communication terminal device 400 is not particularly limited. The communication terminal device 400 may be a mobile terminal (such as a smartphone or a tablet) owned by the member.

[0060] By operating the communication terminal device 400, a member can input information regarding an event that occurred in the environment surrounding the member (hereinafter, also referred to as "event information"). The event information includes, for example, information indicating that a delay has occurred in the operation status of a public transportation means used by the member for commuting, and information regarding the weather that affects commuting, such as snow accumulation or storm.

[0061] The external server 500 includes, for example, a weather server. The weather server is configured to output weather information in the search area to the behavior analysis system 100 via the communication network NW. The weather information includes information regarding the weather for each time zone of the day in the search area. The search area can be set to include the location of the member's home and the location of the office. The location of the member's home can be specified, for example, from the location information of the communication terminal device 400 held by the member.

[0062] The external server 500 includes, for example, a traffic server that manages the operation of public transportation means. The traffic server is configured to output the operation information of public transportation means in the above search area to the behavior analysis system 100 via the communication network NW. The operation information of public transportation means includes the operation schedule of public transportation means for each time zone of the day in the search area.

[0063] The behavior analysis system 100 accumulates the event information transmitted from the communication terminal device 400 and / or the external server 500 in an internal database. FIG. 9 is a block diagram showing the functional configuration of the behavior analysis system 100 according to Embodiment 2. The behavior analysis system 100 according to Embodiment 2 differs from the behavior analysis system 100 according to Embodiment 1 in the configuration of the data management unit 20. As shown in FIG. 9, the data management unit 20 according to Embodiment 2 is obtained by adding an event log DB 23 to the data management unit 20 according to Embodiment 1.

[0064] The event log DB23 stores event information transmitted from the communication terminal device 400 and / or the external server 500. The behavior change estimation unit 40 estimates changes in the behavior of the members based on the tendency data stored in the individual behavior DB22, the log data transmitted from the entry / exit management system 200, and the event information stored in the event log DB23.

[0065] Specifically, the behavior change estimation unit 40 estimates whether the actual entry / exit times of the members included in the log data deviate from the behavior tendencies of the members represented by the tendency data. As described in Embodiment 1, when the actual entry time deviates from the entry time range, the behavior change estimation unit 40 estimates changes in the behavior of the members in consideration of the number of deviations, the degree of deviation, and the period of deviation.

[0066] Next, the behavior change estimation unit 40 determines whether the change in the behavior of the members estimated from the log data is due to an event that occurred in the environment surrounding the members, based on the event information stored in the event log DB23. FIG. 10 is a diagram for explaining an example of the processing in the behavior change estimation unit 40. FIG. 10 shows the actual entry times (black dot points in the figure) of a certain member from April 1, 2023 to April 1, 2025, and the entry time range of the member (square frame in the figure). In the example of FIG. 10, the time from 7:50 am to 8:10 am is obtained as the entry time range of the member.

[0067] Assume a situation where the actual entry time of the member included in the log data dated September 6, 2023 is 11:10 am. The white dot point in the figure indicates the actual entry time of the member on September 6. As is clear from FIG. 10, the entry time on September 6 deviates significantly from the entry time range of the member.

[0068] In this case, the behavior change estimation unit 40 reads out the event information for September 6, 2023 from the event information stored in the event log DB 23. For example, if the event information for September 6, 2023 includes information indicating that a delay has occurred in the operation status of the transportation means, the behavior change estimation unit 40 determines that the fact that the actual arrival time on September 6, 2023 deviates from the arrival time range is due to an event (delay in the transportation means) occurring in the environment surrounding the member. In this case, the behavior change estimation unit 40 estimates that the behavior of the member has not changed as of September 6, 2023. Therefore, the behavior change estimation unit 40 does not generate behavior change data.

[0069] Furthermore, in the example of FIG. 10, the actual arrival times included in the log data for the period from December 15, 2023 to February 28, 2024 continuously deviate from the arrival time range. The white dots in the figure indicate the actual arrival times of the member during the period. As is clear from FIG. 10, the arrival times during the period deviate from the arrival time range.

[0070] The behavior change estimation unit 40 reads out the event information for the period from December 15, 2023 to February 28, 2024 from the event information stored in the event log DB 23. For example, if the event information for the period includes snow accumulation information, the behavior change estimation unit 40 determines that the fact that the actual arrival times for the period deviate from the arrival time range is due to an event (delay due to snow accumulation) occurring in the environment surrounding the member. In this case, the behavior change estimation unit 40 estimates that the behavior of the member has not changed during the period. Therefore, the behavior change estimation unit 40 does not generate behavior change data.

[0071] On the contrary, if there is no event information in the event log DB 23 for the date and time or period when the actual arrival time deviates from the arrival time range, the behavior change estimation unit 40 estimates that the behavior of the member has changed. Therefore, the behavior change estimation unit 40 generates behavior change data and stores it in the individual behavior DB 22.

[0072] The processing executed by the behavior analysis system 100 according to the second embodiment described above can be summarized in the flowchart shown in FIG. 7. However, the content of the process in S40 of FIG. 7 is different from that of the behavior analysis system 100 according to the first embodiment. FIG. 11 is a flowchart showing the content of the process in S40 of FIG. 7.

[0073] As shown in FIG. 11, first in S40, the behavior analysis system 100 compares, by S401, the tendency data stored in the individual behavior DB 22 with the log data transmitted from the entrance / exit management system 200, and determines whether the log data deviates from the tendency data.

[0074] If the log data does not deviate from the tendency data (when the determination in S401 is NO), the behavior analysis system 100 estimates, by S405, that the behavior of the member has not changed.

[0075] On the other hand, when the log data deviates from the tendency data (when the determination in S401 is YES), the behavior analysis system 100 estimates, by S402, whether the behavior of the member has changed in consideration of the number of times the log data deviates from the tendency data, the degree of deviation, and the period of deviation. If any of the number of times the log data deviates from the tendency data, the degree of deviation, and the period of deviation is less than the threshold value, the behavior analysis system 100 estimates, by S405, that the behavior of the member has not changed.

[0076] On the other hand, if at least one of the number of times the log data deviates from the trend data, the degree of deviation, and the period of deviation satisfies a threshold value and it is estimated that the behavior of the member has changed (when the determination in S402 is YES), the behavior analysis system 100, in S403, determines whether the change in the behavior of the member is due to the occurrence of an event by referring to the event information at the date and time or during the period when the log data deviates from the trend data. If no event has occurred at the date and time or during the period when the log data deviates from the trend data, S403 makes a NO determination. In this case, the behavior analysis system 100 estimates, in S404, that the behavior of the member has changed. The behavior analysis system 100 stores the behavior change data in the personal behavior DB22.

[0077] Conversely, if an event has occurred at the date and time or during the period when the log data deviates from the trend data, S403 makes a YES determination. In this case, the behavior analysis system 100 estimates, in S405, that the behavior of the member has not changed.

[0078] By performing the above-described processing, only the behavior change data indicating the change in the behavior of the member not due to the events occurring in the environment surrounding the member is accumulated in the personal behavior DB22. Therefore, it is possible to exclude the fact that the behavior of the member has changed due to the event from the change in the behavior of the member. According to this, it becomes possible to accurately grasp the change in the behavior due to the mental health state of the member.

[0079] [Embodiment 3] In addition to the above-described accidental events, the behavior of the member can also change due to a change in the environment based on the member's own will. In order to accurately grasp the change in the behavior due to the mental health state of the member, it is necessary to exclude the change in the behavior due to such a change in the member's environment. In Embodiment 3, a behavior analysis system considering the change in the member's environment will be described.

[0080] FIG. 12 is a block diagram showing the functional configuration of the behavior analysis system 100 according to Embodiment 3. The behavior analysis system 100 according to Embodiment 3 differs from the behavior analysis system 100 according to Embodiment 1 in the configuration of the data management unit 20. As shown in FIG. 12, the data management unit 20 according to Embodiment 3 is obtained by adding a personal environment DB 24 to the data management unit 20 according to Embodiment 1.

[0081] The personal environment DB 24 stores data related to the environment surrounding the members (hereinafter also referred to as "environment data"). The environment data includes, for example, data related to changes in the environment of the members, such as the marriage of the members, the birth of the members or their spouses, and the transfer of residence.

[0082] The member can input the member's environment data by operating the communication terminal device 400. Alternatively, the supervisor can input the member's environment data obtained through an interview with the member or the like using the communication terminal device 300.

[0083] The behavior change estimation unit 40 estimates changes in the behavior of the member based on the trend data stored in the personal behavior DB 22, the log data transmitted from the entry / exit management system 200, and the environment data stored in the personal environment DB 24.

[0084] Specifically, the behavior change estimation unit 40 estimates whether the actual record of the member's entry / exit time included in the log data deviates from the behavior trend of the member represented by the trend data. As described in Embodiment 1, when the actual record of the entry time deviates from the entry time range, the behavior change estimation unit 40 estimates the change in the member's behavior in consideration of the number of deviations, the degree of deviation, and the period of deviation.

[0085] Next, the behavior change estimation unit 40 determines whether the estimated change in the member's behavior is due to a change in the member's environment based on the environmental data stored in the personal environment DB 24. FIG. 13 is a diagram for explaining an example of the processing in the behavior change estimation unit 40. In FIG. 13, the actual entry times (black dot points in the figure) of a certain member from April 1, 2023 to April 1, 2025 and the member's entry time range (square frame in the figure) are shown. In the example of FIG. 13, the time from 7:50 am to 8:10 am is obtained as the entry time range.

[0086] In such a situation, assume that the actual entry times of the member included in the log data after October 1, 2023 deviate from the member's previous entry time range. In the example of FIG. 13, after October 1, 2023, the actual entry times of the member are concentrated in a time zone later than the entry time range.

[0087] In this case, the behavior change estimation unit 40 reads the member's environmental data from the personal environment DB 24. For example, if the environmental data contains information indicating that the member moved on October 1, 2023, the behavior change estimation unit 40 determines that the deviation of the actual entry times after October 1, 2023 from the entry time range is due to a change in the member's environment (move). In this case, the behavior change estimation unit 40 estimates that the member's behavior has not changed after October 1, 2023. Therefore, the behavior change estimation unit 40 does not generate behavior change data.

[0088] On the contrary, if it is determined that the member's environment has not changed during the date and time or period when the actual entry time deviates from the entry time range by referring to the member's environmental data, the behavior change estimation unit 40 estimates that the member's behavior has changed. Therefore, the behavior change estimation unit 40 generates behavior change data and stores it in the personal behavior DB 22.

[0089] The processes executed by the behavior analysis system 100 according to the third embodiment described above can be summarized in the flowchart shown in FIG. 7. However, the content of the process in S40 of FIG. 7 is different from that of the behavior analysis system 100 according to the first embodiment. FIG. 14 is a flowchart showing the content of the process in S40 of FIG. 7.

[0090] As shown in FIG. 14, first in S40, the behavior analysis system 100 compares, by S401, the tendency data stored in the individual behavior DB 22 with the log data transmitted from the entry / exit management system 200, and determines whether the log data deviates from the tendency data.

[0091] If the log data does not deviate from the tendency data (when the determination in S401 is NO), the behavior analysis system 100 estimates, by S405, that the behavior of the member has not changed.

[0092] On the other hand, when the log data deviates from the tendency data (when the determination in S401 is YES), the behavior analysis system 100 estimates, by S402, whether the behavior of the member has changed in consideration of the number of times the log data deviates from the tendency data, the degree of deviation, and the period of deviation. If any of the number of times the log data deviates from the tendency data, the degree of deviation, and the period of deviation is less than the threshold value, the behavior analysis system 100 estimates, by S405, that the behavior of the member has not changed.

[0093] On the other hand, when at least one of the number of times the log data deviates from the trend data, the degree of deviation, and the period of deviation satisfies the threshold value and it is estimated that the behavior of the member has changed (when the determination in S402 is YES), the behavior analysis system 100, in S406, determines whether the change in the member's behavior is due to a change in the member's environment by referring to the environmental data at the date and time or during the period when the log data deviates from the trend data. If the member's environment has not changed at the date and time or during the period when the log data deviates from the trend data, S406 determines NO. In this case, the behavior analysis system 100 estimates, in S404, that the member's behavior has changed. The behavior analysis system 100 stores the behavior change data in the personal behavior DB22.

[0094] Conversely, if the member's environment has changed at the date and time or during the period when the log data deviates from the trend data, S406 determines YES. In this case, the behavior analysis system 100 estimates, in S405, that the member's behavior has not changed.

[0095] As described above, according to the behavior analysis system 100 according to the third embodiment, it is possible to exclude that the behavior of the member has changed due to a change in the member's environment from the change in the member's behavior. According to this, it is possible to accurately grasp the change in behavior due to the mental health state of the member.

[0096] [Embodiment 4] In the above-described first embodiment, a configuration has been described in which, from the behavior change data accumulated in the personal behavior DB22, using a plurality of parameters such as the number of times the member's behavior has changed, the period during which the behavior has changed, and the degree of change in the behavior, it is determined whether the change in the member's behavior is due to a mental disorder of the member.

[0097] However, with the above configuration, there is a concern that the mental discomfort of the member cannot be detected until at least one of the plurality of parameters exceeds the threshold value. Therefore, in Embodiment 4, a configuration for detecting changes in the mental health state of the member earlier will be described.

[0098] FIG. 15 is a block diagram showing the functional configuration of the behavior analysis system 100 according to Embodiment 4. The behavior analysis system 100 according to Embodiment 4 differs from the behavior analysis system 100 according to Embodiment 1 in the configuration of the data management unit 20. As shown in FIG. 15, the data management unit 20 according to Embodiment 4 differs from the data management unit 20 according to Embodiment 1 in that it includes a plurality of individual behavior DBs 22A, 22B, ···. Hereinafter, the plurality of individual behavior DBs 22A, 22B, ··· may be collectively referred to as "individual behavior DB 22".

[0099] The entry / exit management system 200 generates log data in which the actual entry / exit times of a plurality of members (for example, Member A, Member B, ···) are recorded, and transmits the generated log data to the behavior analysis system 100 via the communication network NW. The log data of the plurality of members is stored in the entry / exit log DB 22.

[0100] The plurality of individual behavior DBs 22 are provided corresponding to the plurality of members respectively. The individual behavior DB 22A stores the attribute data of Member A. The individual behavior DB 22B stores the attribute data of Member B. The attribute data of the member includes information such as the member's gender, age, occupation, department to which the member belongs, address, and family composition.

[0101] Member A can input his own attribute data by operating his own communication terminal device 400A. Member B can input his own attribute data by operating his own communication terminal device 400B. Although not shown, the attribute data of other members is similarly stored in the corresponding individual behavior DB 22.

[0102] The tendency analysis unit 30 analyzes the behavior tendencies for each member from the log data stored in the entry / exit log DB 22. The tendency analysis unit 30 stores the tendency data of member A in the individual behavior DB 22A, and stores the tendency data of member B in the individual behavior DB 22B. The tendency data of other members are similarly stored in the corresponding individual behavior DB 22.

[0103] The behavior change estimation unit 40 estimates the change in behavior for each member based on the tendency data stored in the individual behavior DB 22 and the log data transmitted from the entry / exit management system 200. The behavior change estimation unit 40 stores the behavior change data of member A in the individual behavior DB 22A. The behavior change estimation unit 40 stores the behavior change data of member B in the individual behavior DB 22B. The behavior change data of other members are similarly stored in the corresponding individual behavior DB 22. That is, in each individual behavior DB 22, the behavior change data of each member and the attribute data of that member are stored in association with each other.

[0104] The warning generation unit 50 determines the mental health state of each member based on the behavior change data of a plurality of members stored in a plurality of individual behavior DB 22. Specifically, the warning generation unit 50 divides a plurality of members into a plurality of groups composed of members having the same attribute based on the attribute data stored in each individual behavior DB 22. The grouping conditions can be arbitrarily set by the user (for example, supervisor) of the behavior analysis system 100. For example, members with the same gender and age group can form one group. Alternatively, members with the same age group and job type can form one group.

[0105] Next, the warning generation unit 50 reads out the behavior change data of the plurality of members constituting the group for one of the plurality of groups from the individual behavior DB 22. For example, when member A and member B belong to the same group, the warning generation unit 50 reads out the behavior change data of member A from the individual behavior DB 22A and reads out the behavior change data of member B from the individual behavior DB 22B.

[0106] Next, the warning generation unit 50 compares the behavior change data of a plurality of members. Specifically, the warning generation unit 50 determines whether the patterns of behavior changes of the plurality of members are similar. For example, the warning generation unit 50 calculates, from the behavior change data of each member, as parameters representing the pattern of behavior change, the number of times the behavior has changed, the period during which the behavior has changed, and the degree of change in the behavior. Then, the warning generation unit 50 determines whether the behavior change patterns are similar based on whether the values of these parameters are approximate.

[0107] When the patterns of behavior changes of a plurality of members are similar, the warning generation unit 50 determines that the change in the behavior of the member is not peculiar and is normal for members having the same attributes. For example, when the period during which the actual entry time of member A deviates from the entry time range overlaps with the period during which the actual entry time of member B deviates from the entry time range, the warning generation unit 50 determines that the behavior change pattern of member A is similar to the behavior change pattern of member B. In this case, the warning generation unit 50 determines that the change in the behavior of member A is not due to a mental disorder of member A himself / herself, but due to another factor (for example, a change in the working environment). Therefore, the warning generation unit 50 determines that it is not necessary to generate a warning to prompt care for the mental state of member A.

[0108] On the contrary, when the patterns of behavioral changes of multiple members are not similar, the alarm generation unit 50 identifies the member with the largest amount of behavioral change. The amount of behavioral change can be calculated based on the values of the parameters representing the patterns of behavioral changes described above. If there is a member among multiple members with the same attribute whose amount of behavioral change is large compared to other members, it is presumed that the behavioral change of this member is peculiar. For example, when the period during which the actual arrival time of member A deviates from the arrival time range is longer than the period during which the actual arrival time of member B deviates from the arrival time range, the alarm generation unit 50 determines that the pattern of behavioral change of member A and the pattern of behavioral change of member B are not similar. In this case, the alarm generation unit 50 determines that the behavioral change of member A may be due to a mental disorder of member A, and determines that it is necessary to generate an alarm to prompt care for the mental state of member A.

[0109] The processes executed by the behavior analysis system 100 according to the fourth embodiment described above can be summarized in the flowchart shown in FIG. 7. However, the processing contents of S50 and S60 in FIG. 7 are different from those of the behavior analysis system 100 according to the first embodiment. FIG. 16 is a flowchart showing the processing contents of S50 and S60 in FIG. 7.

[0110] As shown in FIG. 16, first in S50, the behavior analysis system 100 compares the behavior change data of multiple members having the same attribute by S501. In S501, the behavior analysis system 100 determines whether the patterns of behavioral changes of multiple members are similar based on the values of the parameters (the number of times the behavior has changed, the period during which the behavior has changed, and the degree of change in the behavior, etc.) obtained from the behavior change data of each member.

[0111] When the patterns of behavioral changes of multiple members are similar (when the determination in S502 is YES), the behavior analysis system 100 determines that the behavioral changes of each member are not peculiar and skips the processing of S503.

[0112] When the patterns of behavior changes of multiple members are not similar (when the determination at S502 is NO), the behavior analysis system 100 identifies, at S503, the member among the multiple members whose amount of behavior change is the largest. The behavior analysis system 100 determines that the behavior change of the identified member may be due to a mental disorder of this member, and generates an alarm for prompting care for the mental state of the member. In S70 of FIG. 7, the behavior analysis system 100 notifies the generated alarm to the communication terminal device 300.

[0113] As described above, according to the behavior analysis system 100 according to the fourth embodiment, by comparing the behavior change data of multiple members having the same attribute, it is possible to determine whether the behavior change of each member is a specific one not seen in other members or a normal one seen in multiple members. Further, when the behavior change of a member is specific, the behavior change can be grasped early. According to this, it becomes possible to discover the change in the mental health state of the member earlier.

[0114] [Embodiment 5] FIG. 17 is a block diagram showing the functional configuration of the behavior analysis system 100 according to the fifth embodiment. The behavior analysis system 100 according to the fifth embodiment differs from the behavior analysis system 100 according to the first embodiment in the configuration of the data management unit 20. As shown in FIG. 17, the data management unit 20 according to the fifth embodiment is obtained by adding an alarm DB 25 to the data management unit 20 according to the first embodiment.

[0115] The alarm DB 25 includes an alarm table indicating the types of alarms generated by the alarm generation unit 50. FIG. 18 is a diagram showing an example of the alarm table. As shown in FIG. 18, the alarm table includes data related to the pattern of behavior change. The pattern of behavior change is expressed by, for example, the speed and frequency at which the behavior changes. For example, the patterns of behavior change include patterns such as "the behavior is changing gradually", "the frequency of behavior change is increasing", and "the behavior has suddenly changed".

[0116] The warning table further includes data regarding multiple types of warnings. Each warning represents the content of care necessary to recover the mental discomfort of the member. For example, the types of warnings include warnings such as "require observation", "hearing by supervisor is necessary", and "medical examination by a specialized institution is necessary".

[0117] In the warning table, a pattern of behavior change is associated with the type of warning. For example, in the first row of the warning table, a warning of "require observation" is associated with the pattern of behavior change of "behavior is gradually changing". In the second row of the warning table, a warning of "hearing by supervisor is necessary" is associated with the pattern of behavior change of "the frequency of behavior change is increasing". In the third row of the warning table, a warning of "medical examination by a specialized institution is necessary" is associated with the pattern of behavior change of "behavior has suddenly changed". Regarding the correspondence between the pattern of behavior change and the type of warning, it can be set by the user (for example, supervisor) of the behavior analysis system 100.

[0118] Returning to FIG. 17, when the warning generation unit 50 calculates the pattern of the member's behavior change from the behavior change data read from the individual behavior DB 22, by referring to the warning table shown in FIG. 18, it determines the type of warning based on the calculated pattern of behavior change and generates a warning of the determined type.

[0119] According to the behavior analysis system 100 according to Embodiment 5, by generating a warning according to the pattern of the member's behavior change, the supervisor can implement appropriate care for the mental health state of the member.

[0120] [Other configuration examples] In the above-described embodiment, the configuration for analyzing the behavior of members using log data regarding the attendance records (entry and exit times) of members to and from facilities such as offices and schools has been described. However, it is also possible to use log data regarding the attendance records for some areas within the facility (for example, members' living quarters, toilets, rest rooms, etc.) to analyze the behavior of members.

[0121] [Appendix] The above-described embodiment is a specific example of the following appendix.

[0122] (Appendix 1) A behavior analysis system for analyzing the behavior of members belonging to an organization, a communication unit that communicates with an entry / exit management system for managing the entry and exit of the member to a predetermined area used by the member, a first database that accumulates log data in which the attendance records of the member are recorded, received by the communication unit from the entry / exit management system, a processor, and a memory that stores a program executed by the processor, wherein the processor, according to the program, generates trend data representing the tendency of the behavior of the member by analyzing the log data accumulated in the first database, estimates a change in the behavior of the member by comparing the log data received by the communication unit from the entry / exit management system with the trend data, determines the mental health state of the member from the estimated change in the behavior of the member, and generates an alarm for prompting care for the mental aspect of the member based on the determination result of the health state.

[0123] (Appendix 2) When the log data received from the entry / exit management system deviates from the trend data, the processor estimates a change in the behavior of the member based on at least one of the number of deviations, the period of deviation, and the degree of deviation, according to the behavior analysis system described in Appendix 1.

[0124] (Appendix 3) When the behavior of the member has changed, the processor determines the mental health state of the member based on at least one of the number of times the behavior has changed, the period during which the behavior has changed, and the degree of change in the behavior, according to the behavior analysis system described in Appendix 1 or 2.

[0125] (Appendix 4) The communication unit is configured to receive event information regarding an event that occurred in the environment surrounding the member. The communication unit further includes a second database for storing the event information received by the communication unit. The processor When the log data received from the entry / exit management system deviates from the trend data, the processor determines whether the deviation is due to the occurrence of the event by referring to the event information. When it is determined that the deviation is due to the occurrence of the event, the processor estimates that the behavior of the member has not changed, according to the behavior analysis system described in any one of Appendices 1 to 3.

[0126] (Appendix 5) The communication unit is configured to receive environmental data regarding the environment surrounding the member. The communication unit further includes a third database for storing the environmental data received by the communication unit. The processor When the log data received from the entry / exit management system deviates from the trend data, the processor determines whether the deviation is due to a change in the environment of the member by referring to the environmental data. When it is determined that the deviation is due to a change in the environment of the member, it is presumed that the behavior of the member has not changed. The behavior analysis system according to any one of Appendices 1 to 4.

[0127] (Appendix 6) The first database is configured to store the log data of a plurality of members. The processor By analyzing the log data of the plurality of members stored in the first database, the tendency data of each member is generated. By comparing the log data of each member received by the communication unit from the entry / exit management system with the tendency data of the member, a change in the behavior of each member is estimated. Compare the changes in the behavior of members having the same attribute among the plurality of members. When the changes in the behavior of the members having the same attribute are not similar, an alarm is generated for the member having the largest change in behavior amount among the members having the same attribute. The behavior analysis system according to any one of Appendices 1 to 5.

[0128] (Appendix 7) When the changes in the behavior of the members having the same attribute are similar, the processor does not generate the alarm for the members having the same attribute. The behavior analysis system according to Appendix 6.

[0129] (Appendix 8) Further include a fourth database that stores a table associating the pattern of behavior change with the type of alarm. The processor determines the type of alarm to be generated based on the pattern of the estimated change in the behavior of the member by referring to the table. The behavior analysis system according to any one of Appendices 1 to 7.

[0130] (Appendix 9) A behavior analysis method for analyzing the behavior of members belonging to an organization, A step in which a processor receives log data in which the record of the member's entry and exit from a predetermined area used by the member is recorded from an entry / exit management system that manages the member's entry and exit to and from the predetermined area; A step in which the processor stores the log data received from the entry / exit management system in a first database; A step in which the processor generates trend data representing the tendency of the member's behavior by analyzing the log data stored in the first database; A step in which the processor estimates the change in the member's behavior by comparing the log data received from the entry / exit management system with the trend data; A step in which the processor determines the mental health state of the member from the estimated change in the member's behavior, and generates an alarm prompting care for the member's mental aspect based on the determination result of the health state. An action analysis method comprising the above steps.

[0131] (Appendix 10) A step in which the processor receives event information regarding an event occurring in the environment surrounding the member; The processor further comprises a step of storing the received event information in a second database, The step of estimating the change in the member's behavior is When the log data received from the entry / exit management system deviates from the trend data, a step of determining whether the deviation is due to the occurrence of the event by referring to the event information; The action analysis method according to Appendix 9, comprising a step of estimating that the member's behavior has not changed when it is determined that the deviation is due to the occurrence of the event.

[0132] (Appendix 11) A step in which the processor receives environmental data regarding the environment surrounding the member; further comprising the step of storing the received environmental data in a third database; The step of estimating a change in the behavior of the member includes: when the log data received from the entry / exit management system deviates from the trend data, determining whether the deviation is due to a change in the environment of the member by referring to the environmental data; when it is determined that the deviation is due to a change in the environment of the member, estimating that the behavior of the member has not changed, the behavior analysis method according to Appendix 9 or Appendix 10.

[0133] (Appendix 12) The first database is configured to store the log data of a plurality of members; The step of generating the trend data includes generating the trend data of each member by analyzing the log data of the plurality of members stored in the first database; The step of estimating a change in the behavior of the member includes estimating a change in the behavior of each member by comparing the log data of each member received from the entry / exit management system with the trend data of the member; The step of generating the warning includes: comparing changes in the behavior of members having the same attribute among the plurality of members; when the changes in the behavior of the members having the same attribute are not similar, generating the warning for the member having the largest change in behavior amount among the members having the same attribute, the behavior analysis method according to any one of Appendices 9 to 11.

[0134] (Appendix 13) The step of generating the warning further includes not generating the warning for the members having the same attribute when the changes in the behavior of the members having the same attribute are similar, the behavior analysis method according to Appendix 12.

[0135] (Appendix 14) It further includes a fourth database for storing a table associating the pattern of behavior change with the type of the alarm, The step of generating the alarm includes the step of determining the type of the alarm to be generated based on the pattern of the change in the behavior of the member estimated by referring to the table, according to the behavior analysis method according to any one of Appendices 9 to 13.

[0136] (Appendix 15) A program for causing a computer to execute the behavior analysis method according to any one of Appendices 9 to 14.

[0137] The configuration exemplified as the above-described embodiment is an example of the configuration of the present disclosure, and it is also possible to combine it with another known technique. It is also possible to change the configuration by omitting a part or the like without departing from the gist of the present disclosure.

[0138] The embodiment disclosed this time should be considered as illustrative in all respects and not restrictive. As long as there is no contradiction, at least two of the embodiments disclosed this time may be combined. The technical scope shown by the present disclosure is shown by the claims rather than the description of the above-described embodiments, and it is intended that all changes within the meaning and scope equivalent to the claims are included.

Explanation of Reference Numerals

[0139] 10 Communication unit, 20 Data management unit, 21 Entrance / exit log DB, 22, 22A, 22B Individual behavior DB, 23 Event log DB, 24 Individual environment DB, 25 Alarm DB, 30 Trend analysis unit, 40 Behavior change estimation unit, 50 Alarm generation unit, 100 Behavior analysis system, 101 CPU, 102 RAM, 103 ROM, 104 I / F device, 105 Storage device, 200 Entrance / exit management system, 300, 400 Communication terminal device, 500 External server.

Claims

1. An action analysis system for analyzing the actions of members belonging to an organization, comprising: a communication unit that communicates with an entrance / exit management system that manages the entrance and exit of the members to a predetermined area used by the members; a first database that stores log data in which the entrance / exit records of the members received by the communication unit from the entrance / exit management system are recorded; a processor; a memory that stores a program executed by the processor, wherein the processor, according to the program, generates tendency data representing the tendency of the actions of the members by analyzing the log data stored in the first database; estimates a change in the actions of the members by comparing the log data received by the communication unit from the entrance / exit management system with the tendency data; determines the mental health state of the members from the estimated change in the actions of the members; An action analysis system that generates an alarm prompting care for the mental aspect of the members based on the determination result of the health state.

2. The action analysis system according to claim 1, wherein when the log data received by the processor from the entrance / exit management system deviates from the tendency data, the processor estimates a change in the actions of the members based on at least one of the number of deviations, the period of deviation, and the degree of deviation.

3. The action analysis system according to claim 1 or 2, wherein the processor determines the mental health state of the members based on at least one of the number of times the actions of the members have changed, the period during which the actions have changed, and the degree of change in the actions.

4. The communication unit is configured to receive event information regarding an event occurring in the environment surrounding the members, further comprising a second database that stores the event information received by the communication unit, wherein the processor when the log data received by the processor from the entrance / exit management system deviates from the tendency data, determines whether the deviation is due to the occurrence of the event by referring to the event information; The action analysis system according to claim 1, wherein when it is determined that the deviation is due to the occurrence of the event, it is estimated that the actions of the members have not changed.

5. The communication unit is configured to receive environmental data regarding the environment surrounding the members. It further includes a third database for storing the environmental data received by the communication unit. The processor When the log data received from the entry / exit management system deviates from the trend data, by referring to the environmental data, determines whether the deviation is due to a change in the environment of the member. The behavior analysis system according to claim 1, wherein when it is determined that the deviation is due to a change in the environment of the member, it is presumed that the behavior of the member has not changed.

6. The first database is configured to store the log data of a plurality of members. The processor By analyzing the log data of the plurality of members stored in the first database, generates the trend data of each member. By comparing the log data of each member received by the communication unit from the entry / exit management system with the trend data of that member, estimates the change in the behavior of each member. Compares the changes in the behavior of members having the same attribute among the plurality of members. The behavior analysis system according to claim 1, wherein when the changes in the behavior of members having the same attribute are not similar, an alarm is generated for the member having the largest amount of change in behavior among the members having the same attribute.

7. The behavior analysis system according to claim 6, wherein the processor does not generate the alarm for the members having the same attribute when the changes in the behavior of the members having the same attribute are similar.

8. It further includes a fourth database for storing a table associating the pattern of behavior change with the type of alarm. The behavior analysis system according to claim 1, wherein the processor determines the type of alarm to be generated based on the pattern of the estimated change in the behavior of the member by referring to the table.

9. A behavior analysis method for analyzing the behavior of members belonging to an organization, comprising: A step in which a processor receives log data in which the entry / exit performance of a member is recorded from an entry / exit management system that manages the entry / exit of the member to a predetermined area used by the member. A step in which the processor stores the log data received from the entry / exit management system in a first database. The step of the processor generating trend data representing the tendency of the member's behavior by analyzing the log data stored in the first database; The step of the processor estimating a change in the member's behavior by comparing the log data received from the entry / exit management system with the trend data; The step of the processor determining the mental health state of the member from the estimated change in the member's behavior and generating an alarm prompting care for the member's mental aspect based on the determination result of the health state, an action analysis method.

10. The step of the processor receiving event information regarding an event occurring in the environment surrounding the member; The step of the processor storing the received event information in a second database, further comprising: The step of estimating a change in the member's behavior is When the log data received from the entry / exit management system deviates from the trend data, determining whether the deviation is due to the occurrence of the event by referring to the event information; The action analysis method according to claim 9, comprising the step of estimating that the member's behavior has not changed when it is determined that the deviation is due to the occurrence of the event.

11. The step of the processor receiving environmental data regarding the environment surrounding the member; The step of storing the received environmental data in a third database, further comprising: The step of estimating a change in the member's behavior is When the log data received from the entry / exit management system deviates from the trend data, determining whether the deviation is due to a change in the member's environment by referring to the environmental data; The action analysis method according to claim 9, comprising the step of estimating that the member's behavior has not changed when it is determined that the deviation is due to a change in the member's environment.

12. The first database is configured to store the log data of a plurality of members; The step of generating the trend data includes the step of generating the trend data of each member by analyzing the log data of the plurality of members stored in the first database. The step of estimating the change in the behavior of the member includes the step of estimating the change in the behavior of each member by comparing the log data of each member received from the entry / exit management system with the tendency data of the member. The step of generating the alert is the step of comparing the changes in the behavior of the members having the same attribute among the plurality of members, and when the changes in the behavior of the members having the same attribute are not similar, the step of generating the alert for the member having the largest amount of change in behavior among the members having the same attribute. The behavior analysis method according to claim 9.

13. The step of generating the alert further includes the step of not generating the alert for the members having the same attribute when the changes in the behavior of the members having the same attribute are similar. The behavior analysis method according to claim 12.

14. further comprising a fourth database storing a table associating the pattern of the behavior change with the type of the alert, the step of generating the alert includes the step of determining the type of the alert to be generated based on the pattern of the change in the behavior of the member estimated by referring to the table. The behavior analysis method according to claim 9.

15. A program for causing a computer to execute the behavior analysis method according to any one of claims 9 to 14.

Images