JP2018156379A - Measuring program, measuring method and measuring device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable easy estimation of the state of a person.SOLUTION: The measuring device 1 includes a pressure detection unit 1b, a determination unit 1c, and an estimation unit 1d. The pressure detection unit 1b detects pressure. The determination unit 1c determines whether or not a person is in contact with the pressure detection unit 1b based on the shape and/or size of an area to which the detected pressure is applied. When it is determined that the person is in contact, the estimation unit 1d estimates the state of the person according to the distribution of the magnitude of the pressure corresponding to the detected person.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a measurement program, a measurement method, and a measurement apparatus.

  Investigations such as interests and preferences may be made for multiple persons. For example, the results of the survey are used for marketing strategies related to products and services. Therefore, it is considered to use an information processing system for investigation of interests and preferences for an unspecified number of persons.

  For example, there is a proposal that quantitatively grasps the degree of interest in exhibition products by people who enter the exhibition hall based on the staying time, and uses it to develop effective sales activities. In this proposal, the number of visitors staying in each exhibition booth and the staying time are totaled by reading the visitor card in which the personal information of the visitor is registered for each exhibition booth.

  In addition, the body temperature, sweating, and heart rate of the user are acquired by a sensor, the on / off operation for the communication switch by the user is detected, and based on the acquired information, the user selects which object for which object. There is a proposal of an apparatus for creating object information indicating whether such emotions and consciousness are generated. In this proposal, the object information is analyzed, and analysis information indicating the popularity of each exhibit and the user's preference is created.

  Furthermore, there is a proposal of a moving body detection system that judges a rough flow line of a person based on shoe-shaped attributes and displays content information corresponding to the line. The moving object detection system includes a plurality of moving object identification devices. The moving object identification device generates shoe type information from the detection result of the pressure of the human foot, and determines the shoe type attribute from the shoe type information. The moving body detection system determines that the moving body identification devices in which the same shoe-type attribute is detected are connected as the flow line information, and the content information suitable for the flow line information or the shoe-type attribute information is displayed by the display device. indicate.

Japanese Patent Laid-Open No. 10-198728 JP-A-2005-275960 JP 2010-218177 A

  Here, a mechanism for estimating the state of the person becomes a problem. For example, as described above, the method of analyzing the user's preference by collecting the user's body temperature, sweating, heart rate, on / off of the switch by the user, etc. places a heavy burden on the user. On the other hand, for example, it is also conceivable to install a camera to monitor a person's action and estimate the state of the person from the person's action using an image processing technique. However, since monitoring with a camera is information that can be used to identify and identify an individual, the captured image may give bad impression to the person.

  In one aspect, an object of the present invention is to make it possible to easily estimate a person's state.

  In one aspect, a measurement program is provided. The measurement program detects the pressure by the pressure detection unit, determines whether the person is in contact with the pressure detection unit based on the shape and / or size of the detected pressure-applied region, If it is determined that the person is present, the computer is caused to execute a process of estimating the state of the person according to the distribution of the pressure magnitude corresponding to the detected person.

  In one aspect, the state of a person can be easily estimated.

It is a figure which shows the measuring device of 1st Embodiment. It is a figure which shows the example of the measurement system of 2nd Embodiment. It is a figure which shows the example of a connection of the server and sensor sheet of 2nd Embodiment. It is a figure which shows the hardware example of the server of 2nd Embodiment. It is a figure which shows the hardware example of the sensor sheet | seat of 2nd Embodiment. It is a figure which shows the function example of the server of 2nd Embodiment. It is a figure which shows the example of the measurement data of the load distribution of 2nd Embodiment. It is a figure which shows the example of the positional relationship between the exhibit of a 2nd Embodiment, and a person. It is a figure which shows the operation example of the person who becomes the preload of 2nd Embodiment. It is a figure which shows the example of the load pattern which shows the preload of 2nd Embodiment. It is a figure which shows the example of the foot type | mold table of 2nd Embodiment. It is a figure which shows the example of the person table of 2nd Embodiment. It is a figure which shows the example of the result table of 2nd Embodiment. 10 is a flowchart illustrating an example of information collection processing according to the second embodiment. It is a flowchart which shows the gender determination processing example of 2nd Embodiment. It is a flowchart which shows the interest level determination processing example of 2nd Embodiment. It is a flowchart which shows the example of an analysis process of 2nd Embodiment. It is a figure which shows the example of the interest pattern table of 2nd Embodiment. It is a flowchart which shows the example of a guidance process of 2nd Embodiment. It is a figure which shows the example of a guidance display of 2nd Embodiment.

Hereinafter, the present embodiment will be described with reference to the drawings.
[First Embodiment]
FIG. 1 is a diagram illustrating a measurement apparatus according to the first embodiment. The measuring device 1 estimates a person's state. The state of the person is a person's posture, a person's motion, or a person's degree of interest or degree of interest determined from the person's posture and movement.

The measuring device 1 includes a storage unit 1a, a pressure detection unit 1b, a determination unit 1c, and an estimation unit 1d.
The storage unit 1a may be a volatile storage device such as a RAM (Random Access Memory) or a non-volatile storage device such as an HDD (Hard Disk Drive) or a flash memory. The determination unit 1c and the estimation unit 1d can be realized by a CPU (Central Processing Unit), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like. The determination unit 1c and the estimation unit 1d may be realized by a processor that executes a program. The “processor” may include a set of multiple processors (multiprocessor).

  The pressure detector 1b detects the pressure applied to the pressure detector 1b. For example, the pressure detection unit 1b detects the pressure applied to the pressure detection unit 1b by an object placed on the pressure detection unit 1b. A surface (pressure detection surface) for detecting the pressure of the pressure detection unit 1 b is provided outside the measuring device 1. For example, the pressure detection surface of the pressure detection unit 1b is provided on a walking surface (such as a floor surface or the ground) on which a person walks. In one example, the pressure detection unit 1b includes a sensor matrix m1.

  The sensor matrix m1 forms a pressure detection surface. The sensor matrix m1 has a sheet shape, and includes a plurality of pressure sensors arranged in a two-dimensional lattice pattern on the surface of the sheet. The pressure detection unit 1b detects the shape and size of a region to which pressure is applied by using the sensor matrix m1.

  The determination unit 1c determines whether or not a person is in contact with the pressure detection unit 1b based on the shape and / or size of the detected pressure-applied region. For example, the determination unit 1c determines whether or not the sole (including the sole) of a person is in contact with the pressure detection unit 1b. In one example, the determination unit 1c obtains the load distribution 2 as a pressure detection result by the pressure detection unit 1b.

  The load distribution 2 includes information on the load areas 2a and 2b on the pressure detection surface of the pressure detection unit 1b. For example, in the load distribution 2 of FIG. 1, the direction from the upper side to the lower side is the positive direction of the X axis, and the direction from the right side to the left side is the positive direction of the Y axis. And let the upper right corner of the load distribution 2 of FIG. 1 be the origin (X, Y) = (0, 0). The coordinate grid point corresponds to a pressure detection position by one pressure sensor of the sensor matrix m1. The lattice point is associated with a load value indicating the magnitude of pressure.

  Therefore, the determination unit 1c uses the load distribution 2 to determine the shape of the area where pressure is applied (for example, the shape of the load areas 2a and 2b) and the size of the area where pressure is applied (for example, the total area of the load areas 2a and 2b). ) Can be obtained.

  For example, the memory | storage part 1a memorize | stores previously the information which shows the pattern of a person's foot shape or shoe shape. And the determination part 1c determines whether the load area | regions 2a and 2b correspond to a person by collating the shape of the load area | regions 2a and 2b, and the pattern of the shape memorize | stored in the memory | storage part 1a. For example, the determination unit 1c determines that the load regions 2a and 2b correspond to a person when the degree of matching between the shape of the load regions 2a and 2b and the pattern of the shape stored in the storage unit 1a is greater than a predetermined value. . In this case, the determination unit 1c determines that a person (for example, a person 3) is in contact with the pressure detection unit 1b. On the other hand, the determination unit 1c determines that the load regions 2a and 2b do not correspond to a person when the degree of matching between the shape of the load regions 2a and 2b and the pattern of the shape stored in the storage unit 1a is equal to or less than a predetermined value. To do. In this case, the determination unit 1c determines that a person is not in contact with the pressure detection unit 1b.

  Further, for example, the storage unit 1a stores in advance information indicating a typical value of the area of a person's foot shape or shoe shape. And the determination part 1c collates the area of the shape of the load area | regions 2a and 2b with the typical value of the area memorize | stored in the memory | storage part 1a, and it is determined whether the load area | regions 2a and 2b correspond to a person. judge. For example, the determination unit 1c determines that the load regions 2a and 2b correspond to a person when the areas of the load regions 2a and 2b and the typical values of the areas stored in the storage unit 1a match with a predetermined accuracy. . In this case, the determination unit 1c determines that a person (for example, a person 3) is in contact with the pressure detection unit 1b. On the other hand, the determination unit 1c determines that the load regions 2a and 2b do not correspond to a person when the areas of the load regions 2a and 2b and the typical values of the areas stored in the storage unit 1a do not match with a predetermined accuracy. To do. In this case, the determination unit 1c determines that a person is not in contact with the pressure detection unit 1b.

  Further, the determination unit 1c uses both the information indicating the pattern of the shape of the foot or shoe shape of the person and the typical value of the area of the foot or shoe shape stored in the storage unit 1a to detect the pressure. It may be determined whether a person is in contact with the part 1b. For example, the determination unit 1c determines that the degree of coincidence between the shape of the load regions 2a and 2b and the pattern of the shape stored in the storage unit 1a is greater than a predetermined value, and the area of the load regions 2a and 2b and the storage unit 1a. When the stored area typical value matches with a predetermined accuracy, it may be determined that the load areas 2a and 2b correspond to a person. On the other hand, the determination unit 1c stores the degree of coincidence between the shape of the load regions 2a and 2b and the pattern of the shape stored in the storage unit 1a below a predetermined value or stores the area of the load regions 2a and 2b and the storage unit 1a. When the typical area value does not match with a predetermined accuracy, it may be determined that the load areas 2a and 2b do not correspond to a person.

  When the load areas 2a and 2b correspond to a person, the determination unit 1c determines that the load area 2a is a left foot load distribution and the load area 2b is a right foot due to the positional relationship and shape symmetry of the load areas 2a and 2b. It can also be determined that the load distribution is.

  When the estimation unit 1d determines that the person is in contact with the pressure detection unit 1b, the estimation unit 1d estimates the state of the person according to the distribution of the magnitude of the pressure corresponding to the detected person. For example, when the determination unit 1c determines that the sole of the person 3 is in contact with the pressure detection unit 1b, the estimation unit 1d determines whether the pressure corresponding to the detected person 3 is distributed. The state of the person 3 is estimated. More specifically, the estimation unit 1d obtains a load value (pressure magnitude) at each coordinate point belonging to the load regions 2a and 2b based on the load distribution 2. And the estimation part 1d acquires the bias | inclination of the load value in the load area | regions 2a and 2b.

  In one example, the estimation unit 1d specifies the direction in which the person 3 is facing based on the shape and / or size of the load areas 2a and 2b. For example, the estimation unit 1d determines whether the load region 2a, 2b is matched with the pattern of the shape of a person's foot or shoe (the toe side is the front side and the reverse side is the back side). , 2b is determined to be the front side. Then, for example, in the load areas 2a and 2b, the estimation unit 1d is configured such that when the relatively large load value is concentrated on the front side and the relatively small load value is concentrated on the rear side, It is estimated that a relatively large load is applied to (a preload). Similarly, the estimation unit 1d can also estimate that a relatively large load is applied to the back side of the person 3 (a back load). Here, in the example of the load distribution 2, the darker the color, the larger the load value.

  By using the above processing by the estimation unit 1d, more information about the person 3 can be obtained. For example, consider a situation where the object 5 is displayed on the table 4. And the pressure detection surface of the pressure detection part 1b is arrange | positioned at the floor surface in front of the stand 4 and the target object 5. FIG. That is, the side corresponding to X = 0 of the pressure detection surface is arranged on the side of the table 4 and the object 5. In this case, the estimation unit 1d estimates the degree of interest in the object of the person 3 according to the direction in which the identified person 3 is facing and the distribution of the magnitude of the pressure corresponding to the detected person 3. May be.

  Specifically, the object 5 side of the area where the pressure detector 1b is provided is the front side of the area, and the opposite side is the back side of the area. When the person 3 enters the area where the pressure detector 1b is provided or when the person 3 stays in the area for a predetermined time or longer, the estimating unit 1d indicates that the person 3 is interested in the object 5 It is possible to judge. Further, the estimation unit 1d may determine that the person 3 is interested in the object 5 when the person 3 moves from the rear side to the front side of the area. Further, when the person 3 is preloaded at a position relatively close to the object 5, it may be determined that the person 3 is interested in the object 5. The estimation unit 1d may score the degree of interest of the person 3 with respect to the object 5 by such determination. For example, each time the state of the person 3 is detected, the estimation unit 1d may add a predetermined value to the score representing the degree of monitoring to calculate the degree of interest of the person 3 with respect to the object 5. In this case, the estimation unit 1d evaluates that the person 3 is more interested in the object 5 as the score is larger.

  Thereby, a person's state can be estimated easily. For example, it is conceivable to investigate the interests and interests of the participants by questionnaires on paper and the Web for a large number of unspecified people who have visited an exhibition hall. However, such a method places a heavy burden on the responding person. A method of analyzing the user's preference by collecting a person's body temperature, sweating, heart rate, and on / off of the switch by the person is also conceivable, but this method also has a heavy burden on the person side. On the other hand, for example, it is also conceivable to install a camera to monitor a person's action and estimate the state of the person from the person's action using an image processing technique. However, since monitoring with a camera is information that can be used to identify and identify an individual, the captured image may give bad impression to the person.

  Therefore, the measuring device 1 estimates the state of the person 3 using the pressure detection result by the pressure detection unit 1b. This makes it easier for the person 3 to be in a relatively simple facility than using many sensors that measure the body temperature, sweating, heart rate, etc. of the person 3 or installing a camera that monitors the action of the person 3. Can be estimated. In particular, since it is only necessary for the person 3 to step on the pressure detection unit 1b with his / her foot, the action of the person 3 is not hindered. Since it is not necessary to force the person 3 to take a special action, the burden on the person 3 can be reduced compared to a method in which a reply is made using paper or a switch. Furthermore, it is not necessary to give the person 3 an unpleasant feeling as in monitoring with a camera. Thus, by using the measuring apparatus 1, there is an advantage that it is possible to efficiently investigate the degree of interest in the target object 5 for an unspecified number of persons.

Next, the function will be described in more detail by exemplifying a case where a server computer (sometimes simply referred to as a server) having the function of the measuring device 1 is provided in the exhibition hall.
[Second Embodiment]
FIG. 2 is a diagram illustrating an example of a measurement system according to the second embodiment. The measurement system according to the second embodiment includes a server 100 and a sensor sheet 200. The server 100 and the sensor sheet 200 are connected by a predetermined cable.

The server 100 is a server computer used for investigating the degree of interest in exhibits exhibited by persons who have visited the exhibition hall. The server 100 is an example of the measuring device 1.
The sensor sheet 200 is a sensor (pressure sensor) that detects pressure. The sensor sheet 200 has a rectangular sheet shape and is laid on the floor surface (walking surface) of the exhibition hall. The sensor sheet 200 is an example of the pressure detection unit 1b. Here, an exhibition stand 10 is provided in the exhibition hall, and an exhibit 11 is installed on the exhibition stand 10. The display stand 10 is a stand for displaying and displaying the exhibits 11. The exhibit 11 is an item displayed in the exhibition hall. One sensor sheet 200 is provided for the exhibit 11. For example, when the person 50 who visited the exhibition hall wants to see the exhibit 11, the person 50 gets on the sensor sheet 200 and sees the exhibit 11. The area where the sensor sheet 200 is provided may be considered as one booth where the exhibit 11 is displayed.

  FIG. 3 is a diagram illustrating a connection example between the server and the sensor sheet according to the second embodiment. In the exhibition hall, multiple exhibits are displayed. For this reason, sensor sheets 200, 200a, 200b,... Are provided in the exhibition hall. The measurement system of the second embodiment also includes sensor sheets 200a, 200b,.

  As described above, the sensor sheet 200 is provided for the exhibit 11. The sensor sheet 200a is provided for the exhibit 11a. The sensor sheet 200b is provided for the exhibit 11b. Sensor sheets are also provided on a one-to-one basis for other exhibits. An ID (IDentifier) (referred to as sensor ID) is assigned to the sensor sheet. In addition, an ID (referred to as an exhibit ID) is also given to the exhibit. The server 100 holds a correspondence relationship between the sensor ID and the exhibit ID in advance.

  FIG. 4 is a diagram illustrating a hardware example of the server according to the second embodiment. The server 100 includes a processor 101, a RAM 102, an HDD 103, a connection IF (InterFace) 104, an image signal processing unit 105, an input signal processing unit 106, a medium reader 107, and a network IF 108. Each hardware is connected to the server 100 bus.

  The processor 101 is hardware that controls information processing of the server 100. The processor 101 may be a multiprocessor. The processor 101 is, for example, a CPU, DSP, ASIC, or FPGA. The processor 101 may be a combination of two or more elements of CPU, DSP, ASIC, FPGA, and the like.

  The RAM 102 is a main storage device of the server 100. The RAM 102 temporarily stores at least part of an OS (Operating System) program and application programs to be executed by the processor 101. The RAM 102 stores various data used for processing by the processor 101.

  The HDD 103 is an auxiliary storage device of the server 100. The HDD 103 magnetically writes data to and reads data from a built-in magnetic disk. The HDD 103 stores an OS program, application programs, and various data. The server 100 may include other types of auxiliary storage devices such as flash memory and SSD (Solid State Drive), or may include a plurality of auxiliary storage devices.

  The connection IF 104 is an interface for connecting the sensor sheet 200 and the server 100. As the connection IF 104, for example, an interface such as USB (Universal Serial Bus) can be used. The connection IF 104 is also used to connect the sensor sheets 200a, 200b,... (Not shown in FIG. 4) and the server 100.

  The image signal processing unit 105 outputs an image to the display 21 connected to the server 100 in accordance with an instruction from the processor 101. As the display 21, a CRT (Cathode Ray Tube) display, a liquid crystal display, or the like can be used.

  The input signal processing unit 106 acquires an input signal from the input device 22 connected to the server 100 and outputs it to the processor 101. As the input device 22, for example, a pointing device such as a mouse or a touch panel, a keyboard, or the like can be used.

  The medium reader 107 is a device that reads a program and data recorded on the recording medium 23. As the recording medium 23, for example, a magnetic disk such as a flexible disk (FD) or HDD, an optical disk such as a CD (Compact Disc) or a DVD (Digital Versatile Disc), or a magneto-optical disk (MO) is used. Can be used. Further, as the recording medium 23, for example, a non-volatile semiconductor memory such as a flash memory card can be used. For example, the medium reader 107 stores the program and data read from the recording medium 23 in the RAM 102 or the HDD 103 in accordance with an instruction from the processor 101.

  The network IF 108 communicates with other devices via the network 20. The network IF 108 may be a wired communication interface or a wireless communication interface.

  FIG. 5 is a diagram illustrating a hardware example of the sensor sheet according to the second embodiment. The sensor sheet 200 includes a processor 201, a memory 202, a connection IF 203, and a sensor unit 204.

  The processor 201 is hardware that controls the operation of the sensor sheet 200. The processor 201 is, for example, a DSP, ASIC, or FPGA. The processor 201 may be a combination of two or more elements of DSP, ASIC, FPGA, and the like.

The memory 202 stores sensor data acquired by the sensor unit 204.
The connection IF 203 is an interface for connecting the sensor sheet 200 and the server 100. For example, an interface such as a USB can be used as the connection IF 203.

  The sensor unit 204 is formed by a plurality of pressure sensors arranged two-dimensionally on the sheet surface. The pressure sensor 204a is one of a plurality of pressure sensors. The plurality of pressure sensors form a sensor matrix. That is, each of the plurality of pressure sensors is arranged in a grid pattern.

  The sensor unit 204 measures the load value (load value) corresponding to the pressure applied by the object on the sheet surface to the sheet surface by each pressure sensor. More specifically, two films of a material such as PET (PolyEthylene Terephthalate) are prepared, and the electrodes are wired in the row direction on one film, and the electrodes are wired in the column direction on the other film. To do. Then, the pressure sensitive conductive ink is applied on the electrodes, and the two films are overlapped so that the electrodes of the two films overlap in the matrix direction, thereby forming the sensor unit 204. If it does so, the intersection part of the matrix of each electrode will function as a pressure sensor, and the resistance value of an applicable location will change according to a pressure (in response to a load). This resistance value is converted into a digital value (load value) by the processor 201 and transmitted to the server 100.

  FIG. 6 is a diagram illustrating a function example of the server according to the second embodiment. The server 100 includes a storage unit 110, a load distribution measurement unit 120, a foot type collation unit 130, a person attribute determination unit 140, an interest level determination unit 150, and an analysis processing unit 160.

  The storage unit 110 is realized as a storage area secured in the RAM 102 or the HDD 103. The load distribution measuring unit 120, the foot type collating unit 130, the person attribute determining unit 140, the interest level determining unit 150, and the analysis processing unit 160 are executed by the processor 101 by executing the program stored in the RAM 102 by the processor 101. May be a function. Alternatively, the load distribution measurement unit 120, the foot type collation unit 130, the person attribute determination unit 140, the interest level determination unit 150, and the analysis processing unit 160 may be realized by hard wired logic such as FPGA or ASIC.

The storage unit 110 stores various types of information used for processing of each unit. The storage unit 110 stores a foot table, a person table, and a result table.
The foot type table is a table in which information indicating the shape of the sole of a person's foot or the sole (referred to as a foot type) is registered. Footprints are sometimes referred to as footprints. The information indicating the foot shape may be a feature vector that represents the shape of the sole or sole of a person with a plurality of types of feature amounts. Information indicating the foot shape registered in the foot shape table is created in advance and stored in the storage unit 110.

  The person table is a table in which attribute information such as foot shape and weight actually acquired for a person is registered in association with a person ID (referred to as a person ID). The information indicating the foot pattern registered in the person table may also be a feature vector indicating the actually acquired foot pattern.

The result table is a table in which the determination result of the interest level for each exhibit determined for a person is registered in association with the person ID.
The load distribution measuring unit 120 uses the sensor sheet 200 to measure the load distribution in the sensor unit 204 and generates load distribution measurement data. The load distribution is a set of points at which a load is applied in the sensor unit 204 (points where the load value is 0 or more or a predetermined value or more). The load distribution measurement unit 120 stores the load distribution measurement data in the storage unit 110. The load distribution measuring unit 120 similarly generates load distribution measurement data using the sensor sheets 200a, 200b,... (Not shown in FIG. 6).

  The foot type collating unit 130 identifies the shape of the load region from the measurement data of the load distribution measured by the load distribution measuring unit 120. The foot type collation unit 130 collates the shape of the identified load area with the foot shape stored in the storage unit 110, and whether a person is placed on the sensor sheet 200 (whether the person is in contact with the sensor sheet 200). Determine whether or not. For example, as described above, when the foot shape is represented by a feature vector, the foot shape matching unit 130 converts the shape of the identified load area into a feature vector and indicates the foot shape stored in the storage unit 110. You may collate with a feature vector. In this case, the foot-type collation unit 130 determines that a person is placed on the sensor sheet 200 when both feature vectors match with a predetermined accuracy, and otherwise, no person is placed on the sensor sheet 200. Is determined. The foot collator 130 can also determine that a plurality of persons are placed on the sensor sheet 200 based on the combination of load areas.

  The person attribute determination unit 140 determines attribute information such as the weight and gender of the person on the sensor sheet 200 based on the load distribution measurement data. For example, the person attribute determination unit 140 identifies a load region corresponding to one person from the measurement data of the load distribution, and integrates the load value in the load region, thereby calculating the weight (or weight) of the person. The corresponding amount). The person attribute determination unit 140 determines the gender of the person based on the calculated weight, the shape of the load area corresponding to the person, the load tendency inside and outside the foot, and the like. Here, the load tendency on the inside and outside of the foot represents a tendency that a load is applied to the inside (crotch side) of the sole or a load is applied to the outside (opposite side of the crotch) of the sole. For example, females tend to be loaded on the inner side (inner load tendency), and males tend to be loaded on the outer side (outer load tendency). The person attribute determination unit 140 registers the determined attribute information in the person table stored in the storage unit 110 in association with the person ID of the corresponding person.

  The interest level determination unit 150 determines the level of interest of the person on the sensor sheet 200 with respect to the exhibit 11 based on the load distribution measurement data. For example, the interest level determination unit 150 determines the interest level of the person 50 with respect to the exhibit 11 by determining the stay time, position, moving direction, posture, and the like of the person 50 on the sensor sheet 200. The interest level determination unit 150 obtains the interest level from a plurality of scores. The greater the score, the higher the degree of interest. The interest level determination unit 150 registers the determined interest level in the result table stored in the storage unit 110 in association with the person ID of the corresponding person.

  The analysis processing unit 160 analyzes the tendency of the degree of interest of each exhibit by a plurality of persons using the result table stored in the storage unit 110 and causes the display 21 to display the analysis result. For example, the analysis processing unit 160 may cause the display 21 to display a ranking of exhibits that are relatively highly interested by a plurality of people who have visited the exhibition hall. Alternatively, when the display 21 is arranged beside the exhibit 11, the analysis processing unit 160 displays another exhibit that is interested in another person who is interested in the exhibit 11. An image recommended for the person 50 who is viewing 11 may be displayed on the display 21. Further, the analysis processing unit 160 may display navigation (for example, presentation of a booth number or route display) to the other exhibit on the display 21.

  FIG. 7 is a diagram illustrating an example of load distribution measurement data according to the second embodiment. The load distribution measuring unit 120 uses the sensor sheet 200 to measure a distribution of load values (load distribution) applied to the sensor unit 204 and generate measurement data. The measurement data is a set of load values measured at each grid point (each pressure sensor) of the sensor matrix in the sensor unit 204. For example, the position of each grid point is represented by a two-dimensional (X, Y) coordinate system. Therefore, the measurement data includes a set of (X, Y) coordinate values and a load value measured by the pressure sensor existing at the position represented by the coordinate values for each lattice point.

  In FIG. 7, one grid point is represented by one square. At a position where no load is applied, the load value is zero. In the measurement data, the load value is positive with respect to the position where the load is applied. In FIG. 7, the darker the color, the larger the load value (the same applies to the following drawings). A region represented by consecutive points having a positive load value forms one load region. FIG. 7 shows an example of a load area by a shoe sole of a person's left foot. A map of load values in the load region is called a load pattern.

  FIG. 8 is a diagram illustrating an example of a positional relationship between an exhibit and a person according to the second embodiment. FIG. 8A illustrates the positional relationship between the exhibit 11 and the persons 50 and 60 when the persons 50 and 60 viewing the exhibit 11 are viewed from directly above. For example, one end (upper left of the sensor sheet 200 in FIG. 8A) of the sides of the sensor sheet 200 on the display 11 side is set as the origin (0, 0) of the (X, Y) coordinates. The direction from the left side to the right side in FIG. 8A is taken as the positive direction of the X axis. In addition, the direction from the upper side to the lower side in FIG.

  Speaking of the positional relationship shown in FIG. 8A, the person 50 exists closer to the exhibit 11 than the person 60. The person 60 exists at a position farther from the exhibit 11 than the person 50. When viewing the exhibit 11, the persons 50 and 60 enter the booth of the exhibit 11 from the side with the larger Y coordinate and move to the side with the smaller Y coordinate.

  FIG. 8B illustrates shoe sole regions 51 and 52 corresponding to the person 50 and shoe sole regions 61, 62, 63 and 64 corresponding to the person 60. The shoe sole regions 51 and 52 are, for example, shoe sole regions corresponding to shoe soles of sneakers. The shoe sole regions 61, 62, 63, and 64 are shoe sole regions corresponding to high heels, for example.

  The position of the person 50 on the sensor sheet 200 is represented by the coordinates of the load center point P1 of the load area corresponding to the shoe sole areas 51 and 52. Here, the load center point P1 is the center of gravity of the two load regions corresponding to the shoe sole regions 51 and 52. The center of gravity of the load region may be obtained in consideration of the actually measured load value, or may be obtained with a constant load density in the load region. At this time, the index of the distance between the exhibit 11 and the person 50 is Y coordinate = L1 of the load center point P1.

  Note that the foot-type matching unit 130 determines two load regions corresponding to the shoe sole regions 51 and 52 as distances between both load regions (for example, a distance between the centers of gravity of both load regions) and shape features (two The shape of the load area is bilaterally symmetric and is similar with a predetermined similarity).

  Similarly, the position of the person 60 on the sensor sheet 200 is represented by the coordinates of the load center point P2 of the load region corresponding to the shoe sole regions 61, 62, 63, 64. Here, the load center point P2 is the center of gravity of the four load regions corresponding to the shoe sole regions 61, 62, 63, 64 (may be the center of gravity considering the load value). At this time, the index of the distance between the exhibit 11 and the person 60 is Y coordinate = L2 of the load center point P2.

  In addition, the foot type | mold collation part 130 specifies two load areas corresponding to the shoe sole area | regions 61 and 62 as a 1st load area group by collating with the foot form memorize | stored in the memory | storage part 110, for example. Similarly, the foot type collating unit 130 identifies two load areas corresponding to the shoe sole areas 63 and 64 as the second load area group. The foot collation unit 130 then determines the distance between the first load area group and the second load area group (the distance between the centers of gravity of both groups) and the shape characteristics (of the two load area groups). The shape is symmetrical and similar with a predetermined similarity, etc.).

  FIG. 9 is a diagram illustrating an operation example of a person who becomes a preload according to the second embodiment. The person 50 steps into the area of the sensor sheet 200 (that is, the booth of the exhibit 11) and approaches the exhibit 11 in order to view the exhibit 11. Furthermore, the person 50 brings his eyes close to the exhibit 11 in order to pay more attention to the exhibit 11 (FIG. 9A). At this time, the person 50 is in a forward leaning posture and has a preload.

  In addition, the person 50 may touch the exhibit 11 in order to observe the exhibit 11 in more detail (FIG. 9B). In this case, in order to touch the exhibit 11, the person 50 assumes a forward leaning posture and a preload.

  FIG. 10 is a diagram illustrating an example of a load pattern indicating a preload according to the second embodiment. FIG. 10A illustrates load patterns 310 and 320 when the person 50 takes the right foot forward of the left foot and assumes a forward leaning posture. The forward direction of the person 50 (the direction in which the foot is advanced forward) is the shape of the load patterns 310 and 320 (the front side with the toes and the stepping parts swells more than the rear side with the heel (width It is specified by (large) shape. The interest level determination unit 150 determines that the person 50 is facing the direction of the exhibit 11 when the forward direction of the person 50 is facing the negative direction of the Y axis. The load pattern 310 is a left foot load pattern. The load pattern 320 is a right foot load pattern.

The load pattern 310 has regions 311, 312, and 313.
A region 311 is a region on the toe side of the left sole. A region 311 is a region to which a relatively large load value belongs in the case of a preload. A region 312 is a central portion of the left foot sole. A region 312 is a region to which a load value smaller than the region 311 belongs in the case of a preload. An area 313 is an area on the heel side of the left sole. A region 313 is a region to which a load value smaller than that of the region 312 belongs.

The load pattern 320 has regions 321, 322 and 323.
An area 321 is an area on the toe side of the right foot sole. The region 321 is a region to which a relatively large load value belongs in the case of a preload. A region 322 is a region at the center of the right foot sole. The region 322 is a region to which a load value smaller than the region 321 belongs in the case of the preload. The region 323 is a region on the heel side of the right foot sole. The region 323 is a region to which a load value smaller than that of the region 322 belongs.

  When the person 50 puts his right foot forward of the left foot and assumes a forward leaning posture, the region 321 tends to be a region wider than the region 311. The degree-of-interest determination unit 150 can determine that the load is a pre-load for the person 50 with respect to the two load areas specified by being shifted in the front-rear direction. That is, the interest level determination unit 150 has a relatively large area (for example, areas 311 and 321) with a large load value on the toe side, such as the load patterns 310 and 320, and a foot load pattern (for example, load) on the front side. When the corresponding area (for example, the area 321) of the pattern 320) is larger than the corresponding area (for example, the area 311) of the foot load pattern (for example, the load pattern 310) on the rear side, the person 50 is in the forward leaning posture. Judge that there is. Even when the person 50 puts his left leg forward of the right leg and assumes a forward leaning posture, it is similarly determined whether the person 50 is in the forward leaning posture (with the left and right of the determination condition reversed).

  FIG. 10B illustrates load patterns 330 and 340 when the person 50 is in a forward tilt posture with the right foot and the left foot aligned. The load pattern 330 is a left foot load pattern. The load pattern 340 is a right foot load pattern.

The load pattern 330 has regions 331, 332, and 333.
The region 331 is a region on the toe side of the left sole. The region 331 is a region to which a relatively large load value belongs in the case of a preload. A region 332 is a region of the center part of the left sole. The region 332 is a region to which a load value smaller than the region 331 belongs in the case of a preload. A region 333 is a region on the heel side of the left sole. The region 333 is a region to which a load value smaller than that of the region 332 belongs.

The load pattern 340 has regions 341, 342, and 343.
The region 341 is a region on the toe side of the right foot sole. A region 341 is a region to which a relatively large load value belongs in the case of a preload. A region 342 is a region at the center of the right foot sole. The region 342 is a region to which a load value smaller than the region 341 belongs in the case of the preload. The region 343 is a region on the heel side of the right foot sole. The region 343 is a region to which a load value smaller than that of the region 342 belongs.

  When the person 50 has the right and left feet aligned and assumes a forward leaning posture, the regions 331 and 341 are regions of the same size. Therefore, the degree-of-interest determination unit 150 can determine that the load is a preload with respect to the two load areas specified in the front-rear direction with respect to the person 50 as follows. That is, the degree-of-interest determination unit 150 has a relatively large range of load values on the toe side, such as the load patterns 330 and 340, and the range on the toe side is the same for both load patterns (within a predetermined error). The person 50 is determined to be in a forward leaning posture.

  FIG. 11 is a diagram illustrating an example of a foot table according to the second embodiment. The foot table 111 is stored in the storage unit 110 in advance. The foot type table 111 includes items of a foot type ID and a foot type pattern.

  In the foot type ID item, foot type identification information (foot type ID) is registered. In the foot pattern item, information indicating a typical foot shape of a person is registered. The information indicating the shape of the foot shape may be image information indicating the shape of the foot shape, or may be a feature vector corresponding to the shape of the foot shape. When registering a feature vector corresponding to a foot shape, information on the size (area) of the foot shape (not shown in FIG. 11) is also registered in the foot table 111 as a foot pattern. .

  For example, a record with a foot pattern ID “a” and a foot pattern “p1” is registered in the foot pattern table 111. This record indicates that a typical human foot pattern “p1” is registered in advance for the foot pattern ID “a”. In the foot pattern table 111, records including a foot pattern ID and a foot pattern are registered in the same manner for other foot patterns.

  The foot type table 111 is created in advance by the server 100 by machine learning based on, for example, information on the human foot type (the shape of soles and soles) sampled in advance, and is stored in the storage unit 110 in advance. Stored.

  FIG. 12 is a diagram illustrating an example of a person table according to the second embodiment. The person table 112 is stored in the storage unit 110 in advance. The person table 112 includes information on a person ID, a measured foot pattern, a weight, a load feature amount, and sex.

  Person identification information (person ID) is registered in the item of person ID. In the item of the actually measured foot pattern, information indicating the shape of the actually measured foot shape is registered. As described above, the information indicating the shape of the foot shape may be image information indicating the shape of the foot shape, or may be a feature vector corresponding to the shape of the foot shape. In the case where the foot molds of both feet are used for collation, image information and feature vectors corresponding to the shape of the foot molds of both feet (two feature vectors, one for each of the left and right) may be used. In the body weight item, the body weight (or a value corresponding to the body weight) measured based on the load pattern is registered. A feature amount (load feature amount) representing a load pattern is registered in the item of load feature amount. The load feature amount is an amount representing a tendency of distribution of load values in the load pattern. Sex is registered in the item of gender.

  For example, a record in which the person ID is “U1”, the actually measured foot pattern is “Y1”, the weight is “W1”, the load feature amount is “C1”, and the gender is “male” is registered in the person table 112. . This record indicates that the actually measured foot pattern “Y1” is acquired for the person indicated by the person ID “U1”. In addition, this record indicates that the weight “W1”, the load feature amount “C1”, and the sex “male” are acquired for the actually measured load pattern for the person indicated by the person ID “U1”.

In the person table 112, records including the actually measured foot pattern, the weight, the load feature amount, and the gender are registered for the person ID in the same manner.
FIG. 13 is a diagram illustrating an example of a result table according to the second embodiment. The result table 113 is stored in the storage unit 110 in advance. The result table 113 includes items of item number, time, exhibit ID, person ID, and interest level.

  In the item number item, a number for identifying the record is registered. The time at which the record was recorded is registered in the time item. Exhibit identification information (exhibit ID) is registered in the item of exhibit ID. Person identification information (person ID) is registered in the item of person ID. In the item of interest level, the degree of interest in a person's exhibit is registered.

  For example, in the result table 113, a record having an item number “1”, a time “T1”, an exhibit ID “A1”, a person ID “U1”, and an interest level “2” is registered. This record is identified by item number “1” and indicates that it was recorded at time “T1”. Further, this record indicates that the interest level of the person with the person ID “U1” with respect to the exhibit with the exhibit ID “A1” is “2”. In the result table 113, similar records are registered for the interest level of each person with respect to each exhibit.

  Next, a processing procedure by the server 100 will be described. In the following description, an example in which the sensing result by the sensor sheet 200 is detected will be described. However, the procedure for other sensor sheets (for example, the sensor sheets 200a, 200b,...) Is the same procedure.

FIG. 14 is a flowchart illustrating an example of information collection processing according to the second embodiment. In the following, the process illustrated in FIG. 14 will be described in order of step number.
(S11) The load distribution measuring unit 120 detects an input to the sensor sheet 200 and acquires measurement data. Specifically, the load distribution measurement unit 120 detects a positive load value (may be a load value equal to or greater than a predetermined threshold) by the pressure sensor of the sensor unit 204 of the sensor sheet 200. The load distribution measurement unit 120 identifies a load region based on the positions of a plurality of pressure sensors that have detected a load value continuously for a certain period of time (for example, about several seconds) (to identify a person who has stopped). Further, the load distribution measuring unit 120 acquires a load pattern in the load region. The load distribution measuring unit 120 stores the load area information and the load pattern information in the storage unit 110 in association with the sensor ID of the sensor sheet 200. Note that when the load value is detected instantaneously, it is estimated that only a person or the like has passed on the sensor sheet 200, so the load distribution measurement unit 120 does not load the sensor sheet 200 instantaneously. Detection of a value need not be considered as an input.

  (S12) The foot collator 130 performs foot pattern matching. Specifically, the foot type collating unit 130 stores the shape of the load region and the size (area) of the load region acquired by the load distribution measuring unit 120 for each foot of the foot type table 111 stored in the storage unit 110. Match with type pattern. The foot-type collation unit 130 identifies a foot-shaped pattern that best matches the shape of the load region by collation, and obtains a degree of coincidence (degree of coincidence) between the two. The matching of the foot pattern may be performed on the foot pattern of one foot or may be performed on the foot pattern of both feet. In addition, the foot collator 130 may perform the foot pattern matching using both the shape of the load region and the size of the load region, or any one of them.

  (S13) The foot type collation unit 130 determines whether or not a person is placed on the sensor sheet 200 based on the pattern matching result in step S12. If it is determined that a person has been placed, the foot collation unit 130 proceeds to step S14. If it is determined that no person is present, the foot collator 130 ends the process. For example, the foot-type matching unit 130 determines that a person is placed when the degree of matching obtained in step S12 is greater than a predetermined value, and determines that no person is placed when the degree of matching is equal to or less than a predetermined value. To do.

  (S14) The person attribute determination unit 140 measures the weight of the person detected this time. Specifically, the person attribute determination unit 140 calculates the integral value of the load value of the load pattern in the load region used for the pattern matching in step S12 as a value corresponding to the weight of the person.

  (S15) The person attribute determination unit 140 determines the gender of the person detected this time. For example, the person attribute determination unit 140 determines the sex of the person based on the shape of the load area, the weight, and the load tendency in the load pattern. More specifically, as illustrated in FIG. 8 (B), the shape of the load region is formed by a combination of several load region portions, and the footwear mainly worn by women such as high heels is used. When it is considered that this is the case, the person attribute determination unit 140 can determine the gender of the person as female. At this time, the person attribute determination unit 140 may consider weight (for example, a load area corresponding to high heels is detected and determined to be female when the weight is equal to or less than a predetermined weight).

  Alternatively, when it is considered that the shape of the load area corresponds to footwear used by both men and women like sneakers, the person attribute determination unit 140 determines the gender of the person based on the weight tendency in the weight or load pattern. Can be determined. For example, when the weight is relatively large (for example, larger than a predetermined weight) and the load tendency in the load pattern is an outer load tendency, the person attribute determination unit 140 determines the sex of the person as male. On the other hand, when the weight is relatively small (for example, a predetermined weight or less) and the load tendency in the load pattern is an inner load tendency, the person attribute determination unit 140 determines the sex of the person as female. As another method, a size such as the length or width of a shoe is obtained from the size of the load area, and men or women may be further narrowed down according to the size (for example, if the length of the shoe is larger than a predetermined length). Male, female if less than specified length). The gender determination method illustrated here is an example, and the person attribute determination unit 140 may determine gender by another method. Details of the process in step S15 will be described later.

  (S16) The person attribute determination unit 140 determines whether or not the person detected this time is a new person. If the person is a new person, the person attribute determination unit 140 proceeds to step S17. If the person is not a new person, the person attribute determination unit 140 proceeds to step S18. Here, the new person means an unregistered person in the person table 112 stored in the storage unit 110. For example, the person attribute determination unit 140 obtains a load feature amount by executing a predetermined calculation based on the load pattern of the person detected this time. Then, the person attribute determination unit 140 indicates the actually measured foot pattern registered in the person table 112, the weight, the load feature amount, and the sex, and the actually measured foot pattern obtained for the current person (the shape of the load region is shown). Information), body weight, load feature, and gender. When it is determined that a record including the same attribute information as the current person is already registered in the person table 112 by the collation, the person attribute determination unit 140 determines that the person is not a new person. On the other hand, if it is determined that a record including the same attribute information as the current person is not registered in the person table 112, the person attribute determination unit 140 determines that the person is a new person.

  (S17) The person attribute determination unit 140 registers the attribute information of the person (new person) detected this time in the person table 112. Specifically, the person attribute determination unit 140 newly assigns a person ID to a new person. Then, the person attribute determination unit 140 registers the actually measured foot pattern, weight, load feature amount, and gender obtained this time in the person table 112 in association with the newly assigned person ID.

  (S18) The interest level determination unit 150 determines the interest level (interest level determination) for the exhibit 11 by the person detected this time. Details of the interest level determination will be described later. Here, as described above, the sensor sheet 200 and the exhibit 11 are associated one-to-one. For this reason, the interest level determination unit 150 identifies the exhibit ID of the exhibit 11 based on the sensor ID of the sensor sheet 200.

  (S19) The interest level determination unit 150 registers the interest level of the exhibit 11 by the person detected this time in the result table 113 stored in the storage unit 110. Specifically, the interest level determination unit 150 registers information on the item number, time, exhibit ID, person ID, and interest level in the result table 113.

  Note that the load distribution measurement unit 120 may detect a plurality of load regions corresponding to a plurality of persons with respect to the sensor sheet 200 (for example, as illustrated in FIGS. 8A and 8B). A plurality of persons may be placed on the sensor sheet 200). In this case, the load distribution measuring unit 120 specifies a load region (or load region group) corresponding to the left foot (or right foot) from collation with a foot pattern registered in advance. Then, the load distribution measuring unit 120 identifies a load region (which may be called a set of load regions) corresponding to the left and right feet of one person from the symmetry of the left and right foot shapes and the proximity of the distance. To do. In addition, the foot-type collation unit 130, the person attribute determination unit 140, and the interest level determination unit 150 execute the processes after step S12 on the load areas corresponding to the left and right feet of the selected single person. To do. When the load area is specified for a plurality of persons, the foot pattern matching unit 130, the person attribute determining unit 140, and the interest level determining unit 150 sequentially perform the processing from step S12 on each person. .

  FIG. 15 is a flowchart illustrating an example of gender determination processing according to the second embodiment. In the following, the process illustrated in FIG. 15 will be described in order of step number. The procedure shown below corresponds to step S15 in FIG.

  (S21) The person attribute determination unit 140 determines whether or not the shape of the load area detected this time corresponds to the back surface (sole) of the footwear for women. When the shape of the load region corresponds to the back side of the footwear for women, the person attribute determination unit 140 proceeds with the process to step S28. If the shape of the load region does not correspond to the back side of the footwear for women, the person attribute determination unit 140 proceeds with the process to step S22. For example, as described above, when the shape of the load region corresponds to the back side of the high heel (shoe sole) used mainly for women, the person attribute determination unit 140 corresponds to the back side of the footwear for women. Judge that. On the other hand, when the shape of the load area corresponds to the back surface (sole) of the sneaker used for both men and women, the person attribute determination unit 140 determines that the shape of the load area does not correspond to the back surface of the footwear for women. To do. Patterns of the shapes of the back surfaces (shoe soles) of various shoes such as high heels and sneakers are stored in the storage unit 110 in advance.

  (S22) The person attribute determination unit 140 determines whether the weight of the person detected this time is greater than a predetermined weight. If the weight of the person is greater than the predetermined weight, the person attribute determination unit 140 proceeds to step S23. If the weight of the person is less than or equal to the predetermined weight, the person attribute determination unit 140 proceeds with the process to step S26. For example, as the predetermined weight, a weight value corresponding to 50 kg (unit may be arbitrary) is set in advance.

  (S23) The person attribute determination unit 140 determines whether or not the size of the load area detected this time is larger than a predetermined size. If the size of the load area is larger than the predetermined size, the person attribute determination unit 140 proceeds to step S25. If the size of the load area is equal to or smaller than the predetermined size, the person attribute determination unit 140 proceeds to step S24. Here, as the size of the load region, for example, the length in the major axis direction of the load region can be used. Or you may use the length of the width direction orthogonal to the major axis direction of a load area | region as a size of a load area | region. As yet another example, the area of the load region may be used as the size of the load region.

  (S24) The person attribute determination unit 140 determines whether or not the load pattern of the load region detected this time has an outward load tendency. If the load pattern of the load area has an outward load tendency, the person attribute determination unit 140 proceeds to step S25. If the load pattern of the load area is not the outward load tendency, the person attribute determination unit 140 proceeds to step S28. For example, the human attribute determination unit 140 determines that the load pattern in the load area has an outward load tendency when a larger load value is distributed in the area outside the load area than in the area inside the load area. Judge that there is. In other cases, the person attribute determination unit 140 determines that the load pattern of the load region does not have an outward load tendency.

(S25) The person attribute determination unit 140 determines that the gender of the person detected this time is male. Then, the person attribute determination unit 140 ends the process.
(S26) The person attribute determination unit 140 determines whether or not the size of the load area detected this time is equal to or smaller than a predetermined size. If the size of the load area is equal to or smaller than the predetermined size, the person attribute determination unit 140 proceeds to step S28. If the size of the load area is larger than the predetermined size, the person attribute determination unit 140 proceeds to step S27. Here, as exemplified in step S23, the person attribute determination unit 140 may use the length in the major axis direction, the length in the width direction, or the area of the load region as the size of the load region. it can.

  (S27) The person attribute determination unit 140 determines whether or not the load pattern of the load region detected this time has an inner load tendency. If the load pattern of the load area has an inner load tendency, the person attribute determination unit 140 proceeds to step S28. If the load pattern of the load area is not the inner load tendency, the person attribute determination unit 140 proceeds to step S25. For example, the human attribute determination unit 140 determines that the load pattern in the load area has an inner load tendency when a larger load value is distributed in the area inside the load area than in the area outside the load area. Judge that there is. In other cases, the person attribute determination unit 140 determines that the load pattern of the load region does not have the inner load tendency.

(S28) The person attribute determination unit 140 determines that the gender of the person detected this time is female. Then, the person attribute determination unit 140 ends the process.
As described above, the person attribute determination unit 140 narrows down the gender of the person step by step according to the shape and size of the load region and the load tendency of the load pattern in the load region. Thereby, the gender determination accuracy of the person can be improved. Note that the reason why the male is determined to be male in the case of the external load tendency is that, in general, the ratio of males to the external load tendency is high. On the other hand, the reason for determining a woman in the case of an inner load tendency is that, in general, the proportion of women who are in an inner load tendency is high. Further, the person attribute determination unit 140 can further improve the determination accuracy of the gender of the person by determining the gender of the person using the weight measured for the person.

  Note that information indicating a classification such as female-only, male-only, or bisexuality may be registered in advance in each record of the foot table 111. In this case, in step S21, the person attribute determination unit 140 may proceed to step S25 to determine the gender of the person as male when it corresponds to the back side of the footwear for men only.

  FIG. 16 is a flowchart illustrating an example of interest level determination processing according to the second embodiment. In the following, the process illustrated in FIG. 16 will be described in order of step number. The procedure shown below corresponds to step S18 in FIG. The initial value of the interest level Q immediately before step S31 is set to Q = 0.

  (S31) The interest level determination unit 150 sets the interest level Q = 1 by stopping the person in the area in front of the exhibit 11 (the floor area covered by the sensor unit 204). The interest level determination unit 150 starts measuring the staying time on the sensor sheet 200 for the person detected this time.

  (S32) The interest level determination unit 150 determines whether or not points of time have been added to the interest level Q. When the points based on time have been added, the interest level determination unit 150 proceeds with the process to step S35. If the points due to time have not been added, the interest level determination unit 150 proceeds with the process to step S33. Here, the addition of points according to time means addition of points to the degree of interest based on the person's stay time on the sensor sheet 200.

  (S33) The interest level determination unit 150 determines whether or not the stay time of the corresponding person on the sensor sheet 200 is equal to or longer than a predetermined time. The predetermined time is, for example, 30 seconds or 1 minute. When the stay time of the corresponding person on the sensor sheet 200 is equal to or longer than the predetermined time, the interest level determination unit 150 proceeds with the process to step S34. When the stay time of the person on the sensor sheet 200 is less than the predetermined time, the interest level determination unit 150 proceeds with the process to step S35.

  (S34) The interest level determination unit 150 adds 1 point to the interest level Q. This is because it is estimated that the longer the person's stay time on the sensor sheet 200 is, the higher his interest in the exhibit 11 is.

  (S35) The degree-of-interest determination unit 150 determines whether the points based on the distance have been added to the degree of interest Q. When the points based on the distance have been added, the interest level determination unit 150 proceeds with the process to step S38. When the points based on the distance have not been added, the interest level determination unit 150 proceeds with the process to step S36. Here, the addition of points by distance means addition of points of interest level due to a change in the position of a person on the sensor sheet 200.

  (S36) The degree-of-interest determination unit 150 determines whether the corresponding person has approached the exhibit 11 within a predetermined distance. The predetermined distance is, for example, 50 cm or 1 m. When the corresponding person approaches within a predetermined distance from the exhibit 11, the interest level determination unit 150 proceeds with the process to step S37. When the corresponding person is away from the exhibit 11 by a predetermined distance, the interest level determination unit 150 proceeds with the process to step S38.

  (S37) The interest level determination unit 150 adds 1 point to the interest level Q. This is because when a person moves on the sensor sheet 200 closer to the exhibit 11, the person's interest in the exhibit 11 is estimated to be high.

  (S38) The interest level determination unit 150 determines whether or not the points due to the load have been added to the interest level Q. When the points due to the load have been added, the interest level determination unit 150 proceeds with the process to step S42. If the points due to the load have not been added, the interest level determination unit 150 proceeds with the process to step S39. Here, the addition of points by load means the addition of points of interest based on the forward leaning posture of the person illustrated in FIGS.

  (S39) The interest level determination unit 150 determines the direction (forward direction) of the corresponding person. As described above, the interest level determination unit 150 determines the orientation of the person based on the shape of the load region (or load pattern). For example, the front side with the toes and the stepping part has a swelled shape (wider) than the back side with the heel, so it corresponds to both ends of the load area in the long axis direction of the foot shape The larger side of the region (in the direction orthogonal to the long axis) is determined as the front side of the person. On the other hand, the front side and the opposite side are determined as the back side of the person. The direction from the rear side to the front side of the person is the front direction of the person. As described above, the interest level determination unit 150 identifies the direction (forward direction) in which the person is facing based on the shape and / or size of the pressure-applied region corresponding to the person.

  (S40) The degree-of-interest determination unit 150 determines, based on the distribution of load values in the load pattern, whether the corresponding person faces the exhibit 11 and is a preload. When it is a preload facing the exhibit 11, the interest level determination unit 150 proceeds with the process to step S41. When facing the exhibit 11 and not the preload, the interest level determination unit 150 proceeds to step S42. For example, the degree-of-interest determination unit 150 determines that the forward direction of the person 50 is in the negative direction of the Y axis, and the load pattern acquired for the person is the load of the preload illustrated in FIG. If it matches the pattern, it is determined that it is a preload facing the exhibit 11. On the other hand, the interest level determination unit 150 determines that the load pattern acquired for the corresponding person when the front direction of the person 50 does not face the negative direction of the Y axis is the preload illustrated in FIG. When it does not conform to the load pattern, it is determined that it is not a preload by facing the exhibit 11.

  (S41) The interest level determination unit 150 adds 1 point to the interest level Q. This is because when the person is leaning forward, it is considered that the person is paying attention to or touching the exhibit 11, and the person's interest in the exhibit 11 is This is because it is estimated to be high.

  (S42) The interest level determination unit 150 determines whether the corresponding person has left the front of the exhibit 11. When it leaves, the interest degree determination part 150 complete | finishes a process (the measurement of the stay time with respect to the applicable person is stopped). As a result, the degree of interest Q for the exhibit 11 of the corresponding person is determined. If the user has not left, the degree-of-interest determination unit 150 proceeds with the process to step S32.

  For example, the interest level determination unit 150 determines that the corresponding person has left the front of the exhibit 11 when no load area corresponding to the foot pattern of the corresponding person is detected in the sensor sheet 200. On the other hand, the interest level determination unit 150 determines that the corresponding person has not left the front of the exhibit 11 when the load area corresponding to the foot pattern of the corresponding person is continuously detected in the sensor sheet 200. To do.

  Note that, in step S40, the interest level determination unit 150 may add that the corresponding person exists within a predetermined distance from the exhibit 11 as a condition for adding points by load. This is because, as illustrated in FIG. 9, when a person pays attention to or touches the exhibit 11, the person approaches the exhibit 11. That is, by adding the fact that the corresponding person exists within a predetermined distance from the exhibit 11 to the condition for adding points based on the load, it is possible to further improve the determination accuracy of the interest level of the person.

  In this way, the degree-of-interest determination unit 150 determines the object of the person (for example, the exhibit 11) according to the direction in which the identified person is facing and the pressure distribution (load pattern) corresponding to the detected person. ). In particular, the degree-of-interest determination unit 150 estimates the degree of interest (degree of interest) in a stepwise manner according to at least one of the time when the identified person has contacted the sensor sheet 200 and the position of contact. As a result, the server 100 can acquire the degree of interest of the person in the exhibit 11 in detail. The interest level determination unit 150 may cause the display 21 to display the level of interest in the exhibit 11 determined this time for the corresponding person.

  In addition, the interest level determination unit 150 may determine whether a person is interested in or not interested in the exhibit 11 according to a part of the procedures described above (two patterns of interest or not). May be determined). For example, the degree-of-interest determination unit 150 may determine the direction of the person from the load area, and determine whether there is interest or not according to whether the load is a preload based on the load pattern. More specifically, the interest level determination unit 150 may determine that there is interest if it is a preload, and may determine that there is no interest if it is not a preload.

  The server 100 can analyze the records in the result table 113 collected by the procedure illustrated in FIG. 14, and can be used for improving services in the exhibition hall, marketing, and the like. Next, an example of such an analysis will be described.

FIG. 17 is a flowchart illustrating an example of analysis processing according to the second embodiment. In the following, the process illustrated in FIG. 17 will be described in order of step number.
(S51) The analysis processing unit 160 analyzes the interest pattern for each person based on the result table 113 stored in the storage unit 110. Specifically, the analysis processing unit 160 refers to the result table 113, and specifies the time series of the exhibit ID of the exhibit traced by a person with a certain person ID and the interest level for each exhibit. The analysis processing unit 160 performs the identification for each person ID.

  (S52) Based on the result of step S51, the analysis processing unit 160 stores the order in which the person with a certain person ID traces the exhibits and the degree of interest in each exhibit in the interest pattern table stored in the storage unit 110. Record.

  FIG. 18 is a diagram illustrating an example of an interest pattern table according to the second embodiment. The interest pattern table 114 is created based on the result table 113 by the analysis processing unit 160 and stored in the storage unit 110. The interest pattern table 114 includes items of person ID, exhibit ID1, interest level q1, exhibit ID 2, interest level q2,.

  A person ID is registered in the item of person ID. In the item of exhibit ID 1, the exhibit ID of the exhibit that the person concerned visited first in the exhibition hall is registered. In the item of the interest level q1, the interest level of the corresponding person with respect to the exhibit that the corresponding person visited first is registered. In the item of exhibit ID2, the exhibit ID of the exhibit that the person concerned visited second time in the exhibition hall is registered. In the item of the interest level q2, the interest level of the corresponding person with respect to the exhibit that the corresponding person visited for the second time is registered. Thereafter, the interest pattern table 114 includes a set of interest levels for the third exhibit and the third exhibit, a set of interest rates for the fourth exhibit and the fourth exhibit, and so on. A set of exhibit ID and interest level is registered in order.

  For example, in the interest pattern table 114, the person ID is “U1”, the exhibit ID 1 is “A1”, the interest level q1 is “2”, the exhibit ID 2 is “A3”, the interest level q2 is “4”,.・ Record is registered. In this record, the person with the person ID “U1” has the first exhibit indicated by the exhibit ID 1 “A1”, the second exhibit indicated by the exhibit ID 2 “A3” in the exhibition hall, ······················································································································ Furthermore, the degree of interest q1 for the first exhibit of the person with the person ID “U1” is “2”, and the degree of interest q2 for the second exhibit is “4”,. In the interest pattern table 114, records of interest patterns are similarly registered for other persons.

  For example, based on the interest pattern table 114, the analysis processing unit 160 can obtain the interest and tendency of interest for each exhibit with respect to an unspecified number of people. Specifically, when there are a relatively large number of persons who are interested in the first exhibit and the second exhibit, the first exhibit and the second exhibit include many persons. It is presumed that there is a common factor that is of interest. Therefore, based on the interest pattern table 114, the analysis processing unit 160 guides the exhibition (navigation) according to the analysis to the person who is interested in the exhibit 11 (the person currently staying in the booth of the exhibit 11). ) May be performed. In the following description, as an example, the display 21 is installed beside the exhibit 11 (next to the exhibit 11 on the display stand 10), and a person viewing the exhibit 11 can see the screen of the display 21. It shall be possible.

  FIG. 19 is a flowchart illustrating an example of guidance processing according to the second embodiment. In the following, the process illustrated in FIG. 19 will be described in order of step number. For example, the analysis processing unit 160 periodically executes the following procedure at a predetermined cycle.

  (S61) The analysis processing unit 160 determines whether or not a person is staying in front of the exhibit 11. When a person is staying in front of the exhibit 11, the analysis processing unit 160 proceeds to step S62. When the person is not staying in front of the exhibit 11, the analysis processing unit 160 ends the process. For example, the analysis processing unit 160 determines whether or not the person is staying in front of the exhibit 11 based on the determination result of whether or not the person is placed on the sensor sheet 200 by the foot collation unit 130 in steps S12 and S13. judge. Specifically, when the person is on the sensor sheet 200, the analysis processing unit 160 is staying in front of the exhibit 11, and when the person is not on the sensor sheet 200, the analysis processing unit 160 It is determined that the person is not staying before.

  (S62) The analysis processing unit 160 determines whether or not the interest level Q of the corresponding person with respect to the exhibit 11 has reached a threshold value (that is, whether or not Q has exceeded the threshold value). When the interest level Q has reached the threshold value, the analysis processing unit 160 proceeds to step S63. When the interest level Q has not reached the threshold value, the analysis processing unit 160 ends the process. The analysis processing unit 160 performs the determination in step S <b> 62 by monitoring the point addition status with respect to the interest level Q of the corresponding person by the interest level determination unit 150. A threshold value for Q is preset in the analysis processing unit 160 (for example, a threshold value for Q = 3).

  (S63) Based on the interest pattern table 114 stored in the storage unit 110, the analysis processing unit 160 displays guidance on recommended exhibits on the display 21. For example, based on the interest pattern table 114, the analysis processing unit 160 may have another person who has been interested in the exhibit 11 after visiting the exhibit 11 (or before visiting the exhibit 11). The name of the exhibit and the booth number of the other exhibit are displayed on the display 21.

  Alternatively, the analysis processing unit 160 may cause the display 21 to display the way to the booth corresponding to the booth number. In addition, the analysis processing unit 160 may guide another exhibit that is interested in another person of the same gender as the person in front of the current exhibit 11.

  FIG. 20 is a diagram illustrating an example of guidance display according to the second embodiment. The analysis processing unit 160 generates information on the guidance display 400 and outputs it to the display 21. The analysis processing unit 160 displays the guidance display 400 on the display 21.

  For example, the guidance display 400 says, “Persons who are interested in this exhibit are also interested in the exhibition“ XXX ”in booth # 5. For example, the person who has seen the guidance display 400 can decide to go to the fifth booth.

  In addition to the guidance display, the analysis processing unit 160 may cause the display 21 to display a ranking of exhibits that have obtained a relatively high degree of interest from a large number of people who have visited the exhibition hall. For example, the analysis processing unit 160 refers to the result table 113, calculates the total value of the interest level for each exhibit, ranks each exhibit in descending order of the total interest level, , Etc.) may be displayed on the display 21. The analysis processing unit 160 may periodically execute such ranking and change the content of the ranking displayed on the display 21.

  As described above, the analysis processing unit 160 changes the display content of the display 21 (display device) installed together with the exhibit (target object) according to the estimation result of the degree of interest, so that the person who visited the exhibition hall Can support efficient patrols. As the display contents, various contents such as the degree of interest estimated for the corresponding person, the guidance display 400 to other exhibits, and the ranking of interest for each exhibit as described above can be considered. . The analysis processing unit 160 may switch these contents at a predetermined cycle and display them on the display 21.

  Furthermore, in the second embodiment, an example in which the sensor sheets 200, 200a, 200b,... Are provided in the exhibition hall is shown, but they may be provided in other facilities. For example, it may be possible to provide sensor sheets 200, 200a, 200b,... For each product in a store where a product is sold to a customer. Also in this case, the server 100 can collect and analyze the degree of interest for each product of the customer.

  Thus, according to the measurement system of the second embodiment, the state of a person can be easily estimated. For example, it is conceivable to investigate the interests, interests, satisfaction, etc. of participants by questionnaires using paper or the Web for an unspecified number of people who have visited an exhibition hall or a store. However, such a method places a heavy burden on the responding person. A method of analyzing the user's preference by collecting a person's body temperature, sweating, heart rate, and on / off of the switch by the person is also conceivable, but this method also has a heavy burden on the person side. On the other hand, for example, it is also conceivable to install a camera to monitor a person's action and estimate the state of the person from the person's action using an image processing technique. However, since monitoring with a camera is information that can be used to identify and identify an individual, the captured image may give bad impression to the person.

  Therefore, the server 100 estimates the state of the person using the pressure detection result by the sensor sheets 200, 200a, 200b,. This makes it easier to estimate the person's condition with relatively simple equipment than using many sensors that measure the body temperature, sweating, heart rate, etc., or installing a camera that monitors the person's behavior. It becomes possible. In particular, since it is only necessary for the person to step on the sensor sheet 200, 200a, 200b,. Since it is not necessary to force the person to take special actions, the burden on the person can be reduced compared to a method in which answers are made using paper or switches. Furthermore, it is not necessary to give the person an unpleasant feeling as in the case of monitoring with a camera. Further, by using the measurement system according to the second embodiment, there is an advantage that it is possible to efficiently investigate the degree of interest in exhibits and products for an unspecified number of people.

  The information processing according to the first embodiment can be realized by causing a processor that functions as the determination unit 1c or the estimation unit 1d to execute a program. The information processing according to the second embodiment can be realized by causing the processor 101 to execute a program. The program can be recorded on a computer-readable recording medium 23.

  For example, the program can be distributed by distributing the recording medium 23 on which the program is recorded. Alternatively, the program may be stored in another computer and distributed via a network. For example, the computer stores (installs) a program recorded in the recording medium 23 or a program received from another computer in a storage device such as the RAM 102 or the HDD 103, and reads and executes the program from the storage device. Good.

DESCRIPTION OF SYMBOLS 1 Measuring apparatus 1a Memory | storage part 1b Pressure detection part 1c Judgment part 1d Estimation part 2 Load distribution 2a, 2b Load area | region 3 Person 4 units | set 5 Object m1 Sensor matrix

Claims (10)

The pressure is detected by the pressure detector,
It is determined whether a person is in contact with the pressure detection unit based on the detected shape and / or size of the pressure-applied region,
When it is determined that the person is in contact, the state of the person is estimated according to the distribution of the magnitude of the pressure corresponding to the detected person.
A measurement program for causing a computer to execute processing.   The computer according to claim 1, wherein the computer is configured to identify a direction and / or sex that the person is facing based on a shape and / or size of a pressure area corresponding to the person. Measurement program.   According to the specified direction of the person and the distribution of the magnitude of pressure corresponding to the detected person, the computer is caused to execute a process of estimating the degree of interest in the object of the person. The measurement program according to claim 2.   The measurement program according to claim 3, wherein the computer executes a process of estimating the degree of interest according to at least one of a time when the identified person contacts the pressure detection unit and a position where the person contacts. .   5. The measurement program according to claim 3, wherein the computer executes a process of changing a display content of a display device installed together with the object according to the estimation result of the degree of interest. In determining whether the person is in contact with the pressure detection unit, determine whether the sole of the person's foot is in contact with the pressure detection unit,
In the estimation of the state of the person, the state of the person is estimated according to the distribution of the magnitude of the pressure corresponding to the sole of the person.
The measurement program according to claim 1, wherein the process is executed by a computer.   The computer according to claim 1, wherein the pressure detection unit causes a computer to execute a process of detecting the pressure applied to the pressure detection unit by an object placed on the pressure detection unit. The described measurement program.   The measurement program according to claim 1, wherein the pressure detection unit is provided on a walking surface on which the person walks. The pressure is detected by the pressure detector,
It is determined whether a person is in contact with the pressure detection unit based on the detected shape and / or size of the pressure-applied region,
When it is determined that the person is in contact, the state of the person is estimated according to the distribution of the magnitude of the pressure corresponding to the detected person.
A measurement method, wherein a computer executes processing. A pressure detector for detecting pressure;
A determination unit that determines whether a person is in contact with the pressure detection unit based on the detected shape and / or size of the pressure-applied region;
An estimation unit that estimates the state of the person according to the distribution of the magnitude of the pressure corresponding to the detected person when it is determined that the person is in contact;
A measuring apparatus comprising:

Images