JP7353127B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

BACKGROUND ART Conventionally, techniques have been proposed that acquire various sensor information from a terminal device owned by a user and acquire information regarding the user based on the acquired various sensor information.

An example of such technology is a sensor that detects changes in the acceleration of the subject's trunk in the forward direction and lateral or vertical directions; means for estimating physical strength age from the ratio of the change in the direction of travel detected by the sensor and the change in the lateral direction, and the correlation stored in the storage section; There are known pedometers and the like that are characterized by the following.

Japanese Patent Application Publication No. 2007-089703

However, with the above-mentioned conventional technology, although it is possible to estimate the user's physical strength and age from the correlation between acceleration changes and age, it is not possible to estimate further attribute information. Furthermore, in recent years, from the viewpoint of personal information protection, it has become difficult to directly obtain user attribute information that can identify an individual. Therefore, there is a need for a technique that can estimate user attribute information more effectively than conventional techniques.

The present application has been made in view of the above, and includes an information processing device, an information processing method, and an information processing method for estimating user attribute information from the user's behavioral characteristics using detection information detected by a terminal device that moves with the user. The purpose is to provide information processing programs.

The information processing device according to the present application includes an acquisition unit that acquires detection information periodically detected by a terminal device that moves with a user, and an acquisition unit that acquires detection information that is periodically detected by a terminal device that moves with the user, and a a learning unit that performs machine learning based on the learning unit; and an estimation unit that estimates attribute information of the user based on the learning model obtained as a result of machine learning by the learning unit and the detection information acquired by the acquisition unit . The detection information detected by the terminal device is PDR information regarding the indoor position and movement direction of the terminal device detected using PDR technology using a sensor of the terminal device.

According to one aspect of the embodiment, the user's attribute information can be estimated from the user's behavior characteristics using detection information detected by a terminal device that moves with the user.

FIG. 1 is an explanatory diagram showing an overview of an information processing method according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram illustrating a configuration example of a user terminal according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of an information processing device according to an embodiment. FIG. 5 is a diagram illustrating an example of display location information according to the embodiment. FIG. 6 is a diagram illustrating an example of PDR history information according to the embodiment. FIG. 7 is a diagram illustrating an example of estimated attribute information according to the embodiment. FIG. 8 is a flowchart showing the processing procedure according to the embodiment. FIG. 9 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, an information processing apparatus, an information processing method, and a form for implementing an information processing program (hereinafter referred to as an "embodiment") according to the present application will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. In addition, in the following embodiments, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. Overview of information processing method]
First, with reference to FIG. 1, an overview of an information processing method performed by an information processing apparatus according to an embodiment will be described. FIG. 1 is an explanatory diagram showing an overview of an information processing method according to an embodiment. In the following, a case will be described as an example in which the information processing apparatus according to the embodiment estimates the user's demographics (demographic attributes) from the user's behavioral characteristics when shopping in a store. Note that the demographics are just one example of user attribute information. Actually, arbitrary attribute information such as psychographics (psychological attributes) can be estimated.

The user terminal 10 (terminal device) shown in FIG. The indoor position and movement direction of the user terminal 10 are detected using PDR (Pedestrian Dead Reckoning) technology that uses sensors such as sensors, gyro sensors, magnetic sensors, atmospheric pressure sensors, etc.). At this time, if there are multiple floors within the store, the user terminal 10 may add information regarding "altitude" or "floor" to the PDR information. The user terminal 10 also includes a wearable device that is a glasses-shaped or watch-shaped information processing terminal. Note that the user terminal 10 may be linked/integrated with a shopping cart used in a store. For example, the user terminal 10 may acquire information from various sensors and electronic devices mounted on the cart through wired or wireless communication. Further, the user terminal 10 may be mounted on a cart as a touch panel type information display device. Further, the user terminal 10 is not limited to a cart, and may be linked/integrated with a shopping cart or a tray. Further, the user terminal 10 may be lent to the store by the store when the user U enters the store, and returned to the store when the user U pays for the product or leaves the store.

The information processing apparatus 100 shown in FIG. 1 is, for example, a desktop PC (Personal Computer), a server, a mainframe, a workstation, or the like. Further, the information processing device 30 may be one of a plurality of servers that implement distributed computing or cloud computing. The information processing device 100 communicates with one or more user terminals 10, and based on the PDR information regarding the indoor position and movement direction of the user terminal 10, determines the user U's demo based on the user U's behavior characteristics during shopping in the store. Estimate graphics.

As shown in FIG. 1, the user terminal 10 enters the store together with the user U (step S1). When the user terminal 10 enters the store, it notifies the information processing device 100 of store entry information indicating that the user has entered the store (step S2). At this time, the user terminal 10 may notify the information processing device 100 according to the embodiment of the first PDR information of the user terminal 10 at the entrance/exit of the store as the store entry information. Note that the entrance and exit of the store may be different. Furthermore, the store entrance may be read as the departure point, and the store exit may be read as the destination. When the information processing device 100 receives the notification of store entry information from the user terminal 10, it starts collecting PDR information regarding the indoor position and movement direction of the user terminal 10 (step S3). Thereafter, the user terminal 10 tours (moves) within the store together with the user U.

While the user terminal 10 is patrolling the store with the user U, the user terminal 10 acquires PDR information periodically (every 5 seconds, every 10 seconds, every 30 seconds, etc.) (step S4), and each time/predetermined information is acquired. PDR at regular intervals (every 1 minute, every 3 minutes, every 5 minutes, etc.)/When a predetermined number of items (10, 30, 50, etc.) are acquired/At a predetermined timing (such as when turning a corner) The information is notified to the information processing device 100 (step S5). The information processing device 100 stores/accumulates the PDR information notified from the user terminal 10 (step S6), and estimates the demographics of the user U from the PDR information collected up to that point (step S7).

The information processing device 100 according to the embodiment collects PDR information while the user terminal 10 is patrolling the store together with the user U in the store, thereby determining the flow line of the user U in the store and the behavior while moving. can be known, and the demographics of user U can be estimated based on that information.

For example, the information processing device 100 can estimate the age group of the user U based on information regarding the acceleration of PDR information notified from the user terminal 10. Furthermore, if the user U is always moving at an extremely low speed (lower than a predetermined speed), it can be estimated that the user U is an elderly person, a disabled person, a disabled person, or a physically disabled person. On the other hand, if the user U is moving at a relatively high speed (a predetermined speed or higher), it can be estimated that the user U is young or at least healthy.

In addition, in a store where the only means of transportation between the upper and lower floors is stairs, if the user U moves slowly only on the first floor without using the stairs or the upper floors, it may be considered that the user U is an elderly person who has difficulty moving up and down the stairs. It can also be presumed that the person is a physically challenged person, such as a person with a disability, a disabled person, or an injured or sick person. Furthermore, it is possible to estimate whether the person is young or elderly based on the speed of movement (ascending and descending) on the stairs. Further, if the upper floor is a floor that sells products for young people/women, for example, it can be estimated that the user U who moved to the upper floor by stairs is a young person/female. Additionally, if user U is staying in an area where maternity products are sold, it can be assumed that user U is a pregnant woman or has a pregnant woman in her family/relatives/friends/acquaintances. can.

Further, when the user U is moving in a meandering manner, if there are display shelves of products nearby, it can be assumed that the user U is looking around (observing) various products in the store. At this time, it can be estimated that the user U is an elderly person based on the empirical rule that the older the person gets, the more they walk while observing.

Note that the display shelves are an example of store fixtures. Display shelves also include frozen and refrigerated showcases. Further, the display shelf may be, for example, a stand (display stand, sales stand), a wagon, a stall, a cart, etc. placed at a specific position in the store and on which recommended products, special sale products, etc. are placed. Additionally, the product may be hung on a hook or hanger rack. Further, the product may be placed on the floor, placed on a wall or ceiling, or suspended from the ceiling.

In addition, if the user U is always moving in a meandering manner even if there are no product display shelves nearby, the user U may be an elderly person who has difficulty walking straight, a disabled person, an injured or sick person, etc. It can be estimated that At this time, by further collecting information regarding the inclination of the user U's trunk along with the PDR information, it can be estimated that the user U is using a cane.

Furthermore, if user U is always moving with other users, it can be estimated that the other users are family members or close friends of user U. When it is estimated that the user U is an elderly person or the like, it can also be estimated that the other user is a supporter of the user U.

Furthermore, when user U uses a toilet/restroom, it can be determined based on the PDR information whether the toilet/restroom is for men or women. or female. Further, when user U uses a baby rest room (nursing room, diaper changing room, etc.), stroller rental counter, etc., it can be estimated that user U is bringing a baby/infant with him.

Note that demographic estimation cannot be performed until a certain amount of PDR information is collected, so the information processing device 100, for example, until the number of collected PDR information reaches a predetermined number (threshold) or more, Demographic estimation may not be performed.

In addition, although the accuracy of demographic estimation is expected to be low at first, as the number of PDR information is cumulatively accumulated, the accuracy of demographic estimation will gradually improve. is expected.

The information processing device 100 provides information to the user terminal 10 based on the estimated demographic results (step S8). For example, information about the location of products likely to be of interest to user U and the shortest route, the location of rest areas/elevators/escalators/restrooms and their congestion status, the location of the nearest store clerk, the display of a button to call a store clerk, etc. The information is provided to the user terminal 10.

While moving in the store with the user U, the user terminal 10 may stop/decelerate in front of a display shelf where products are displayed, or pass in front of the display shelf at a low speed (below a predetermined speed). When this happens (step S9), it is determined that the purchase of the product has been considered, and the PDR information during that time is notified to the information processing device 100 (step S10). Note that when the user terminal 10 is linked to the cart, it detects that the product has been placed in the cart based on the amount of increase/decrease/change in the mass of the cart's loaded items around the display shelf, and at that point The information processing device 100 may be notified of the PDR information.

The information processing device 100 stores/accumulates the PDR information notified from the user terminal 10 (step S11), and estimates the demographics of the user U from the PDR information collected up to that point (step S12).

For example, if user U is considering purchasing alcoholic beverages, it can be estimated that user U is an adult. Further, if the user U is considering purchasing a product for women/a product for women, it can be estimated that the user U is a woman. Further, if the user U is considering purchasing baby/children's clothes/baby/children's goods, it can be estimated that the user U or his/her relatives/friends/acquaintances have a baby/infant.

In addition, based on the combination of products that user U considered purchasing and the route (flow line) that user U has traveled, the age and age of user U are determined based on a learning model using machine learning and data mining of purchase history information. It is also possible to estimate gender, etc. In addition, by knowing the products that the user U first went to/considered purchasing after entering the store, it is possible to estimate the products that the user U is most interested in and the preferences of the user U. I can do it.

Note that if the PDR information periodically notified from the user terminal 10 does not change for a certain period of time/the amount of change in the PDR information is within the allowable range, the information processing device 100 allows the user U to respond to the PDR information. It can be assumed that the person stopped in front of the display shelf and was considering purchasing the product. Furthermore, if the user terminal 10 repeatedly approaches and stops at a specific display shelf, the information processing device 100 can estimate that the user U is unsure about purchasing the product on that display shelf. . The approach and stop of the user terminal 10 to the display shelf can be known from the PDR information.

The information processing device 100 provides information to the user terminal 10 based on the estimated demographic results (step S13). For example, the user terminal 10 is provided with information regarding a discount coupon for a product that the user U was considering purchasing, point addition and useful information at the time of purchase, display locations of related products, time sale information, and the like.

While the user terminal 10 is walking around the store with the user U, the user terminal 10 and the information processing device 100 repeat the processes of steps S4 to S13 described above.

When the user U finishes visiting the store and pays for the product/leaves the store (step S14), the user terminal 10 sends payment/exit information indicating that the user U has made the payment/left the store. The processing device 100 is notified (step S15). Note that, in reality, the user terminal 10 may notify the information processing device 100 of PDR information acquired in front of the store terminal for payment/at the store entrance/exit as the payment/exit information. When the information processing device 100 receives the payment/exit information notification from the user terminal 10, it ends collecting the PDR information of the user terminal 10 (step S16).

Here, the information processing device 100 controls the user terminal 10 when the PDR information notified from the user terminal 10 indicates outside the store or when the PDR information is not notified from the user terminal 10 for a certain period of time or more. The collection of PDR information may be terminated.

Finally, the information processing device 100 comprehensively estimates the demographics of the user U from all the PDR information collected from the time the user terminal 10 (i.e., the user U) enters the store until payment/exit (step S17). As a result, based on the estimated demographic results, the information processing device 100 determines which products the user U is interested in/which the user U is likely to be interested in, for the user terminal 10 after finishing the payment/leaving the store. Useful information to encourage the next visit to the store, such as product advertisements, discount coupons, and time sale information, is provided (step S18).

Note that the provision of information in steps S8, S13, and S18 described above is not essential. That is, the information processing device 100 does not necessarily have to provide information. In steps S8, S13, and S18 described above, it is optional whether the information processing device 100 provides information or not. Further, the timing at which the information processing device 100 provides information is also arbitrary. For example, regarding the provision of information in steps S8 and S13 above, the information processing device 100 provides information at any timing from when the user terminal 10 (i.e., user U) enters the store until payment/exit. It's okay.

[2. Information processing system configuration]
Next, the configuration of the information processing system 1 including the information processing apparatus 100 according to the embodiment will be described using FIG. 2. FIG. 2 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As illustrated in FIG. 2, the information processing system 1 according to the embodiment includes a user terminal 10 and an information processing device 100. These various devices are connected via a network N so that they can communicate by wire or wirelessly. Furthermore, the number of devices included in the information processing system 1 shown in FIG. 2 is not limited to what is illustrated. For example, the information processing system 1 may include multiple user terminals 10.

The user terminal 10 is an information processing terminal that acquires and stores PDR information of its own device according to user operations and functions that the user terminal 10 has. For example, the user terminal 10 acquires PDR information by using various sensors installed in the user terminal 10. Then, the user terminal 10 transmits the acquired PDR information to the information processing device 100.

As described above, the information processing device 100 acquires PDR information from the user terminal 10, estimates the product that the user U is interested in based on the PDR information and display location information, and selects the product that the user U is interested in based on the estimated product. This is a server device that predicts products that U is likely to be interested in. Note that the information processing device 100 may have a function as a service server that provides various services. For example, the information processing device 100 may have a function as a web server that provides a website related to a service.

[3. User terminal configuration]
Next, the configuration of the user terminal 10 according to the embodiment will be described using FIG. 3. FIG. 3 is a diagram showing a configuration example of the user terminal 10 according to the embodiment. As shown in FIG. 3, the user terminal 10 includes a communication section 11, an input section 12, a display section 13, a detection section 14, a storage section 15, and a control section 16.

(About communication department 11)
The communication unit 11 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the information processing device 100 and the like. The communication unit 11 is realized by, for example, an antenna, a NIC (Network Interface Card), or the like.

(About input section 12 and display section 13)
The input unit 12 is an input device that receives various operations from the user U. For example, the input unit 12 is realized by operation keys etc. provided on the user terminal 10. The display unit 13 is a display device for displaying various information. For example, the display unit 13 is realized by a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Note that when a touch panel is employed in the user terminal 10, a part of the input section 12 and the display section 13 are integrated.

(About the detection unit 14)
The detection unit 14 detects various information regarding the user terminal 10. Specifically, the detection unit 14 detects the user U's operation on the user terminal 10, the location information of the user terminal 10, information regarding devices connected to the user terminal 10, the environment in the user terminal 10, The behavior, state, etc. of the user U who owns the user terminal 10 is detected. In the example shown in FIG. 3, the detection unit 14 includes an operation detection unit 141, a position detection unit 142, an external device detection unit 143, an environment detection unit 144, and a motion detection unit 145.

(About the operation detection unit 141)
The operation detection unit 141 detects user U's operation on the user terminal 10. For example, the operation detection unit 141 detects an operation by the user U based on information input to the input unit 12. That is, the operation detection unit 141 detects that there is an input of an operation of touching the screen on the input unit 12, that there is an input of voice, etc. Further, the operation detection unit 141 may detect that a predetermined application (hereinafter simply referred to as "app") has been activated by the user U. If this application is an application that operates an imaging device within the user terminal 10, the operation detection unit 141 detects that the imaging function is being used by the user U. Further, the operation detection unit 141 may detect an operation in which the user terminal 10 itself is moved based on data detected by an acceleration sensor, a gyro sensor, or the like provided in the user terminal 10.

(About the position detection unit 142)
The position detection unit 142 detects the current position of the user terminal 10. Specifically, the position detection unit 142 detects the indoor position of its own device using PDR technology. For example, the position detection unit 142 uses sensors (acceleration sensor, gyro sensor, magnetic sensor, etc.) of the user terminal 10 to measure the moving direction, amount of movement, and moving distance of the user U holding the user terminal 10. Estimate your current location.

Further, the position detection unit 142 can detect the position using various methods. For example, in addition to the PDR technique, the position detection unit 142 may detect the position using various communication functions of the user terminal 10 as an auxiliary positioning means for position correction and the like.

(Wi-Fi positioning)
For example, the position detection unit 142 detects the position of the user terminal 10 using the Wi-Fi (registered trademark) communication function of the user terminal 10 or the communication network provided by each communication company. Specifically, the position detection unit 142 detects the position of the own device by performing Wi-Fi communication and measuring the distance to nearby base stations and access points.

(Beacon positioning)
Further, the position detection unit 142 may detect the position using the Bluetooth (registered trademark) function of the user terminal 10. For example, the position detection unit 142 detects the position of its own device by connecting to a beacon transmitter connected by a Bluetooth function.

(geomagnetic positioning)
Further, the position detection unit 142 detects the position of the own device based on the geomagnetic pattern of the structure measured in advance and the geomagnetic sensor provided in the own device.

(RFID positioning)
Further, for example, if the user terminal 10 is equipped with an RFID (Radio Frequency Identification) tag function equivalent to a contactless IC card used at station ticket gates, shops, etc., or has a function to read RFID tags. In this case, the location where the payment was made is recorded together with the information that the payment was made by the user terminal 10. The position detection unit 142 may detect the position of the user terminal 10 by acquiring such information. Further, the position may be detected by an optical sensor, an infrared sensor, or the like provided in the user terminal 10.

(GPS positioning)
Further, the position detection unit 142 receives radio waves sent from a GPS (Global Positioning System) satellite, and detects a position (for example, latitude and longitude) indicating the current position of the user terminal 10 based on the received radio waves. Good too. However, GPS is not suitable for indoor position detection because the position detection accuracy decreases when the user terminal 10 is inside a building. Therefore, when using GPS, it is assumed that it will be used for supplementary purposes or outdoors.

The position detection unit 142 detects the position of its own device using PDR technology and, if necessary, one or a combination of the above-mentioned auxiliary positioning means. Then, the acquisition unit 161, which will be described later, acquires the position information of the user terminal 10 based on the information of the position detected by the position detection unit 142 and the time of detection.

(About external device detection unit 143)
The external device detection unit 143 detects an external device connected to the user terminal 10. For example, the external device detection unit 143 detects an external device based on exchange of communication packets with the external device. The external device detection unit 143 then recognizes the detected external device as a terminal connected to the user terminal 10. Further, the external device detection unit 143 may detect the type of connection with the external device. For example, the external device detection unit 143 detects whether the external device is connected by wire or wireless communication. Further, the external device detection unit 143 may detect a communication method used in wireless communication. Further, the external device detection unit 143 may detect an external device based on information acquired by a radio wave sensor that detects radio waves emitted by the external device, an electromagnetic wave sensor that detects electromagnetic waves, or the like.

(About the environment detection unit 144)
The environment detection unit 144 detects the environment in the user terminal 10. The environment detection unit 144 uses various sensors and functions provided in the user terminal 10 to detect information regarding the environment. For example, the environment detection unit 144 may include a microphone that collects sounds around the user terminal 10, an illuminance sensor that detects the illuminance around the user terminal 10, an acceleration sensor (or , a gyro sensor, etc.), a humidity sensor that detects the humidity around the user terminal 10, a geomagnetic sensor that detects the magnetic field at the location of the user terminal 10, and the like. The environment detection unit 144 detects various information using various sensors. For example, the environment detection unit 144 detects the noise level around the user terminal 10 and whether the illuminance around the user terminal 10 is suitable for imaging. Furthermore, the environment detection unit 144 may detect surrounding environment information based on photos and videos taken with a camera.

(About motion detection unit 145)
The motion detection unit 145 detects the motion and state of the user U who owns the user terminal 10, using a motion sensor or the like, for example. Motion sensors include acceleration sensors, gyro sensors, step sensors, biological sensors, and the like. The acceleration sensor is a sensor that detects the acceleration of the user terminal 10. The gyro sensor is a sensor that detects the attitude, angular velocity, etc. of the user terminal 10. The step count sensor is a sensor that counts the number of steps walked by the user U of the user terminal 10. The biosensor is a sensor that detects the heart rate, body temperature, etc. of the user U of the user terminal 10.

(About storage unit 15)
The storage unit 15 stores various information. The storage unit 15 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. For example, the storage unit 15 stores various information detected by the detection unit 14 in association with the date and time of detection. Specifically, the storage unit 15 stores PDR information based on various information detected by the detection unit 14. Furthermore, the storage unit 15 stores information regarding applications installed on the user terminal 10.

(About the control unit 16)
The control unit 16 is, for example, a controller, and various programs stored in a storage device inside the user terminal 10 use RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc. This is achieved through execution. Further, the control unit 16 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The control unit 16 controls a process of providing PDR information of the user terminal 10 to the information processing apparatus 100. For example, the control unit 16 executes and controls a program (app) for realizing the process of providing PDR information of the user terminal 10. The program may be downloaded to the user terminal 10 and executed by accessing the information processing device 100, or the program may be downloaded to the user terminal 10 and executed by the server device (information processing device 100 or providing various programs) according to an operation by the user U who has the user terminal 10. It may be downloaded from an external server) and installed on the user terminal 10.

As shown in FIG. 3, the control unit 16 includes an acquisition unit 161, a reception unit 162, and a transmission unit 163, and realizes or executes information processing functions and operations described below. For example, the control unit 16 executes the above-mentioned program using the RAM as a work area, thereby realizing the information processing functions and operations described below. Note that the internal configuration of the control unit 16 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it performs information processing to be described later. Further, the connection relationship between the respective processing units included in the control unit 16 is not limited to the connection relationship shown in FIG. 3, and may be other connection relationships.

(About the acquisition unit 161)
The acquisition unit 161 acquires various information. For example, the acquisition unit 161 acquires various information detected by the detection unit 14 by controlling the detection unit 14 . For example, the acquisition unit 161 acquires position information of the user terminal 10 based on information detected by the position detection unit 142. Note that the acquisition unit 161 acquires information regarding the context of the user terminal 10, including not only location information but also various sensor information such as information regarding the environment around the user terminal 10. The acquisition unit 161 acquires PDR information based on various information detected by the detection unit 14.

The acquisition unit 161 may acquire PDR information at predetermined time intervals. For example, the acquisition unit 161 periodically (every 10 seconds, every 30 seconds, every minute, etc.) acquires PDR information by controlling the detection unit 14 described above. Note that the timing at which the acquisition unit 161 acquires the PDR information may be set by the information processing apparatus 100.

(Regarding the receiving section 162)
The receiving unit 162 receives various information. For example, the receiving unit 162 receives provided information transmitted from the information processing device 100. The control unit 16 displays the provided information received by the receiving unit 162 on the display unit 13 or stores it in the storage unit 15.

(About the transmitter 163)
The transmitter 163 transmits various information. Specifically, the transmitter 163 transmits PDR information to the information processing device 100. For example, the transmitter 163 transmits identification information for identifying the user terminal 10, identification information for identifying the user U, PDR information acquired by the acquisition unit 161, and information indicating the acquisition date and time of the PDR information. are associated with each other and transmitted to the information processing apparatus 100.

[4. Configuration of information processing device]
Next, the configuration of the information processing device 100 according to the embodiment will be described using FIG. 4. FIG. 4 is a diagram illustrating a configuration example of the information processing device 100 according to the embodiment. As shown in FIG. 4, the information processing device 100 includes a communication section 110, a storage section 120, and a control section 130. Note that the information processing device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that accepts various operations from an administrator using the information processing device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. ).

(About communication department 110)
The communication unit 110 is realized by, for example, a NIC or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 10 and the like via the network N.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes display location information 121, PDR history information 122, estimated attribute information 123, provision information 124, and a learning model 125.

(About display location information 121)
The display location information 121 is information in which identification information of a product displayed on a display shelf in a store is associated with a display location where the product is displayed. Note that the display location information 121 may include identification information of all products in the store and their display locations, or may include identification information of specific products (time sale products, advertised products, etc.) in the store. It may include only information and its display location. The display location information 121 may be prepared individually for each store, or may be centrally managed for all target stores by identifying them by store ID.

Here, FIG. 5 shows an example of the display location information 121 according to the embodiment. FIG. 5 is a diagram showing an example of display location information 121 according to the embodiment. In the example shown in FIG. 5, the display location information 121 includes items such as "product ID," "store ID," and "display location." Furthermore, the item "display location" has sub-items such as "position", "direction", and "various sensor information".

"Product ID" indicates identification information for identifying a product displayed on a display shelf in a store. For example, the product ID is a product name, product identification code, etc. The product ID may be any identification information that allows the information processing device 100 to identify the product. "Store ID" indicates identification information that identifies the store where the display shelf where the product is displayed is located. Since display shelves and product placement differ from store to store, it is preferable to identify the store. Note that if the display location information 121 is prepared separately for each store or if the information processing device 100 is a store device used only in a specific store, the "store ID" may be omitted. good. For example, you can delete the "Store ID" field itself, or you can respond by entering blank (not entered)/No Data (N/D)/dummy data for the "Store ID" field. You may.

The "display location" indicates the location of the display shelves and products in the store. For example, "position" indicates the position of a product displayed on a display shelf in a store. "Direction" indicates the direction of products displayed on display shelves in the store. "Various sensor information" indicates information detected by various sensors around products displayed on display shelves in a store.

In this embodiment, the "display location" indicates information corresponding to PDR information regarding the displayed product. Therefore, the "position", "direction", and "various sensor information" included in the "display location" item correspond to the PDR information notified from the user terminal 10. Specifically, the "position" indicates the position where the user U views or picks up a product displayed on a display shelf in the store. "Direction" indicates the direction in which the user U views or picks up the products displayed on the display shelves in the store. That is, the "direction" indicates the direction in which the product exists when viewed from the "position" of the user U. "Various sensor information" indicates information detected by various sensors when the user U views or picks up a product displayed on a display shelf in a store.

In other words, in FIG. 5, as an example of data stored in the display location information 121, a product with product ID "C1" is stored in a store with store ID "L1" at position "P5", orientation "A5", and various sensor information. It shows that it is displayed at the display location "X5".

(About PDR history information 122)
The PDR history information 122 stores PDR information notified from the user terminal 10. Here, FIG. 6 shows an example of the PDR history information 122 according to the embodiment. FIG. 6 is a diagram illustrating an example of PDR history information 122 according to the embodiment. In the example shown in FIG. 6, the PDR history information 122 includes items such as "terminal ID", "user ID", "store ID", and "PDR information". Furthermore, the "PDR information" item has sub-items such as "date and time of acquisition", "position", "azimuth", and "various sensor information".

“Terminal ID” indicates identification information that identifies the user terminal 10 used by the user U. “User ID” indicates identification information that identifies user U. Note that when the user terminal 10 and the user U have a one-to-one relationship, the same/common identification information may be used for the "terminal ID" and the "user ID." In this case, the "terminal ID" and the "user ID" may be combined.

Furthermore, each user U may own multiple user terminals 10. In this case, the information processing device 100 uses identification information that uniquely identifies the user U to associate the PDR information notified from the plurality of user terminals 10 with the user U. Note that the identification information of the user U is, for example, a service ID (user account) given to each user U in a service provided by the information processing device 100. Such an ID may be issued not only by the information processing device 100 but also by a business partnered with the information processing device 100. As a result, even if one user U is using multiple user terminals 10 or logging into a service in different environments, the information processing device 100 can uniquely identify the user U and retrieve PDR information. can be obtained. Further, the information processing device 100 may use cookie information when using a service, a terminal ID unique to the terminal, etc. as the user U's identification information.

“Store ID” indicates identification information that identifies the store that user U visited. Note that the store ID may be specified when the user U enters the store, or may be specified when the first PDR information is notified from the user terminal 10. For example, the user terminal 10 notifies the information processing device 100 of GPS information and the like, and the information processing device 100 identifies the store based on the GPS information and determines the store ID. If the user terminal 10 can recognize the store ID, the user terminal 10 may notify the information processing device 100 of the store ID. Note that if there is no need to identify the store, the "store ID" may be omitted.

“Acquisition date and time” indicates the date and time when the PDR information was detected (acquired) by the user terminal 10. The acquisition date and time is notified from the user terminal 10 along with the PDR information. “Position” indicates the specific location of the user terminal 10. “Direction” indicates a specific direction of the user terminal 10. In FIG. 6, the position is expressed as "P1" and the direction as "A1", but in reality, the position item contains specific information indicating the indoor position of the user terminal 10 (for example, the coordinate system etc.) are stored. Further, the location item may include information regarding a floor within the store. In the azimuth item, specific information indicating the moving azimuth of the user terminal 10 (for example, a numerical value of the azimuth, information indicating the direction, etc.) is stored.

"Various sensor information" indicates information detected by various sensors when the position is detected. In FIG. 6, various sensor information is expressed using concepts such as "X1," but in reality, various sensor information items include the acceleration and tilt of the user terminal 10, geomagnetism, temperature and atmospheric pressure, and user U's product Specific information acquired by various sensors is stored, such as the amount of change in the mass of items written on the cart when the item is placed in the cart.

That is, in FIG. 6, the user U with the user ID "U1" changes the PDR information position from "P1" to "P4" at the store with the store ID "L1" between the acquisition date and time "T1" and "T4". ”, the orientation remains unchanged at “A1”, and the various sensor information remains at “X1”, indicating that the user terminal 10 is moving straight ahead in the same direction as the user U during this time. . Further, the information processing device 100 can also estimate the moving speed of the user U based on the acquisition date and time and the position of the PDR information.

In addition, in FIG. 6, the user U with the user ID "U1" has the PDR information at the store with the store ID "L1" with the location "P5" and the direction " A5'' and various sensor information remain unchanged as "X5," indicating that the user terminal 10 is stopped together with the user U during this time.

Furthermore, in FIG. 6, since the PDR information while the user terminal 10 is stopped together with the user U is the position "P5", the direction "A5", and the various sensor information "X5", among the display location information 121, It is shown that the user is considering purchasing product ID "C1" corresponding to this PDR information.

(About estimated attribute information 123)
Estimated attribute information 123 stores user demographics estimated based on the PDR information stored in PDR history information 122. Here, FIG. 7 shows an example of the estimated attribute information 123 according to the embodiment. FIG. 7 is a diagram illustrating an example of estimated attribute information 123 according to the embodiment. In the example shown in FIG. 7, the estimated attribute information 123 includes items such as "terminal ID", "user ID", "movement status", "considered product", and "demographic".

The “terminal ID” and “user ID” are the same as those in the PDR history information 122. That is, the "terminal ID" indicates identification information that identifies the user terminal 10 used by the user U. “User ID” indicates identification information that identifies user U.

“Moving state” stores information indicating the moving state of the user U estimated based on the PDR information stored in the PDR history information 122. In FIG. 7, the movement state is expressed as a concept such as "W1", but in reality, the movement state of the user U (walking/running/stairs up/stairs down/stopped, etc.) is included in the movement state item. The specific information indicated is stored. Further, in the movement state item, information indicating movement speed, acceleration, and movement pattern (straight, meandering, staggered, etc.) may be stored. For example, as shown in FIG. 6, based on the PDR information stored in the PDR history information 122, the user U with the user ID "U1" visits the store with the store ID "L1" at the acquisition date and time "T1" to " If it is estimated that the user terminal 10 is slowly moving straight ahead in the same direction as the user U until "T4", the moving state such as "walking", "going straight", and "direction" is included in the moving state item. Along with the information indicating the , information indicating the moving speed, acceleration, etc. is stored as necessary.

“Product under consideration” stores identification information (product ID) for identifying a product estimated based on the PDR information stored in the PDR history information 122. Note that the product to be considered is not limited to one, but includes all products estimated based on the PDR information stored in the PDR history information 122.

That is, in FIG. 7, based on the PDR information stored in the PDR history information 122, it is assumed that the user U with the user ID "U1" is considering purchasing the product at the store with the store ID "L1". C1'' is stored in the item of product under consideration. Specifically, the information processing device 100 uses the “position”, “direction”, and “various sensor information” stored in the display location information 121 and the “position”, “direction”, and “various sensor information” stored in the PDR history information 122. When the "various sensor information" are compared, and if they match each other or the error is within the allowable range, the user U has considered purchasing based on the "position", "azimuth", and "direction" stored in the display location information 121. It is estimated that the product is identified by the "product ID" corresponding to "various sensor information".

"Demographics" stores information indicating the demographics of the user U estimated based on the above-mentioned movement status and products under consideration. In Figure 7, demographics are expressed using concepts such as "Y1," but in reality, demographic items include various specific information such as user U's age, gender, occupation, annual income, and place of residence. Remember information. That is, in FIG. 7, the demographic "Y1" of the user U estimated based on the movement state "W1" and the product under consideration "C1" is stored.

Although not shown in FIG. 7, the PDR history information 122 stores interest information of user U, action history information of user U, etc. based on user U's purchase history, action history, etc. You can leave it there. For example, the interest information is information set for the user U by the information processing device 100 based on past purchase history (categories and interests in which the user U is assumed to be interested based on the purchase history of the user U). content of information, etc.). The behavior history information is the behavior history of the user U in the store (in-store movement history, product purchase history, etc.).

(About provided information 124)
The provided information 124 is information in which information indicating the demographics of the user U is associated with information provided in relation to the demographics. Further, the provided information 124 may include information in which identification information for identifying a product is associated with information provided regarding the product. For example, the information processing apparatus 100 selects the corresponding provided information based on the values of the "demographic" and "considered product" items of the estimated attribute information 123 shown in FIG. 7, and notifies the user terminal 10 of the selected information.

(About learning model 125)
The learning model 125 is a learning model used to estimate the demographics of the user U from the behavioral characteristics of the user U during shopping in the store. For example, the information processing device 100 estimates the demographics of the user U based on the learning model 125 and the movement state and the product under consideration stored in the estimated attribute information 123 shown in FIG. Based on the learning model 125, the information processing device 100 also calculates the movement status and the product under consideration stored in the estimated attribute information 123 shown in FIG. 7 from the PDR information stored in the PDR history information 122 shown in FIG. may be estimated.

(About the control unit 130)
The control unit 130 is, for example, a controller, and various programs (corresponding to an example of an estimation program) stored in a storage device inside the information processing device 100 are executed by the CPU, MPU, etc. using the RAM as a work area. This is realized by Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC or an FPGA.

As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, an estimation unit 132, a provision unit 133, and a learning unit 134, and realizes or executes information processing functions and operations described below. . Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be any other configuration as long as it performs information processing to be described later. Further, the connection relationship between the respective processing units included in the control unit 130 is not limited to the connection relationship shown in FIG. 4, and may be other connection relationships.

(About the acquisition unit 131)
The acquisition unit 131 acquires PDR information notified from the user terminal 10 via the communication unit 110. Further, the acquisition unit 131 registers and accumulates the acquired PDR information in the PDR history information 122. For example, while the user terminal 10 is patrolling the store with the user U, the acquisition unit 131 acquires PDR information notified from the user terminal 10 and stores it in the PDR history information 122.

(About the estimation unit 132)
The estimation unit 132 estimates the movement state of the user U based on the PDR information notified from the user terminal 10. Furthermore, the estimating unit 132 estimates the product that the user U has considered purchasing based on the PDR information and the display location information 121 notified from the user terminal 10.

Note that when using the PDR information notified from the user terminal 10, the estimation unit 132 may receive the PDR information output from the acquisition unit 131, or read out the PDR information stored in the PDR history information 122. It's okay.

In the PDR history information 122 shown in FIG. 6, the user U with the user ID "U1" was at the store with the store ID "L1" and the PDR information position was "P1" between the acquisition date and time "T1" and "T4". ” to “P4” and the various sensor information changes from “X1” to “X4”, but the orientation remains unchanged at “A1”, so the estimation unit 132 estimates that the user terminal It is estimated that 10 is moving straight in the same direction as user U, and this is stored in the movement state item of the estimated attribute information 123.

Furthermore, in the PDR history information 122 shown in FIG. Since "P5", the orientation "A5", and the various sensor information "X5" remain unchanged, the estimation unit 132 estimates that the user terminal 10 is stopped together with the user U during this time.

In addition, in the PDR history information 122 shown in FIG. 6, since the PDR information while the user terminal 10 is stopped together with the user U is the position "P5", the direction "A5", and the various sensor information "X5", the display Of the location information 121, it is estimated that the user is considering purchasing the product ID "C1" corresponding to this PDR information, and this is stored in the item of product under consideration in the estimated attribute information 123.

Further, the estimating unit 132 estimates the demographics of the user U based on the learning model 125 and the movement state and considered product of the estimated attribute information 123.

(About the provision section 133)
The providing unit 133 provides information to the user terminal 10 based on the result estimated by the estimating unit 132. For example, the information processing device 100 selects the corresponding provided information based on the values of the “demographic” and “considered product” items of the estimated attribute information 123 and notifies the user terminal 10 of the information processing device 100 .

(About learning section 134)
The learning unit 134 performs machine learning based on the PDR information stored in the PDR history information 122 and reflects it in the learning model 125. For example, when the user terminal 10 completes a tour of the store together with the user U and pays for products/leaves the store (exits), the learning unit 134 stores the PDR history information 122 between entering the store and leaving the store. Machine learning is performed based on the PDR information stored in .

Specifically, the learning unit 134 performs supervised machine learning based on the PDR information stored in the PDR history information 122 and reflects it in the learning model 125. For example, when performing supervised machine learning from information about acceleration in PDR information, supervised learning attaches correct labels to learning data, so this Labels such as ``elderly'' or ``male'' are given and the child learns.

Further, the learning unit 134 may perform machine learning not only for each individual user U but also based on PDR information of a plurality of users U to which the same label is attached, and may reflect the result in the learning model 125.

The machine learning performed by the learning unit 134 may be, for example, deep learning using a deep neural network. Further, the learning unit 134 may utilize data mining or other machine learning algorithms.

[5. Processing procedure]
Next, the procedure of processing by the information processing apparatus 100 according to the embodiment will be described using FIG. 8. FIG. 8 is a flowchart showing the processing procedure according to the embodiment.

As shown in FIG. 8, the control unit 130, based on the GPS information notified from the user terminal 10, usage start information by user U's application operation, or detection information of the user terminal 10 notified from the store, etc. It is detected that the user U moving with the user terminal 10 has entered the store (step S101).

The acquisition unit 131 collects PDR information that is periodically acquired from the user terminal 10 while the user terminal 10 is patrolling the store together with the user U, from the user terminal 10 via the communication unit 110, and stores the PDR information in the PDR history information 122. is stored (step S102).

The estimation unit 132 determines whether the user terminal 10 is moving with the user U based on the PDR information (step S103). For example, the estimation unit 132 determines that the user U is moving when the moving speed/acceleration of the user U continues to be constant. Furthermore, the estimation unit 132 determines that the user U is not moving if the user U has stopped even though there is no obstacle in the moving direction of the user U, or if the user U's moving speed/acceleration has decreased extremely. do.

If the estimation unit 132 determines that the user terminal 10 is moving with the user U (step S103; Yes), the estimation unit 132 estimates the movement state of the user U based on the PDR information during movement, and estimates the estimated attribute information. 123, the movement state of user U is stored in step S104.

Then, the estimating unit 132 estimates the demographics of the user U based on the movement state and estimated products of the user U registered in the estimated attribute information 123 and the learning model 125, and adds the estimated attribute information 123 to the user U's demographics. Demographics are stored (step S105).

Note that if the demographics of the user U are already stored in the estimated attribute information 123, the estimation unit 132 updates the demographics of the user U. That is, user U's demographics are cumulatively updated as PDR information increases, and accuracy improves.

The providing unit 133 notifies the user terminal 10 of information useful for the user U who is on the move, based on the demographics of the user U and the provided information 124 (step S106).

Furthermore, if the estimation unit 132 determines that the user terminal 10 is not moving with the user U (step S103; No), the estimation unit 132 determines that the user U is considering purchasing the product, and displays the PDR information and display information. Based on the location information 121, the product corresponding to the PDR information is estimated, and the estimated product is stored in the estimated attribute information 123 (step S107).

Then, the estimating unit 132 estimates the demographics of the user U based on the movement state and estimated products of the user U registered in the estimated attribute information 123 and the learning model 125, and adds the estimated attribute information 123 to the user U's demographics. Demographics are stored (step S108).

The providing unit 133 notifies the user terminal 10 of information related to the estimated product (product that the user U is considering purchasing) based on the demographics of the user U and the provided information 124 (step S109).

The control unit 130 allows the user U traveling with the user terminal 10 to complete the purchase of the product based on information indicating that the user U has paid for the product/left the store (exited the store), etc. notified from the user terminal 10. It is determined whether or not this has been done (step S110). For example, the control unit 130 may receive PDR information indicating that the user is in front of a store terminal for payment/at the entrance of the store notified by the user terminal 10, GPS position information indicating that the user is outside the store, and user U's application operation. It is determined whether the user U who is moving together with the user terminal 10 has completed the purchase of the product, based on the end-of-use information from the store or the product purchase information of the user U notified from the store. If the control unit 130 determines that the user U has not completed the purchase of the product (step S110; No), the control unit 130 waits until new PDR information is notified from the user terminal 10 (proceeds to step S102). . When the control unit 130 determines that the user U has completed the purchase of the product (step S110; Yes), the control unit 130 moves to final processing (step S111).

The estimation unit 132 estimates the overall shopping behavior of the user U (movement status and products under consideration) based on all the PDR information from entering the store to leaving the store, and adds the estimated attribute information 123 to the estimated attribute information 123. The condition and the product under consideration are stored (step S111).

The estimation unit 132 comprehensively estimates the demographics of the user U based on the user U's movement state and estimated products registered in the estimated attribute information 123 and the learning model 125, and The demographics of user U are stored in (step S112). For example, the user's age, gender, and physical condition are estimated from the context (context, situation, etc.) of the user's behavior, such as the user's movement status and product consideration time during product purchasing behavior in a store, and the product that the user is interested in. can do.

The providing unit 133 provides useful information to the user U to encourage the user to visit the store from next time onwards, based on the demographics of the user U and the provided information 124 (step S113).

The learning unit 134 finally performs machine learning based on all the PDR information stored in the PDR history information 122, and updates the learning model 125 (step S114). Thereafter, the processing procedure according to the above embodiment is ended.

[6. Modified example]
The user terminal 10 and information processing device 100 described above may be implemented in various different forms other than the above embodiments. Therefore, a modification of the embodiment will be described below.

In the above embodiment, the PDR information is generated on the user terminal 10 side, but in reality, the user terminal 10 processes the detection information (sensor information) detected by various sensors installed on the user terminal 10 side. The PDR information may be transmitted to the device 100 and generated on the information processing device 100 side. That is, in the above embodiment, the PDR information transmitted from the user terminal 10 to the information processing apparatus 100 may be detection information of various sensors used to generate PDR information on the information processing apparatus 100 side.

Further, the PDR information may be relative information based on a predetermined position. For example, rather than absolute information such as in front of this shelf on the 2nd floor of a building, information such as how many meters away from the building entrance it is located up, down, left and right, or how many degrees of inclination it is facing from the direction of the building entrance may be used. .

In addition, although the above embodiment is explained using products as an example, in reality, it is possible to target not only products but also books, magazines, materials, etc. stored on the shelves of a library/library room. be. For example, the user terminal 10 notifies the information processing device 100 of PDR information while walking around the library/library room with the user U.

Furthermore, it is possible to target not only display shelves and products but also services and the like. For example, the product in the embodiment may be a service provided within a store. By combining products and services, it is also possible to provide information on services related to products.

Further, while the user terminal 10 is touring the premises of an indoor theme park/amusement facility or the like with the user U, the user terminal 10 may notify the information processing device 100 of the PDR information. In this case, the display shelves and products in the embodiment can be read as on-site attractions/shops, etc. Further, the user terminal 10 may notify the information processing device 100 of PDR information while the user terminal 10 is touring inside a building such as a museum/art gallery/science museum/aquarium together with the user U. In this case, the display shelves and products in the embodiment can be read as exhibits in the building.

In addition, while the user terminal 10 is patrolling buildings such as government offices, post offices, financial institutions (banks, credit unions, insurance companies, securities companies, etc.) with the user U, the user terminal 10 collects PDR information. The processing device 100 may also be notified. In this case, the display shelves and products in the embodiment can be read as a service counter/automatic issuing machine/automatic teller machine (ATM), etc. in the building.

Further, the user terminal 10 may notify the information processing device 100 of the PDR information while the user terminal 10 is patrolling the station premises together with the user U. In this case, the display shelves and products in the embodiment include station platforms, commercial facilities (shops, restaurants, etc.), ticket vending machines, information desks, toilets, stairs, lifting devices (elevators, escalators, etc.), moving walkways, coin lockers, etc. It can be read as The station premises may be inside or outside the ticket gate. Furthermore, if the station is integrated with a nearby commercial facility and the user U can move between the station and the nearby commercial facility without going outside, the nearby commercial facility may be included.

In addition, while the user terminal 10 is touring around buildings such as school facilities, medical institutions, welfare facilities, accommodation facilities, public baths (bathing facilities, hot spring facilities, etc.), theaters, movie theaters, etc., the user The terminal 10 may notify the information processing device 100 of PDR information. In this case, the display shelves and products in the embodiment can be read as equipment in the building/reception counter/room/store/dining room, etc.

Moreover, it is possible to target not only display shelves in stores but also tenants of shopping centers (shopping malls). For example, the user terminal 10 may notify the information processing apparatus 100 of PDR information while the user terminal 10 is touring the premises of the shopping center with the user U. In this case, the shopping center corresponds to the "store" in the embodiment, and the tenant corresponds to the "display shelf". Note that the same applies to arcade shopping streets and underground malls as described above for shopping centers.

[7. Hardware configuration]
The information processing apparatus 100 and the user terminal 10 according to the embodiments described above are realized, for example, by a computer 1000 having a configuration as shown in FIG. The information processing device 100 will be described below as an example. FIG. 9 is a hardware configuration diagram showing an example of a computer 1000 that implements the functions of the information processing device 100 and the user terminal 10. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F). ) has 1700.

CPU 1100 operates based on a program stored in ROM 1300 or HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, programs depending on the hardware of the computer 1000, and the like.

HDD 1400 stores programs executed by CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via communication network 500 (corresponding to network N shown in FIG. 2), sends it to CPU 1100, and sends data generated by CPU 1100 to other devices via communication network Send to device.

The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via an input/output interface 1600. CPU 1100 obtains data from an input device via input/output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input/output interface 1600.

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads this program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the information processing device 100 or the user terminal 10 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the RAM 1200. Furthermore, data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the communication network 500.

Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Furthermore, the above-mentioned components include those that can be easily assumed by those skilled in the art, those that are substantially the same, and those that are in a so-called equivalent range. Furthermore, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the constituent elements can be made without departing from the gist of the embodiments described above.

[8. others〕
Further, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or the processes described as being performed manually can be performed manually. All or part of this can also be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

Furthermore, the embodiments and modifications described above can be combined as appropriate within a range that does not conflict with the processing contents.

[9. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes the acquisition section 131 and the estimation section 132. The acquisition unit 131 acquires detection information periodically detected by the user terminal 10 that moves with the user U. The estimation unit 132 estimates the attribute information of the user U based on the detection information acquired by the acquisition unit 131. Thereby, attribute information such as user demographics can be estimated from the user's behavior characteristics using detection information detected by a user terminal that moves with the user.

Furthermore, the estimation unit 132 estimates the movement state of the user U based on the detection information acquired by the acquisition unit 131, and estimates the attribute information of the user U based on the movement state of the user U. Thereby, attribute information such as user demographics can be estimated from the user's movement state.

Furthermore, when the user U approaches or stays at a specific location, the estimation unit 132 estimates the object corresponding to the detection information acquired by the acquisition unit 131, and estimates the attribute information of the user U based on the object. . Thereby, attribute information such as demographics of the user can be estimated from the product that the user has considered purchasing.

Furthermore, the estimation unit 132 uses object placement location information (display location information 121) indicating the object placed at the location corresponding to the detection information acquired by the acquisition unit 131 and the detection information acquired by the acquisition unit 131. The target object corresponding to the detection information acquired by the acquisition unit 131 is estimated based on the comparison result. Thereby, based on the product display location information 121, it is possible to estimate the product displayed at the location corresponding to the detection information acquired by the acquisition unit 131.

Furthermore, the estimation unit 132 estimates the attribute information of the user U based on both the movement state of the user U and the target object. Thereby, attribute information such as demographics of the user can be estimated with higher accuracy based on both the movement state of the user U and the products that the user has considered purchasing.

Further, the information processing device 100 according to the embodiment further includes a providing unit 133. The providing unit 133 notifies the user terminal 10 of at least one of information to be provided to the user U who is moving and information related to the object, based on the attribute information of the user U estimated by the estimating unit 132. As a result, depending on attribute information such as user demographics, useful information can be notified to users U who are on the move, and information related to products can be notified to users U who are considering purchasing a product. can do. Further, different information can be provided depending on attribute information such as user demographics.

When the user U reaches the destination and completes the movement, the estimation unit 132 estimates the attribute information of the user U based on the detection information acquired by the acquisition unit 131 between the start of the movement and the completion of the movement of the user U. do. The providing unit 133 notifies the user terminal 10 of the provided information based on the attribute information of the user U estimated by the estimating unit 132. Thereby, the attribute information of the user U can be comprehensively estimated based on all the detection information acquired from the start of the movement of the user U to the completion of the movement. Then, based on the results, it is possible to inform the user U after completing the movement of information to be provided according to attribute information such as the user's demographics so as to encourage the user to take the next action.

The information processing device 100 according to the embodiment further includes a learning unit 134 that performs machine learning based on the detection information acquired by the acquisition unit 131 from the start of the movement of the user U to the end of the movement. The estimation unit 132 estimates the attribute information of the user U based on the learning model obtained as a result of machine learning by the learning unit 134 and the detection information acquired by the acquisition unit 131. This makes it possible to repeat machine learning and improve the accuracy of estimating attribute information such as user demographics.

The learning unit 134 performs supervised learning of machine learning from information related to acceleration among the detection information acquired by the acquisition unit. Thereby, the age group, gender, physical condition, etc. of the user U can be estimated with higher accuracy based on the learning model.

The detection information detected by the user terminal 10 is indoor position information based on pedestrian autonomous navigation. That is, the detection information detected by the user terminal 10 may be PDR information. Note that the user terminal 10 does not need to recognize that the information being transmitted from its own device to the information processing device 100 side is PDR information. The user terminal 10 only needs to transmit information that can be recognized as PDR information on the information processing device 100 side or information that is used to generate PDR information on the information processing device 100 side.

As mentioned above, the embodiments of the present application have been described in detail based on several drawings, but these are merely examples, and various modifications and variations can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to carry out the invention in other forms with modifications.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Information processing system 10 User terminal 100 Information processing device 11, 110 Communication unit 12 Input unit 13 Display unit 14 Detection unit 15, 120 Storage unit 121 Display location information 122 PDR history information 123 Estimated attribute information 124 Provided information 125 Learning model 16, 130 control unit 131 acquisition unit 132 estimation unit 133 provision unit 134 learning unit

Claims (11)

an acquisition unit that acquires detection information periodically detected by a terminal device that moves with the user;
a learning unit that performs machine learning based on the detection information acquired by the acquisition unit between the start of the user's movement and the end of the movement;
an estimation unit that estimates attribute information of the user based on a learning model obtained as a result of machine learning by the learning unit and detection information acquired by the acquisition unit;
An information processing device characterized in that the detection information detected by the terminal device is PDR information regarding the indoor position and movement direction of the terminal device detected using PDR technology using a sensor of the terminal device. 2. The estimation unit estimates the movement state of the user based on the detection information acquired by the acquisition unit, and estimates the attribute information of the user based on the movement state of the user. The information processing device described. When the user approaches or stays at a specific location, the estimation unit estimates an object corresponding to the detection information acquired by the acquisition unit, and estimates attribute information of the user based on the object,
The information processing device according to claim 2, wherein the target object is a product displayed at a location corresponding to the detection information acquired by the acquisition unit. The estimation unit compares object placement location information indicating a target placed at a location corresponding to the detection information acquired by the acquisition unit with the detection information acquired by the acquisition unit, and based on the comparison result, The information processing device according to claim 3, wherein the information processing device estimates a target object corresponding to the detection information acquired by the acquisition unit. The information processing apparatus according to claim 3 or 4, wherein the estimating unit estimates the user's attribute information based on both the user's movement state and the target object. The provision unit further includes a provision unit that notifies the terminal device of at least one of information provided to the user who is moving and information related to the object based on the attribute information of the user estimated by the estimation unit. The information processing device according to any one of claims 3 to 5. The estimating unit estimates attribute information of the user based on the detection information acquired by the acquiring unit between the start of the user's movement and the completion of the movement, when the user reaches the destination and completes the movement. The information processing device according to any one of claims 1 to 6, characterized in that: The information processing device according to any one of claims 1 to 7, wherein the learning unit performs supervised learning of machine learning from information related to acceleration among the detection information acquired by the acquisition unit. The information processing device according to any one of claims 1 to 8 , wherein the detection information detected by the terminal device is indoor position information based on pedestrian autonomous navigation. An information processing method performed by a computer, the method comprising:
an acquisition step of acquiring detection information periodically detected by a terminal device that moves with the user;
a learning step of performing machine learning based on the detection information acquired by the acquisition step between the start of the user's movement and the end of the movement;
an estimation step of estimating attribute information of the user based on a learning model obtained as a result of machine learning in the learning step and the detection information obtained in the acquisition step;
An information processing method characterized in that the detection information detected by the terminal device is PDR information regarding the indoor position and movement direction of the terminal device detected using PDR technology using a sensor of the terminal device. an acquisition procedure for acquiring detection information periodically detected by a terminal device that moves with the user;
a learning procedure for performing machine learning based on the detection information acquired by the acquisition procedure between the start of the user's movement and the end of the movement;
causing a computer to execute an estimation procedure for estimating attribute information of the user based on a learning model obtained as a result of machine learning by the learning procedure and the detection information obtained in the acquisition procedure;
An information processing program characterized in that the detection information detected by the terminal device is PDR information regarding the indoor position and movement direction of the terminal device detected using PDR technology using a sensor of the terminal device.

Images