WO2021005750A1

WO2021005750A1 - Behavior type estimation device, behavior type estimation method, and behavior type estimation program

Info

Publication number: WO2021005750A1
Application number: PCT/JP2019/027340
Authority: WO
Inventors: 省吾厚地; 皆木　宗; 賢一小泉; 準史郎神田
Original assignee: 三菱電機株式会社
Priority date: 2019-07-10
Filing date: 2019-07-10
Publication date: 2021-01-14
Also published as: JPWO2021005750A1

Abstract

In the present invention, a position estimation unit (110) estimates the position of a user (20) in an indoor space (30). A behavior estimation unit (120) acquires a location mapping table (152) in which are configured: location areas, which represent locations in the indoor space (30); and location behavior types, which are behavior types of the user in the location areas of the indoor space (30). The behavior estimation unit (120) acquires, from the location mapping table (152), the location behavior type which corresponds to the location area matching the position of the user (20), and estimates the behavior of the user (20) on the basis of the acquired location behavior type. A behavior history generation unit (130) uses the results of estimating the behavior of the user (20) to generate a history of user behavior as behavior history information (155).

Description

Behavior type estimation device, behavior type estimation method, and behavior type estimation program

The present invention relates to a behavior type estimation device, a behavior type estimation method, and a behavior type estimation program. In particular, the present invention relates to an action type estimation device that estimates the user's behavior indoors, an action type estimation method, and an action type estimation program.

In recent years, there has been an increasing movement to support employees to improve their health. Along with such movements, a technique for automatically discriminating a person's behavior or amount of exercise is disclosed.

Patent Document 1 discloses a technique for increasing variations in behavior types of a user to be discriminated by using a plurality of data detected by a wearable sensor worn by the user. Specifically, a technique for further subdividing the behavior classified by the acceleration of the user according to the heart rate of the user is disclosed.

Japanese Unexamined Patent Publication No. 2014-212915

In the technology of Patent Document 1, a sensor such as an accelerometer that detects the movement of the user is indispensable. Therefore, the user needs to wear a wearable sensor or hold a smartphone terminal or the like. Further, when providing a service based on the information transmitted from the wearable sensor, the service provider needs to aggregate this information, and power consumption for continuous data upload becomes an issue. Further, in the case of BYOD (Bring your own device), a procedure such as obtaining permission for data aggregation from each user becomes an issue. Further, when determining the behavior type of a large number of users, it is necessary to prepare as many wearable sensors or smartphone terminals as there are users, which imposes a heavy cost burden.

An object of the present invention is to discriminate an action type at low cost with less burden on the user.

The behavior type estimation device according to the present invention is
A position estimation unit that estimates the user's position indoors,
A place correspondence table in which a place area representing a place indoors and a place action type which is an action type of the user in the place area in the room is set is acquired, and matches the position of the user from the place correspondence table. An action estimation unit that acquires a place action type corresponding to a place area and estimates the user's action based on the acquired place action type.
A behavior history generation unit that generates a history of the user's behavior as behavior history information using the estimation result of the user's behavior is provided.

The behavior type estimation device according to the present invention has an effect that the burden on the user is small and the behavior type can be discriminated at low cost.

The block diagram of the action type estimation system which concerns on Embodiment 1. FIG. The flow chart which shows the operation of the information update part which concerns on Embodiment 1. An example of personal information according to the first embodiment. An example of a place correspondence table according to the first embodiment. An example of a detailed correspondence table according to the first embodiment. An example of a place schedule according to the first embodiment. The flow chart which shows the operation of the action type estimation apparatus which concerns on Embodiment 1. The flow chart which shows the operation of the action estimation part which concerns on Embodiment 1. An example of behavior history information according to the first embodiment. The block diagram of the action type estimation system which concerns on the modification of Embodiment 1. The block diagram of the action type estimation apparatus which concerns on Embodiment 2. FIG. An example of a user calendar according to the second embodiment. The flow chart which shows the operation of the action estimation part which concerns on Embodiment 2. The flow chart which shows the operation of the action type estimation apparatus which concerns on Embodiment 3. An example of action history information according to the third embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In each figure, the same or corresponding parts are designated by the same reference numerals. In the description of the embodiment, the description will be omitted or simplified as appropriate for the same or corresponding parts.

Embodiment 1.
*** Explanation of configuration ***
The configuration of the action type estimation system 500 according to the present embodiment will be described with reference to FIG.
The action type estimation system 500 includes a user communication device 21, an indoor communication device 22, and an action type estimation device 100.
The action type estimation device 100 estimates the behavior of the user 20 in the indoor 30. For example, the indoor 30 is in the building of the company where the user 20 is working. The user 20 is an employee working indoors 30 in the company building. The company determines the amount of exercise of the employee by analyzing the behavior of the employee estimated by the behavior type estimation device 100, and supports the improvement of the health of the employee.

The user communication device 21 is a device that transmits radio waves by short-range wireless communication such as a beacon. Specifically, the user communication device 21 is built in an employee ID card, a name plate attached to the employee ID card, or a key chain or the like carried by the user 20. The user communication device 21 is a device whose cost is lower than that of a wearable terminal or a mobile terminal device, and the burden on the user 20 to carry is small.
Since the radio wave transmitted by the user communication device 21 may be beacon information, it is not necessary for the user 20 to intentionally transmit the information by operating the application or the like, and it is not necessary for the user 20 to obtain permission for transmission.

A plurality of indoor communication devices 22 are installed indoors 30 such as a company building. The indoor communication device 22 receives radio waves transmitted from the user communication device 21 for short-range wireless communication carried by the user 20. Then, the indoor communication device 22 transmits the radio wave transmitted from the user communication device 21 as a signal 31 to the action type estimation device 100. For example, the indoor communication device 22 is set indoors 30 at intervals of several meters to several tens of meters. Alternatively, the indoor communicator 22 is installed at the entrance and exit of a place in the indoor 30. The place in the indoor 30 is, for example, an area for each department or section, a reference room, a dining room, a washroom, a corridor, a staircase, an elevator, or a conference room.

Further, the user 20 may have a personal terminal 23. The personal terminal 23 is a terminal used by the user 20. Specifically, it is a device such as a PC (Personal Computer), a smartphone, a tablet terminal, or a mobile phone terminal. The user 20 uses the personal terminal 23 to perform processing such as updating various information or viewing action history information.

The action type estimation device 100 is a computer. The action type estimation device 100 includes a processor 910 and other hardware such as a memory 921, an auxiliary storage device 922, an input interface 930, an output interface 940, and a communication device 950. The processor 910 is connected to other hardware via a signal line and controls these other hardware.

The action type estimation device 100 includes a position estimation unit 110, an action estimation unit 120, an action history generation unit 130, an information update unit 140, and a storage unit 150 as functional elements. The storage unit 150 stores personal information 151, location correspondence table 152, detailed correspondence table 153, location schedule 154, and action history information 155.

The functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140 are realized by software. The storage unit 150 is provided in the memory 921.

The processor 910 is a device that executes an action type estimation program. The action type estimation program is a program that realizes the functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140.
The processor 910 is an IC (Integrated Circuit) that performs arithmetic processing. Specific examples of the processor 910 are a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and a GPU (Graphics Processing Unit).

The memory 921 is a storage device that temporarily stores data. A specific example of the memory 921 is a SRAM (Static Random Access Memory) or a DRAM (Dynamic Random Access Memory).
The auxiliary storage device 922 is a storage device that stores data. A specific example of the auxiliary storage device 922 is an HDD. Further, the auxiliary storage device 922 may be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, flexible disc, optical disk, compact disc, Blu-ray (registered trademark) disc, or DVD. HDD is an abbreviation for Hard Disk Drive. SD® is an abbreviation for Secure Digital. CF is an abbreviation for CompactFlash®. DVD is an abbreviation for Digital Versaille Disc.

The input interface 930 is a port connected to an input device such as a mouse, keyboard, or touch panel. Specifically, the input interface 930 is a USB (Universal Serial Bus) terminal. The input interface 930 may be a port connected to a LAN (Local Area Network).
The output interface 940 is a port to which a cable of an output device such as a display is connected. Specifically, the output interface 940 is a USB terminal or an HDMI (registered trademark) (High Definition Multimedia Interface) terminal. Specifically, the display is an LCD (Liquid Crystal Display). The action type estimation device 100 may display the action history information 155 on the display via the output interface 940.

The communication device 950 has a receiver and a transmitter. The communication device 950 is wirelessly connected to a communication network such as a LAN, the Internet, or a telephone line. Specifically, the communication device 950 is a communication chip or a NIC (Network Interface Card). The action type estimation device 100 acquires the signal 31 from the indoor communication device 22 via the communication device 950. Further, the action type estimation device 100 may transmit the action history information 155 to the personal terminal 23 of the user 20 via the communication device 950.

The action type estimation program is read into the processor 910 and executed by the processor 910. In the memory 921, not only the action type estimation program but also the OS (Operating System) is stored. The processor 910 executes the action type estimation program while executing the OS. The action type estimation program and the OS may be stored in the auxiliary storage device 922. The action type estimation program and the OS stored in the auxiliary storage device 922 are loaded into the memory 921 and executed by the processor 910. In addition, a part or all of the action type estimation program may be incorporated in the OS.

The action type estimation device 100 may include a plurality of processors that replace the processor 910. These plurality of processors share the execution of the action type estimation program. Each processor, like the processor 910, is a device that executes an action type estimation program.

Data, information, signal values and variable values used, processed or output by the action type estimation program are stored in the memory 921, the auxiliary storage device 922, or the register or cache memory in the processor 910.

The "department" of each of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140 may be read as "processing", "procedure", or "process". Further, the "process" of the position estimation process, the action estimation process, the action history generation process, and the information update process may be read as "program", "program product", or "computer-readable storage medium on which the program is recorded".

The action type estimation program causes a computer to execute each process, each procedure or each process in which the "part" of each of the above parts is read as "process", "procedure" or "process". In addition, the action type estimation method corresponds to each procedure in which the "part" of each of the above parts is read as "procedure".
The action type estimation program may be provided stored in a computer-readable recording medium. In addition, the behavior type estimation program may be provided as a program product.

*** Explanation of operation ***
Next, the operations of the action type estimation system 500 and the action type estimation device 100 according to the present embodiment will be described. The operation procedure of the action type estimation device 100 corresponds to the action type estimation method. Further, the program that realizes the operation of the action type estimation device 100 corresponds to the action type estimation program.

<Information update process>
The operation of the information updating unit 140 according to the present embodiment will be described with reference to FIG.
The information updating unit 140 updates at least one of the personal information 151, the location correspondence table 152, the detailed correspondence table 153, and the location schedule 154.

In step S101, the information update unit 140 determines whether or not there is an update request for the information stored in the storage unit 150. Specifically, the information update unit 140 determines whether or not an update request has been received from the personal terminal 23 of the user 20 for the information stored in the storage unit 150. The update request includes information to be updated and update contents. Specifically, when the user 20 who used to sit and browse in the reference room will now stand and browse for the sake of health, the location correspondence table 152 or the detailed correspondence table 153 will be changed. There is a case.
When there is an update request, in step S102, the information update unit 140 updates the information stored in the storage unit 150 based on the update request. If there is no update request, the process returns to step S101.

FIG. 3 is an example of personal information 151 according to the present embodiment.
Information about individual employees is set in the personal information 151. For example, personal information such as an employee number, an employee name, an affiliation department, and an extension number is set in the personal information 151.

FIG. 4 is an example of the location correspondence table 152 according to the present embodiment.
In the place correspondence table 152, a place area 521 representing a place in the indoor 30 and a place action type 522 which is an action type of the user 20 in the place area 521 in the indoor 30 are set.
As shown in FIG. 4, a coordinate system is set in the indoor 30, and the location area 521 is represented by coordinates in the location correspondence table 152. Alternatively, the place area 521 may be represented by the name of the place in the indoor 30. In that case, a table corresponding to the coordinate system and the name of the place is separately provided indoors 30. In the place action type 522, the type of the action mainly performed by the user 20 in the place area 521 is set. Specifically, in the corridor represented by the coordinates [0,0], [3,0], [3,2], [0,2], since the user 20 is mainly walking, "walking" is Set. Further, in the dining room represented by the coordinates [3,0], [6,0], [6,6], [3,6], since the user 20 is mainly sitting, "sitting" is set. .. Further, in the reference room represented by the coordinates [0,2], [3,2], [3,6], [0,6], since the user 20 is mainly standing, "standing" is set. To.

Since it is considered that the action type at the place differs depending on the user 20, it is preferable that the place correspondence table 152 is provided for each user. As described above, the user 20 who has previously set the place action type 522 in the reference room as "sitting" may reset the place correspondence table 152 so that he / she can stand and browse for the sake of his / her health. In this way, the action type at the place differs depending on the user 20.

FIG. 5 is an example of the detailed correspondence table 153 according to the present embodiment.
In the detailed correspondence table 153, a detailed area 531 that divides the place area 521 included in the place correspondence table 152 and a detailed action type 532 that is an action type corresponding to the detailed area 531 are set. The area and action type setting method is the same as in the location correspondence table 152. Specifically, the reference room is subdivided into a bookshelf area and a reading desk area. In the detailed correspondence table 153 of the reference room, the user 20 stands mainly in the bookshelf area represented by the coordinates [5,0], [6,0], [6,6], [3,6]. , "Standing" is set. Further, in the reading desk area represented by the coordinates [3,0], [5,0], [5,6], [3,6], since the user 20 is mainly sitting, "sitting" is set. Will be done.

FIG. 6 is an example of the place schedule 154 according to the present embodiment.
In the place schedule 154, a schedule in the place area is set. Specifically, the content such as "At the cafeteria, a standing party from 12:00 to 15:00 on March 29, 2019" is set.

The operation of the action type estimation device 100 according to the present embodiment will be described with reference to FIG. 7.

<Position estimation processing>
In step S201, the position estimation unit 110 estimates the position of the user 20 in the indoor 30. The position of the user 20 may be a local coordinate system set in the indoor 30 or a name that specifies the position in the indoor 30. The position of the user 20 may be any information as long as the position in the indoor 30 can be specified. The position estimation unit 110 is a signal communicated between a plurality of indoor communication devices 22 for short-range wireless communication installed indoors 30 and a user communication device 21 for short-range wireless communication carried by the user 20. 31 is acquired, and the position of the user 20 is estimated from the acquired signal 31.
Specifically, a plurality of indoor communication devices 22 installed in the indoor 30 receive radio waves transmitted from the user communication device 21 for short-range wireless communication carried by the user 20, so that the user 20 can receive radio waves. The position is estimated. The indoor communication device 22 receives radio waves from the user communication device 21. Then, the indoor communication device 22 transmits the received radio wave as a signal 31 to the position estimation unit 110. The position estimation unit 110 receives the signal 31 via the communication device 950, and estimates the position of the user 20 based on the signal 31.
In step S202, the position estimation unit 110 determines whether or not the position of the user 20 has been successfully acquired. If successful, the process proceeds to step S203. If unsuccessful, the process returns to step S201.

<Behavior estimation processing>
In step S203, the behavior estimation unit 120 estimates the behavior of the user 20 based on the position of the user 20 acquired by the position estimation unit 110 and the information stored in the storage unit 150. The information stored in the storage unit 150 is at least one of the location correspondence table 152, the detailed correspondence table 153, and the location schedule 154.

The operation of the behavior estimation unit 120 according to the present embodiment will be described with reference to FIG.
In step S301, the action estimation unit 120 acquires the location correspondence table 152, and acquires the location action type 522 corresponding to the location area 521 matching the position of the user 20 from the location correspondence table 152. The behavior estimation unit 120 estimates the behavior of the user 20 based on the acquired location behavior type 522. At this time, the behavior estimation unit 120 selects the location correspondence table 152 corresponding to the user 20 if the location correspondence table 152 is set for each user. Further, the location correspondence table 152 may be set for each job title or role. In that case, the behavior estimation unit 120 acquires the job title or role of the user 20 from the personal information 151. Then, the behavior estimation unit 120 selects the location correspondence table 152 corresponding to the job title or role of the user 20.

In step S302, the action estimation unit 120 acquires the detailed correspondence table 153 in which the detailed area 531 that divides the place area 521 included in the place correspondence table 152 and the detailed action type 532 corresponding to the detailed area 531 are set. .. The action estimation unit 120 acquires the detailed action type corresponding to the detailed area 531 that matches the position of the user 20 from the detailed correspondence table 153. The action estimation unit 120 estimates the action of the user 20 based on the place action type 522 that matches the position of the user 20 and the detailed action type 532 that matches the position of the user 20.

In step S303, the action estimation unit 120 acquires the place schedule 154 in which the schedule in the place area is set. The action estimation unit 120 estimates the action of the user 20 based on the place action type 522, the detailed action type 532, and the current schedule set in the place schedule 154, using the current time and the place schedule 154. ..

Specifically, the processes from step S301 to step S302 are as follows.
The behavior estimation unit 120 may estimate the behavior of the user 20 based only on the location behavior type 522. There is no detailed correspondence table 153 in a place area such as a corridor or an elevator. As described above, in the case of the place area where the detailed correspondence table 153 and the place schedule 154 do not exist, the action estimation unit 120 estimates the action of the user 20 based only on the place action type 522. For example, when the user 20 is in the corridor, it is estimated to be "walking", and when the user 20 is in the elevator, it is estimated to be "standing".

Further, the action estimation unit 120 estimates the action of the user 20 based on the place action type 522 that matches the position of the user 20 and the detailed action type 532 that matches the position of the user 20. For example, when the position estimation unit 110 detects the user 20 in the area of the bookshelf in the data room, the place action type 522 is "standing" and the detailed action type 532 is "sitting". At this time, the behavior estimation unit 120 gives priority to the detailed correspondence table 153 and estimates the behavior of the user 20 as "sitting".

Further, when the place schedule 154 exists for the place corresponding to the position of the user 20, the behavior estimation unit 120 estimates the behavior of the user 20 in consideration of the place schedule 154. For example, when the position estimation unit 110 detects the user 20 in the dining table area of the dining room at 13:00 on March 29, 2019, the place action type 522 becomes "sitting" and the detailed action type 532 also "sitting". ". However, in the location correspondence table 153, since it is a standing party at the cafeteria from 12:00 to 15:00 on March 29, 2019, the behavior estimation unit 120 gives priority to the location schedule 154 and gives the user 20's behavior. Estimated to be "standing".
In addition, in the place schedule table 154, the action type may be set in association with the contents of the schedule. Alternatively, a table such as a schedule-specific action type in which the schedule content and the action type are associated with each other may be stored in the storage unit 150. For example, "standing" is associated with a standing party as an action type by schedule.

Further, the action estimation unit 120 may estimate the action of the user 20 based on the transition of the action type of the user 20 in the time axis direction or the transition of the position of the user 20 in the time axis direction.
As a specific example, it can be estimated that the behavior estimation unit 120 has taken the action of "fast walking" because the position of the user 20 has moved 10 m in 5 seconds. Alternatively, since the behavior estimation unit 120 has taken the action type of "sitting" immediately before, it can be estimated that the possibility of taking the action of "running" is low.

<Behavior history generation process>
The action history generation unit 130 generates the action history of the user 20 as the action history information 155 by using the estimation result of the action of the user 20. Specifically, it is as follows.
In step S204, the action history generation unit 130 determines whether or not the estimation result of the action of the user 20 is the same as the previous action. If they are the same, that is, if there is no change in the behavior of the user 20, the process returns to step S201. If they are not the same, that is, if there is a change in the behavior of the user 20, the process proceeds to step S205.
In step S205, the action history generation unit 130 records a new action and a start time of the new action in the action history information 155. Specifically, the action history generation unit 130 records the current time as the start time of a new action. Further, the action history generation unit 130 may record the current time as the end time of the end of the action.

FIG. 9 is an example of the action history information 155 according to the present embodiment.
In the action history information 155, a time, a place, and an action as an estimation result are set for each employee who is the user 20. In the recording method of the action history information 155, the duration may be aggregated and recorded for each action of each employee. In addition, any recording method may be used as long as the action can be recorded for each user 20.

*** Other configurations ***
<Modification example 1>
In the present embodiment, the description has been made on the assumption that the position estimation unit estimates the position of the user by the beacon. However, if the position of the user indoors can be estimated, a position estimation method other than the beacon may be used.
For example, the position estimation unit may estimate the user's position by using the history information of the gate passage by the ACS (Access Control System). Further, the position estimation unit may estimate the position of the user by using the function of the elevator. Specifically, the position estimation unit uses an elevator control signal. Alternatively, a beacon receiver may be installed in the elevator so that the user can be identified as being in the elevator car. Further, the position estimation unit may estimate the position of the user by using the person identification function by the surveillance camera.
Further, the position estimation unit may estimate the user's position by combining a beacon, an ACS, an elevator, and a surveillance camera.

Here, the estimation of the position using the ACS, which is an entry / exit management system, will be described. Specifically, ACS is one of the security systems that unlocks the gate or door by holding an employee ID card or the like when entering a company premises or a specific room. At that time, a log is taken of what time the individual was at the place. By using this log, for example, the position of "dining room, crossing corridor, working room" can be estimated from the log such as "dining room exit, work room entry". In addition, the estimated position can be used to estimate an action type such as "sitting work, walking, standing work". In addition, the movement speed can be calculated from the time of the log between ACSs.

<Modification 2>
In the present embodiment, the position is estimated by using a plurality of indoor communication devices for short-range wireless communication installed indoors as a receiver and a user communication device for short-range wireless communication carried by the user as a beacon transmitter. The department estimates the user's position. However, a plurality of indoor communication devices for short-range wireless communication installed indoors may be used as a transmitter, and a user communication device for short-range wireless communication carried by the user may be used as a receiver. The position estimation unit may estimate the position of the user by acquiring the signal transmitted from the indoor communication device and received by the user communication device from the user communication device. At this time, a specific example of the user communication device is a mobile terminal such as a smartphone terminal or a tablet terminal.

<Modification example 3>
In the present embodiment, when there is no location correspondence table for each user, the behavior estimation unit acquires the user's job title or role from the personal information and selects the location correspondence table corresponding to the job title or role. If there is no personal information, the job title or role of the user 20 may be acquired by referring to the table of attributes such as job title or role.

<Modification example 4>
In the present embodiment, the information update unit receives an update request from the user and updates information such as a location correspondence table or a detailed correspondence table. However, the action type estimation device may automatically create or update the location correspondence table or the detailed correspondence table by collecting and learning the activity record for each position of each user indoors.

<Modification 5>
The behavior estimation unit may be provided with the following functions to improve the estimation accuracy of the user's behavior.
(1) Although the positions at the start and end of the movement are known, the position during the movement may be unknown. In such a case, the behavior estimation unit estimates the moving position by using the information that can be acquired by the building side such as the operation history information of the elevator and the history information of passing through the gate by ACS, and the moving time. Then, the behavior estimation unit selects a location correspondence table, a detailed correspondence table, or a location schedule using the estimated position, and estimates the behavior.
(2) If the user is stopped near his / her seat, it is highly likely that he / she is sitting. On the other hand, if you are stopped near someone else's seat, you are likely to be standing. Therefore, when the user is stopped near his / her seat, it is presumed to be “sitting”. If the user is stopped near another person's seat, it is presumed to be "standing".
(3) When the position information is unknown for a certain period of time or more, the behavior estimation unit extracts a person having a similar behavior history on that day, and estimates the behavior assuming that the user is taking the same behavior as that person.
(4) The behavior estimation unit estimates the user's behavior by adding information such as time, day of the week, work time and leaving time, and schedules of the previous day and the next day. As an example of the timing, a place correspondence table and a detailed correspondence table different from the usual ones are set at the end of the term or immediately after joining the company. As an example of the day of the week, if there is a schedule with a fixed day of the week, a location correspondence table and a detailed correspondence table are set according to the schedule. As an example of attendance time and leaving time, the behavior estimation department takes into account that the behavior changes normally when the person is late or leaves early. As an example of the schedule of the previous day and the next day, if the presentation is scheduled for the next day, the behavior estimation department presumes that the rehearsal of the presentation is performed standing in the meeting room at the meeting of the previous day.
(5) When the user is moving on the stairs, the behavior estimation unit estimates whether the user is going up or down the stairs by identifying the floors before and after the stairs.

<Modification 6>
In the present embodiment, the functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140 are realized by software. As a modification, the functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140 may be realized by hardware.

FIG. 10 is a diagram showing a configuration of an action type estimation system 500 according to a modified example of the present embodiment.
The action type estimation device 100 includes an electronic circuit 909, a memory 921, an auxiliary storage device 922, an input interface 930, and an output interface 940.

The electronic circuit 909 is a dedicated electronic circuit that realizes the functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140.
The electronic circuit 909 is specifically a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array.
The functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140 may be realized by one electronic circuit or may be distributed to a plurality of electronic circuits.
As another modification, some functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140 may be realized by an electronic circuit, and the remaining functions may be realized by software.

Each of the processor and the electronic circuit is also called a processing circuit. That is, in the action type estimation device 100, the functions of the position estimation unit 110, the action estimation unit 120, the action history generation unit 130, and the information update unit 140 are realized by the processing circuit.

*** Explanation of the effect of this embodiment ***
In the action type estimation system according to the present embodiment, the user's action type is estimated only from the user's position indoors by using the location correspondence table and the detailed correspondence table in which the indoor position and the action type are linked. Therefore, according to the behavior type estimation system according to the present embodiment, the behavior can be estimated without using a motion sensor such as an accelerometer. In addition, the burden on the user to wear the wearable terminal can be reduced. In addition, by diverting indoor person positioning such as normal entry / exit management, it becomes easier to collect information on the service provider side, and the burden on cost can be further reduced.

The action type estimation system according to the present embodiment includes a plurality of information such as a location correspondence table, a detailed correspondence table, and a location schedule, and selects and refers to appropriate information according to the user's personal information, location, or time zone. To do. Therefore, according to the behavior type estimation system according to the present embodiment, it is possible to improve the estimation accuracy of the user's behavior.

In the behavior type estimation system according to the present embodiment, the behavior of a building user can be estimated and the amount of activity can be determined by having a device such as a beacon, which has a lower cost than a relatively high cost device such as a wearable terminal. Can be useful. It is difficult to improve the accuracy of distinguishing between climbing and descending stairs using only the acceleration sensor. Smartphones often use barometric pressure sensors to determine whether they are climbing or descending stairs. In the action type estimation system according to the present embodiment, it is possible to determine the accuracy of a device such as a beacon if the stay floors before and after the stairs can be identified.

Embodiment 2.
In this embodiment, the points different from those in the first embodiment will be mainly described. The same components as those in the first embodiment may be designated by the same reference numerals, and the description thereof may be omitted.

*** Explanation of configuration ***
The configuration of the action type estimation device 100a according to the present embodiment will be described with reference to FIG. The action type estimation device 100a according to the present embodiment includes a user schedule 156 in addition to the configuration of the action type estimation device 100 according to the first embodiment.

FIG. 12 is a diagram showing an example of the user schedule 156 according to the present embodiment.
In the user schedule 156, a date and time 561, a place 562, and a work content 563 are set as a work schedule 564 of the user 20. The work schedule 564 is a daily schedule of the user 20, and is composed of a date and time 561, a place 562, and a work content 563. In addition, an employee number and an employee name that identify the user 20 are set in the user calendar 156. Further, the user schedule 156 may be set with an action type corresponding to the work content 563.
In the present embodiment, the personal information 151 and the user calendar 156 are described as separate information, but the personal information 151 and the user calendar 156 may be configured as one information.

The information update unit 140 also updates the user schedule 156 based on the update request from the user. That is, the information updating unit 140 updates at least one of the location correspondence table 152, the detailed correspondence table 153, the location schedule 154, and the user schedule 156.

*** Explanation of operation ***
The operation of the behavior estimation unit 120 according to the present embodiment will be described with reference to FIG.
In step S301a, the behavior estimation unit 120 acquires the user schedule 156. Specifically, the behavior estimation unit 120 selects the user schedule 156 corresponding to the user 20.
In step S301b, the action estimation unit 120 determines whether or not the user 20 is in a place that matches the work content 563 by using the current time, the position of the user 20, and the user schedule 156. If it is determined that the user 20 is in a place matching the work content 563, the process proceeds to step S301c.

If it is determined that the user 20 is not in a location that matches the work content 563, the process proceeds to step S301. In step S301, the behavior estimation unit 120 estimates the behavior of the user 20 based on the location behavior type 522 corresponding to the location region 521 that matches the location of the user 20 in the location correspondence table 152. The processing of steps S301 to S303 is the same as that of the first embodiment.

In step S301c, the action estimation unit 120 estimates the action of the user 20 based on the work content 563 that matches the work schedule of the user 20. Specifically, it is acquired that the current time is 9:30 on March 29, 2019, and the position of the user 20 is the conference room A. From the user schedule 156, the behavior estimation unit 120 determines that the user 20 is in the presentation, and estimates the behavior of the user 20 as "standing".

*** Explanation of the effect of this embodiment ***
In the action type estimation system according to the present embodiment, if the user's position matches the user's calendar, the user's behavior is estimated directly from the user's calendar. Therefore, the process can be simplified. In addition, by specifying the user calendar in more detail, the estimation accuracy becomes higher, such as sitting and listening or standing in front of the user. In addition, when the user is not at the planned location, the behavior can be estimated with high accuracy by the method described in the first embodiment.

Embodiment 3.
In this embodiment, the points different from those in the first embodiment will be mainly described. The same components as those in the first embodiment may be designated by the same reference numerals, and the description thereof may be omitted.

*** Explanation of configuration ***
The configuration of the action type estimation device according to the present embodiment is the same as the configuration of the action type estimation device 100 according to the first embodiment.
The user's action type includes the type of the user's exercise. As described in the first embodiment, the action type of the user is a type of exercise such as standing, sitting, walking, running, or fast walking.
In the present embodiment, the action history generation unit 130 calculates the amount of exercise of the user based on the action type of the user.

*** Explanation of operation ***
FIG. 14 is a flow chart showing the operation of the action type estimation device 100 according to the present embodiment. FIG. 14 is a diagram corresponding to FIG. 7 of the first embodiment. The difference from FIG. 7 in FIG. 14 is that step S204a is added and step S205 becomes step S205a.

In step S204, the action history generation unit 130 determines whether or not the estimation result of the action of the user 20 is the same as the previous action. If they are not the same, that is, if there is a change in the behavior of the user 20, the process proceeds to step S204a.
In step S204a, the action history generation unit 130 calculates the amount of exercise of the user based on the action type of the user. Specifically, the action history generation unit 130 calculates the calorie consumption in the action of the completed user 20 as the amount of exercise. As a method of calculating calories burned, there is a method of calculating calories burned using a coefficient set in advance for each behavior type, for example, a METS (Metabolic equivalents) value. The action history generation unit 130 calculates the calorie consumption by multiplying the METS value corresponding to the type of completed action by the weight of the user and the duration of the action type. The duration of the action type is calculated as the time from the start time of the completed action type to the current time.

In step S205a, the action history generation unit 130 records the new action and the start time of the new action in the action history information 155, and also records the calories burned in the finished action.

FIG. 15 is a diagram showing an example of action history information 155a according to the present embodiment.
As shown in FIG. 15, in the action history information 155a, the calorie consumption corresponding to each action is stored as the amount of exercise. In addition, the action history information 155a may record a cumulative value of the amount of exercise accumulated.

In the above-described first and second embodiments, each part of the action type estimation device has been described as an independent functional block. However, the configuration of the action type estimation device does not have to be the configuration as in the above-described embodiment. The functional block of the action type estimation device may have any configuration as long as the functions described in the above-described embodiment can be realized. Further, the action type estimation device may be a system composed of a plurality of devices instead of one device.
Further, in the first and second embodiments, a plurality of parts may be combined and carried out. Alternatively, one part of these embodiments may be implemented. In addition, these embodiments may be implemented in any combination as a whole or partially.
That is, in the first and second embodiments, it is possible to freely combine the embodiments, modify any component of each embodiment, or omit any component in each embodiment.

It should be noted that the above-described embodiment is essentially a preferred example and is not intended to limit the scope of the present invention, the scope of the application of the present invention, and the scope of use of the present invention. The above-described embodiment can be variously modified as needed.

20 users, 21 user communication devices, 22 indoor communication devices, 23 personal terminals, 30 indoors, 31 signals, 100, 100a behavior type estimation device, 110 position estimation unit, 120 behavior estimation unit, 130 behavior history generation unit, 140 information Update part, 150 storage part, 151 personal information, 152 place correspondence table, 153 detailed correspondence table, 154 place schedule, 155,155a action history information, 156 user schedule, 561 date and time, 562 places, 563 work contents, 564 work Schedule, 500 action type estimation system, 521 location area, 522 location action type, 513 detailed area, 532 detailed action type, 909 electronic circuit, 910 processor, 921 memory, 922 auxiliary storage device, 930 input interface, 940 output interface, 950 Communication device.

Claims

A position estimation unit that estimates the user's position indoors,
A place correspondence table in which a place area representing a place indoors and a place action type which is an action type of the user in the place area in the room is set is acquired, and matches the position of the user from the place correspondence table. An action estimation unit that acquires a place action type corresponding to a place area and estimates the user's action based on the acquired place action type.
An action type estimation device including an action history generation unit that generates an action history of the user as action history information using the estimation result of the user's action.
The position estimation unit
A signal to be communicated between a plurality of indoor communication devices for short-range wireless communication installed indoors and a user communication device for short-range wireless communication carried by the user is acquired, and from the acquired signal. The action type estimation device according to claim 1, wherein the position of the user is estimated.
The behavior estimation unit
A detailed correspondence table in which a detailed area in which the location area included in the location correspondence table is divided and a detailed action type which is an action type corresponding to the detailed area are set is acquired, and the position of the user is obtained from the detailed correspondence table. The detailed action type corresponding to the detailed area corresponding to is acquired, and the action of the user is estimated based on the place action type matching the position of the user and the detailed action type matching the position of the user. The behavior type estimation device according to claim 1 or 2.
The behavior estimation unit
The place schedule in which the schedule is set in the place area is acquired, and the current time and the place schedule are used to set the place action type, the detailed action type, and the current schedule set in the place schedule. The behavior type estimation device according to claim 3, which estimates the behavior of the user based on the behavior.
The behavior estimation unit
A user calendar in which a date and time, a place, and a work content are set as a work schedule of the user is acquired, and the user matches the work schedule by using the current time, the position of the user, and the user schedule. Claim 3 or claim that, when it is determined whether or not the user is in a place and the user is in a place that matches the work schedule, the behavior of the user is estimated based on the work content that matches the work schedule of the user. Item 4. The action type estimation device according to item 4.
The behavior estimation unit
According to claim 5, when it is determined that the user is not in a place that matches the work schedule, the behavior of the user is estimated based on the place action type corresponding to the place area that matches the position of the user in the place correspondence table. The described behavior type estimation device.
The action type estimation device is
The action type estimation device according to claim 6, further comprising an information updating unit that updates at least one of the location correspondence table, the detailed correspondence table, the location schedule, and the user schedule.
The behavior estimation unit
The method according to any one of claims 1 to 7, wherein the user's behavior is estimated based on the transition of the user's behavior type in the time axis direction or the transition of the user's position in the time axis direction. Behavior type estimation device.
The action type of the user includes the type of exercise of the user.
The action type estimation device according to any one of claims 1 to 8, wherein the action history generation unit calculates the amount of exercise of the user based on the action type of the user.
The position estimater estimates the user's position indoors and
The action estimation unit acquires a place correspondence table in which a place area representing the indoor place and a place action type which is the action type of the user in the indoor place area are set, and the user from the place correspondence table. The place action type corresponding to the place area corresponding to the position of is acquired, and the behavior of the user is estimated based on the acquired place action type.
An action type estimation method in which an action history generation unit uses an estimation result of the user's action to generate a history of the user's action as action history information.
Position estimation processing that estimates the user's position indoors,
A place correspondence table in which a place area representing a place indoors and a place action type which is an action type of the user in the place area in the room is set is acquired, and matches the position of the user from the place correspondence table. An action estimation process that acquires a place action type corresponding to a place area and estimates the user's action based on the acquired place action type.
An action type estimation program that causes a computer to execute an action history generation process that generates an action history of the user as action history information using the user's action estimation result.