Information processing device, information processing method, and program

Abstract

To properly analyze behavior of each user in an area.SOLUTION: An information processing apparatus includes: a flow acquisition unit which acquires flow information including position and time of a communication device used by a user in an area; a first acquisition unit which acquires, based on the flow information acquired by the flow acquisition unit, stay time information indicating a length of time in which the communication device stayed in the area; a second acquisition unit which acquires moving distance information indicating a moving distance of the communication device in the area, on the basis of the flow information; a third acquisition unit which acquires, based on the flow information, stay region information indicating a subdivided region in which the communication device stayed, out of multiple subdivided regions obtained by dividing the area; and a flow analysis unit which analyzes, based on the stay time information acquired by the first acquisition unit, the moving distance information acquired by the second acquisition unit, and the stay region information acquired by the third acquisition unit, whether two or more pieces of flow information acquired by the flow acquisition unit are flow information of the same user or not.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] Conventionally, in stores such as supermarkets and shopping malls, in order to grasp users' consumption trends and further increase sales, it is required to analyze information on how consumers move within a facility. For example, Patent Document 1 proposes a position information collecting apparatus that collects action logs (movement histories) of customer users on a shopping floor by receiving signals transmitted from signal transmitters disposed in a portable container that can be carried by a user in a shopping area and stores products.

Prior Art Literature

Patent Literature

[0003]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] However, for example, when communication devices are attached to a basket and a cart as product carrying tools, and a user carries both the basket and the cart at the same time, two or more pieces of flow line data are obtained for one user. In this case, if it cannot be specified that the two or more pieces of flow line data are data resulting from the action of one user, there are problems that the number of users who used the store cannot be specified after aggregating flow line data from a large number of communication devices, and behavior analysis of individual users within the store cannot be performed. Accordingly, an object of the present invention is to more appropriately perform behavior analysis of individual users within an area.

Means for Solving the Problem

[0005] One aspect of the present invention is an information processing device comprising: a movement path acquisition unit that acquires movement path information including the location and time of a communication device used by a user within an area; a first acquisition unit that acquires stay time information indicating the stay time of the communication device within the area based on the movement path information acquired by the movement path acquisition unit; a second acquisition unit that acquires travel distance information indicating the travel distance of the communication device within the area based on the movement path information; a third acquisition unit that acquires stay area information indicating the stay area of ​​a plurality of divided areas within the area where the communication device stayed, based on the movement path information; and a movement path analysis unit that analyzes whether two or more movement path pieces acquired by the movement path acquisition unit belong to the same user, based on the stay time information acquired by the first acquisition unit, the travel distance information acquired by the second acquisition unit, and the stay area information acquired by the third acquisition unit. [Effects of the Invention]

[0006] According to one aspect of the present invention, it is possible to more appropriately analyze the behavior of individual users within an area. [Brief explanation of the drawing]

[0007] [Figure 1] This is a schematic diagram illustrating the user behavior analysis system of an embodiment. [Figure 2] This figure shows an example of the data structure of a movement pattern dataset. [Figure 3] This diagram illustrates the movement path of a single wireless tag in an exemplary store where the user behavior analysis system of this embodiment is applied. [Figure 4] This diagram shows a basket and cart being used by a single customer to transport items within a store. [Figure 5] This diagram shows five example customer flow patterns within a store. [Figure 6] This figure shows an example of the data structure of group data. [Figure 7] This block diagram shows the internal configuration of each device in the user behavior analysis system of the embodiment. [Figure 8] This flowchart shows the operation of the user behavior analysis system according to the embodiment. [Figure 9] This figure shows two of the five movement paths shown in Figure 5 that were identified as belonging to the same user. [Figure 10] This diagram illustrates data that associates group IDs with zones of stay. [Figure 11] This diagram shows the zones assigned to each user. [Modes for carrying out the invention]

[0008] The following describes one embodiment of the information processing device, information processing method, and program of the present invention. Below, as an example of a system including the information processing device, a user behavior analysis system that identifies user movement information from movement information of a communication device attached to a product transport device such as a shopping cart or shopping basket will be described.

[0009] For example, in stores with multiple sales areas, such as supermarkets, many customers move around the store, pick up items from different sales areas, and pay at the cash register. Shopping carts are used to pick up items and transport them to the cash register. Therefore, in order to analyze the behavior of customers using the store, it is conceivable to attach communication devices to shopping carts and acquire data on the movement of the shopping carts (in other words, the trajectory of the communication devices).

[0010] Incidentally, customers in a store may use only a shopping cart, only a shopping basket, or both. Therefore, in order to more accurately analyze the behavior of store customers, it is necessary to attach communication devices not only to shopping carts but also to shopping baskets. However, when both shopping carts and shopping baskets are used, multiple communication device movement paths will be obtained for the same customer.

[0011] Accordingly, the user behavior analysis system according to one embodiment described below identifies one or more movement lines corresponding to the movement line of each individual user from the movement lines of a plurality of communication devices. Thus, when user behavior analysis is performed after obtaining movement lines of a large number of communication devices, it is possible to identify the number of users who have used the store from the movement lines of the large number of communication devices, and to more appropriately perform behavior analysis of individual users within an area.

[0012] Hereinafter, a case where the communication device attached to a shopping cart or a shopping basket is a wireless tag will be described. However, the type of communication device is not limited thereto, and may be another communication device such as a smartphone, a wearable terminal, or a tablet terminal.

[0013] An outline of a user behavior analysis system 1 according to one embodiment will be described with reference to FIGS. 1 to 6.

[0014] FIG. 1 is a diagram schematically illustrating the user behavior analysis system 1 according to the embodiment. As illustrated in FIG. 1, the user behavior analysis system 1 of the present embodiment includes, for example, a wireless tag 2 attached to a cart CT, a basket, or the like used by each user in a store, a receiver 3, a store terminal 4, and a server 5 (an example of an information processing apparatus). FIG. 1 illustrates a case where the wireless tag 2 is attached to the cart CT.

[0015] The wireless tag 2 is an example of a communication device, and is, for example, a relatively small wireless communication device. The wireless tag 2 radiates radio waves (beacon signals) at a predetermined cycle. The beacon signal is radiated so as to be receivable within a predetermined range, depending on the surrounding radio wave environment. The beacon signal includes, for example, identification information (such as a tag ID) for identifying the wireless tag 2. The receiver 3 and the server 5 are connected via a network NW, and constitute a position specifying system that specifies the position of a visitor within a store. The network NW is, for example, a cellular network, a Wi-Fi network, the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), a public circuit, a private circuit, a radio base station, or the like.

[0016] In one embodiment, positioning of the wireless tag 2 uses the AOA (Angle of Arrival) method, in which the receiver 3 is installed on the ceiling of the store, the receiver 3 receives radio waves (beacon signals) radiated from the wireless tag 2, and the incident angle of the received beacon signal is calculated. The receiver 3 measures the incident angle (direction of arrival) of the beacon signal received from the wireless tag 2, and sends information on the measured incident angle to the server 5. The server 5 specifies the position (XY coordinates) of the wireless tag 2 based on the position (position in XYZ coordinates) of the source receiver 3 within the store and the incident angle with reference to that position. There is no limitation on the communication protocol between the wireless tag 2 and the receiver 3, and examples include Wi-Fi (registered trademark), Bluetooth (registered trademark) Low Energy (hereinafter referred to as BLE), and the like.

[0017] Although the position of the wireless tag 2 can be estimated with a single receiver 3 (locator), it is preferable to provide more receivers 3 in accordance with the magnitude of the received signal strength indicator (RSSI) of the beacon signal, the store area, and the radio wave environment of the store. For example, it is preferable to arrange the receivers 3 at equal intervals on the ceiling of the store, and arrange the receivers 3 at shorter intervals in places where positioning accuracy is particularly required, such as places with dense sales floors. Note that the positioning method for the wireless tag 2 is not limited to the AOA method, and other methods such as the TOA (Time of Arrival) method may also be used. The positioning interval of the wireless tag 2 may be arbitrarily set, but is set to a time (for example, 100 ms to 2 seconds) necessary for accurately grasping the behavior of the user. Note that there may be cases where the receiver 3 cannot receive the beacon signal from the wireless tag 2 (loses the beacon signal) at least temporarily due to poor communication between the wireless tag 2 and the receiver 3, a sleep operation of the wireless tag 2, or the like.

[0018] The store terminal 4 is, for example, located in the store's office and equipped with a display panel such as a personal computer or tablet. The store terminal 4 can communicate with the server 5 via a network NW. The store terminal 4 is a terminal that, for example, acquires movement data from the server 5 and displays the movement in correspondence with the store floor, or acquires and displays the execution results of a movement analysis program from the server 5, but it is not necessarily an essential component of the user behavior analysis system 1.

[0019] Server 5 calculates (acquires) the location of wireless tag 2 and records the movement data set of wireless tag 2. Figure 2 shows an example of the data structure of the movement data set. As shown in Figure 2, the movement data set associates the location data (XY coordinate position) of wireless tag 2 (an example of location information) and the time (timestamp ts) data (time information) for each tag ID, which is the identification information of wireless tag 2. In the following explanation, the data in which the location information and time information of wireless tag 2 are associated with a single tag ID will be referred to as "movement data" (an example of movement information). In other words, the movement data set contains multiple movement data corresponding to each of multiple tag IDs.

[0020] In the movement data set shown in Figure 2, the movement data corresponding to each tag ID corresponds to one movement. Figure 3 is a diagram illustrating the movement of one wireless tag in an exemplary store to which the user behavior analysis system of the embodiment is applied. In Figure 3, the movement FL corresponding to one tag ID is illustrated in a floor plan of a store floor (an example of an area) where product shelves SH and a checkout zone RZ are provided.

[0021] Figure 4 shows a basket and cart used by a single user in a store. A basket BK is placed on the cart CT shown in Figure 4. Here, since a user in the store may use only the cart CT or only the basket BK, wireless tags 2 are attached to both the cart CT and the basket BK in order to perform a more appropriate analysis of the user's behavior in the store. The wireless tags 2 are attached to a location such as the side or bottom of the basket BK or cart CT, so that they do not come off when the basket BK or products are placed in or removed. Preferably, the wireless tags 2 are attached to a location where the radio waves of the wireless tags do not interfere with each other. Figure 4 shows an example where wireless tag 2-1 is installed on the leg of cart CT and wireless tag 2-2 is installed on the side of cage BK, but the installation location of the wireless tags is not limited to the example shown in Figure 4. As shown in Figure 4, when a user transports a cart CT with a basket BK on it, two pieces of movement data are acquired for that user. If a user terminal (such as a smartphone or wearable device) carried by a store user functions as a wireless tag, movement data can also be acquired from the user terminal. Therefore, Server 5 executes a movement analysis program to identify one or more movement data points corresponding to the movement data of individual users from multiple movement data points. Server 5 identifies one or more movement data points corresponding to the same user based on multiple movement data points (multiple movement data points associated with each of multiple tag IDs) acquired within a predetermined time period (e.g., one day).

[0022] Figure 5 shows five exemplary movement paths within a store. For example, Figure 5 shows five movement paths FL1 to FL5 corresponding to five movement path data acquired within a predetermined time within an exemplary store floor (an example of an area). In this example, Server 5 identifies one or more movement paths from the five movement paths FL1 to FL5 that correspond to the same user by executing a movement path analysis program. In order to identify one or more movement paths that correspond to the same user, Server 5 divides the store floor into multiple zones (an example of a divided area) and processes each movement path data. In the example shown in Figure 5, the store floor is divided into 16 zones in a 4x4 grid consisting of zones Z11 to Z44. Note that while Figure 5 shows each zone as a rectangle or square, it is not limited to these, and can also be a polygon such as a regular hexagon. Server 5 has a store map that includes two-dimensional information on the plan of the store floor and two-dimensional information on the boundary positions of each zone on the store floor.

[0023] Figure 6 shows an example of the data structure of group data. Server 5 generates group data as a result of identifying one or more movement data corresponding to the same user from multiple movement data obtained from multiple wireless tags acquired within a predetermined time. The group data shows the result of grouping the tag IDs corresponding to each movement data in the movement data set (Figure 2), with a unique group ID assigned to one or more tag IDs corresponding to the same user. In the example in Figure 6, one group ID is assigned to two tag IDs (xxx01, xxx65). One group ID means that the movement data is caused by the actions of a single user within the store. From this group data, it is possible to recognize one or more tag IDs corresponding to the same user.

[0024] Next, the internal configuration of the user behavior analysis system 1 will be described with reference to the block diagram in Figure 7. Figure 7 is a block diagram showing the internal configuration of each device in the user behavior analysis system of the embodiment. As shown in Figure 7, the wireless tag 2 includes, for example, a control unit 21 and a communication unit 22. The control unit 21 is mainly composed of a microcontroller and controls the entire wireless tag 2. For example, the control unit 21 performs processing on received signals and transmitted signals (processing of baseband signals). The communication unit 22 is an interface for communicating with the receiver 3, and for example modulates the transmission signal to the receiver 3 (e.g., a beacon signal) and broadcasts it according to BLE. The beacon signal includes the tag ID of the wireless tag 2.

[0025] As shown in Figure 7, the receiver 3 comprises a radio wave receiving unit 31, an incident angle measuring unit 32, and a communication unit 33. The radio wave receiving unit 31 includes an antenna that receives beacon signals (radio waves) transmitted from the wireless tag 2. The incident angle measuring unit 32 measures the incident angle of the radio waves from the wireless tag 2 received by the radio wave receiving unit 31. The communication unit 33 is an interface for communicating with the wireless tag 2 and the server 5. For example, the communication unit 33 demodulates the received signal from the wireless tag 2. The communication unit 33 also associates the incident angle information measured by the incident angle measuring unit 32 with the tag ID included in the received beacon signal and transmits it to the server 5 via the network NW.

[0026] As shown in Figure 7, the store terminal 4 comprises a control unit 41, a display unit 42, and a communication unit 43. The control unit 41 is mainly composed of a microcontroller and controls the entire store terminal 4. For example, the control unit 41 acquires movement data from the server 5 via the communication unit 43 for display and displays the movement on the display unit 42 as shown in Figure 3, and / or acquires the execution results of a movement analysis program from the server 5 and displays them on the display unit 42. The display unit 42 includes, for example, a display panel such as an LCD (Liquid Crystal Display) panel and a drive circuit that drives the display panel based on display data acquired from the server 5. For example, by executing a predetermined program, the control unit 41 displays the movement of the wireless tag 2 and the movement of each user on the display unit 42 based on movement data sets for each tag ID acquired from the server 5, and group data as shown in Figure 6. The communication unit 43 functions as a communication interface for communicating with the server 5 via the network NW.

[0027] As shown in Figure 7, the server 5 comprises a control unit 51, storage 52, and a communication unit 53. The control unit 51 is mainly composed of a microcontroller and controls the entire server 5. For example, when the microcontroller of the control unit 51 executes a movement analysis program, the control unit 51 functions as a movement acquisition unit 511, a first data acquisition unit 512, a second data acquisition unit 513, a third data acquisition unit 514, and a movement analysis unit 515.

[0028] The movement path acquisition unit 511 acquires movement path data, including the location and time of use of wireless tags 2 used by users within the store floor. The movement path acquisition unit 511 acquires movement path data for each tag ID based, for example, on information such as the incident angle for each tag ID received from the receiver 3. The first data acquisition unit 512 acquires dwell time information indicating the dwell time of the wireless tag 2 within the store floor, based on the dwell time data of the wireless tag 2 acquired by the dwell time acquisition unit 511. The second data acquisition unit 513 acquires travel distance information indicating the distance traveled by the wireless tag 2 within the store floor, based on the dwell time data of the wireless tag 2 acquired by the dwell time acquisition unit 511. The third data acquisition unit 514 acquires dwell zone information (an example of dwell area information) indicating the zone where the wireless tag 2 stayed, out of multiple zones into which the store floor is divided, based on the dwell time data of the wireless tag 2 acquired by the dwell time acquisition unit 512, the travel distance information acquired by the second data acquisition unit 513, and the dwell zone information acquired by the third data acquisition unit 514, to determine whether two or more dwell time data acquired by the dwell time acquisition unit 511 belong to the same user.

[0029] In one embodiment, the movement path analysis unit 515 analyzes that the movement path information of two or more movement path information belongs to the same user if the degree of matching of the dwell time information, travel distance information, or dwell area information of the two or more movement path information is greater than or equal to the respective threshold. Because this is a simple process of comparing the degree of matching of each piece of information with a threshold, the computational load can be reduced even when the divided areas are set finely.

[0030] In one embodiment, the movement analysis unit 515 is configured as shown in (i) to (iii) below. (i) The degree of agreement between the dwell time information of two dwell time pieces of dwell time information, one of the two or more dwell time pieces of dwell time information mentioned above, and the other dwell time piece of dwell time information, is set to be greater the closer the two dwell time pieces of dwell time information corresponding to each of the two dwell time pieces of dwell time information are. (ii) The degree of matching of the travel distance information of the two movement path information in (i) is set to be greater the closer the lengths of the two travel distances corresponding to each of the two movement path information are. (iii) The degree of matching of the dwell area information of the two movement path information in (i) is set to be greater the closer the number of dwell areas that the two movement path information items have in common is. This reduces the computational load when setting the degree of matching for each piece of information.

[0031] In one embodiment, the movement path analysis unit 515 calculates a score based on the degree of matching of the stay time information, travel distance information, and stay area information of the two or more movement path information, such that the weighting of the stay area information is relatively larger, and analyzes whether the two or more movement path information belong to the same user based on the calculated score. By setting weights for each score in this way, it is possible to perform optimal analysis tailored to the size and type of business of each individual store.

[0032] In one embodiment, the control unit 51 may function as a mapping unit. When the mapping unit analyzes that the two or more movement information pieces belong to the same user, it maps the areas of stay identified based on the two or more movement information pieces to the same user. The control unit 51 functions as a correspondence unit, enabling accurate coverage of the areas occupied by the same user, and allowing for more effective use of the identified areas occupied by the same user.

[0033] In one embodiment, the control unit 51 analyzes that the two or more movement path information belong to the same user, and if there is a period in the first movement path information among the two or more movement path information that does not include the location information of a communication device, the control unit 51 includes an interpolation unit that interpolates the location information of the communication device corresponding to that period in the first movement path information using the location information of the communication device corresponding to that period in the movement path information other than the first movement path information among the two or more movement path information. Because the control unit 51 functions as an interpolation unit, even if location information from one communication device cannot be temporarily obtained, it can be supplemented with location information from other communication devices, allowing for more accurate analysis of user behavior within the store.

[0034] In one embodiment, the control unit 51 may function as a user count identification unit. The user count identification unit identifies the number of users who stayed in the area from the multiple movement information acquired by the movement acquisition unit 511 by counting the two or more movement information pieces as movement information based on one user when the two or more movement information pieces are analyzed to be movement information of the same user. This makes it possible to identify the number of users who used the store.

[0035] Storage 52 is a large-capacity storage device, such as an HDD (Hard Disk Drive), and stores store maps, traffic flow data sets (traffic flow DS; see Figure 2), and group data (see Figure 6). Each piece of data in storage 52 is updated, added, or deleted as appropriate in response to access from the control unit 51. The store map is referenced by the control unit 51 to identify the zone corresponding to the location of the wireless tag 2 among multiple zones on the store floor. The communication unit 53 functions as a communication interface for communicating with the receiver 3 and the store terminal 4 via the network NW.

[0036] Next, with reference to Figure 8, the movement path analysis process performed by the server 5 will be described. Figure 8 is a flowchart showing the operation of the user behavior analysis system of the embodiment. The movement path analysis process is performed by the control unit 51 of the server 5 executing a movement path analysis program, which identifies one or more movement path data corresponding to the same user from the movement path dataset of multiple wireless tags acquired. For example, the process including movement path data FD1 to FD5 corresponding to the five exemplary movement paths FL1 to FL5 shown in Figure 5 will be described as appropriate.

[0037] Referring to Figure 8, the movement path analysis process first determines a reference movement path data (an example of reference movement path information) from the movement path data of multiple wireless tags to be processed (in the example in Figure 5, five movement path data corresponding to five movement paths FL1 to FL5) (step S2). The movement path data of multiple wireless tags to be processed are sequentially used as reference movement path data, and when the processing in steps S2 to S14 is completed, the process proceeds to step S18 (step S16). For example, movement path data FD1 corresponding to movement path FL1 shown in Figure 5 is determined as the reference movement path data. The control unit 51 sequentially calculates the degree of match in stay time (step S4), the degree of match in travel distance (step S6), and the degree of match in stay zone (step S8) between the reference movement path data FD1 and each of the other movement path data FD2 to FD5. The degree of match is an example of the degree of agreement. The following describes exemplary calculation methods for the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone.

[0038] (I) Match of length of stay For example, the degree of match in dwell time refers to the degree of similarity between the two dwell times corresponding to each of two movement data sets, and is calculated, for example, based on the ratio or difference in dwell times between the two movement data sets. If the dwell time of the reference movement data is t1 and the dwell time of the other movement data is t2, the closer the ratio calculated by the following formula (1) is to 100%, the greater the degree of match between the two dwell times corresponding to each of the two movement data sets. In other words, the degree of match in the dwell time information of the two movement data sets is set to be greater the closer the ratio of the lengths of the two dwell times corresponding to the two movement data sets is to 1. That is, the degree of match in the dwell time information of the two movement data sets is set to be greater the closer the two dwell times corresponding to each of the two movement data sets are. (1-(|t1-t2|) / t1)×100[%]…Equation (1) You may also set it so that the closer the difference between the two stay times (|t1-t2|) is to zero (i.e., the smaller the difference in the length of stay times), the greater the match between the two stay times corresponding to each of the two movement data sets.

[0039] If the ratio calculated according to formula (1) above is taken as the degree of match in terms of dwell time, then for each of the dwell time data FD2 to FD5 corresponding to the dwell time FL2 to FL5 shown in Figure 5, the degree of match in terms of dwell time with the reference dwell time data FD1 is as follows. • Movement flow data FD2: 99% • Movement flow data FD3: 98% • Movement data FD4: 100% • Movement flow data FD5: 50%

[0040] (II) Matching degree of travel distance For example, the degree of match between movement distances refers to the degree of identity between the two movement distances corresponding to each of the two movement path data sets, and is calculated based on, for example, the ratio or difference of the movement distances of the two movement path data sets. If the movement distance of the reference movement path data is d1 and the movement distance of the other movement path data is d2, the closer the ratio calculated by the following formula (2) is to 100%, the greater the degree of match between the two movement distances corresponding to each of the two movement path data sets. In other words, the degree of match between the movement distance information of the two movement path data sets is set to be greater the closer the ratio of the lengths of the two movement distances corresponding to the two movement path data sets is to 1. That is, the degree of match between the movement distance information of the two movement path data sets is set to be greater the closer the lengths of the two movement distances corresponding to each of the two movement path data sets are. (1-(|d1-d2|) / d1)×100[%]…Equation (2) You may set it so that the closer the difference between the two travel distances (|d1-d2|) is to zero (i.e., the smaller the difference in the length of the travel distances), the greater the match between the two travel distances corresponding to each of the two movement data sets.

[0041] If the ratio calculated according to formula (2) above is taken as the degree of match of travel distance, then for each of the movement path data FD2 to FD5 corresponding to the movement paths FL2 to FL5 shown in Figure 5, the degree of match of travel distance with the reference movement path data FD1 is as follows. • Movement flow data FD2: 97% • Movement flow data FD3: 85% • Movement flow data FD4: 25% • Movement flow data FD5: 50%

[0042] (III) Matching degree of the zone of stay For example, the degree of match in the dwelling zones refers to the degree to which the corresponding wireless tag 2 stayed in the same zone (dwelling zone) as the two movement path data sets. For example, if Nz is the number of dwelling zones shown by the reference movement path data, and Nc is the number of dwelling zones shown by the other movement path data that are common with the reference movement path data, the degree of match in the dwelling zones is calculated using (Nc / Nz) × 100 [%] (Equation 3). The larger the proportion of dwelling zones that are commonly shown by each of the two movement path data sets, the greater the degree of match. The degree of match in the dwelling zone information of the two movement path data sets is set to be greater the closer the ratio of the number of dwelling zones commonly shown by each of the two movement path data sets to the number of dwelling zones shown by the reference movement path data set is to 1. Alternatively, the degree of match in the dwelling zones may be set to be greater the closer the value of (Nz-Nc) is to zero. In other words, the degree of match in the dwelling area information of the two movement path data sets is set to be greater the closer the number of dwelling areas commonly shown by each of the two movement path data sets is.

[0043] In the example shown in Figure 5, the dwell zones indicated by each movement data are as follows: • Movement data FD1: Z12, Z22, Z24, Z31, Z32, Z33, Z34 • Movement data FD2: Z12, Z14, Z22, Z24, Z31, Z32, Z33, Z34, Z41 • Movement data FD3: Z11, Z12, Z13, Z14, Z21, Z24, Z31, Z34, Z41, Z42, Z43, Z44 • Movement data FD4: Z21, Z22, Z31, Z32 • Movement data FD5: Z11, Z12, Z21, Z22, Z31, Z32

[0044] Therefore, the number of dwell zones Nz indicated by the reference dwell zone data FD1 is 7. The degree of match for each dwell zone of the dwell zones of the dwell zone data FD2 to FD5, other than the reference dwell zone data, is calculated using the above formula (3) and is as follows. • Movement data FD2: 100% (Nc=7) • Movement data FD3: 57% (Nc=4) • Movement data FD4: 43% (Nc=3) • Movement data FD5: 57% (Nc=4)

[0045] Referring again to the flowchart in Figure 8, once the calculation of the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone has been completed between the reference movement data and all other movement data (step S10: YES), the control unit 51 executes step S12. In step S12, the control unit 51 determines whether there is any movement data in which the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone satisfy predetermined conditions. In one embodiment, the conditions are "the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone are equal to or greater than their respective thresholds", or "the value obtained by summing the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone and dividing by 3 (= number of times the degree of match was calculated) is equal to or greater than a predetermined value". By setting such simple conditions, a decision can be made quickly, but the system is not limited to these conditions. For example, if the condition for step S12 is "the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone are all 90% or higher," then the only movement data that satisfies the condition will be movement data FD2.

[0046] If there is movement path data that satisfies the conditions in step S12 (step S12: YES), the control unit 51 records the movement path data in memory (step S14). If the movement path data that satisfies the conditions is movement path data FD2, movement path data FD2 is recorded in association with reference movement path data FD1. In this case, reference movement path data FD1 and movement path data FD2 are analyzed as movement path data of the same user.

[0047] The above describes the series of processes when movement path data FD1 is used as the reference movement path data. Similarly, the control unit 51 executes the processes in steps S2 to S14, using each of the movement path data FD2 to FD5 as the reference movement path data in order. As a result, for example, in the example where movement path analysis processing is applied to the movement path data corresponding to the five movement paths in Figure 5, it is determined that the movement path data FD1 and FD2 corresponding to movement paths FL1 and FL2 are movement path data of wireless tags used by the same user. Figure 9 shows two movement paths identified as belonging to the same user out of the five movement paths shown in Figure 5. As shown in Figure 9, movement paths FL1 and FL2 follow similar paths to each other, but for example, movement path FL2 differs from movement path FL1 in that it enters zones Z14 and Z41.

[0048] Furthermore, the conditions in step S12 may be set considering the weighting of the degree of match of stay time, the degree of match of travel distance, and the degree of match of stay zone. For example, the weight of the degree of match of stay zone may be made relatively higher. For example, in stores with relatively small floor space, the degree of matching between dwell time and distance traveled tends to be high regardless of the shape of the traffic flow. In such cases, it is advisable to define each zone within the store in detail and relatively increase the weight of the degree of matching for the dwell zone. By defining each zone within the store in detail, it becomes possible to create a significant difference in the degree of matching for the dwell zone across multiple traffic flow data sets. When the weighting of the match degree of stay zone is relatively high, for example, the sum of the match degree of stay time, the match degree of travel distance, and the value obtained by multiplying the match degree of stay zone by a coefficient greater than 1 is compared with a predetermined threshold to determine whether the conditions are met.

[0049] Once the series of processes using the movement data as reference movement data is completed (step S16: YES), the control unit 51 creates group data (see Figure 6) based on the movement data recorded in memory in step S14 (step S18). That is, if movement data FD2 is recorded in association with reference movement data FD1, the control unit 51 groups the tag ID corresponding to reference movement data FD1 and the tag ID corresponding to movement data FD2 and assigns a unique group ID. If the reference movement data is not associated with any movement data other than the reference movement data, the control unit 51 assigns a unique group ID to the tag ID corresponding to the reference movement data. One group ID corresponds to one user. Therefore, one or more tag IDs assigned to the same group ID mean that they are tag IDs of wireless tags 2 associated with the same user.

[0050] As described above, in the user behavior analysis system 1 of one embodiment, one or more movement paths are associated with the same user based on the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone, for multiple movement path data obtained from multiple wireless tags. At that time, the calculation of the degree of match in stay time, the degree of match in travel distance, and the degree of match in stay zone can be performed using relatively simple calculations as described above. Therefore, for example, one or more movement path data attributable to the same user can be identified at high speed from a large amount of movement path data acquired within a predetermined time. Furthermore, identifying one or more movement data points attributable to the same user offers the following advantages: (i) When analyzing user behavior after obtaining movement data from numerous wireless tags 2, the number of users who visited the store can be identified from the movement data of the numerous wireless tags 2. (ii) Since each user is associated with one or more movement data points, it becomes possible to perform a more appropriate analysis of individual users' behavior within the store.

[0051] After performing the movement analysis process, the control unit 51 can perform various post-processing operations using one or more tag IDs associated with the same group ID.

[0052] [Example of post-processing, part 1] For example, the control unit 51 may associate all dwelling zones identified based on one or more movement data acquired for one or more tag IDs corresponding to the same group ID with the same user. That is, when the control unit 51 determines that the movement data of two or more wireless tags 2 is the movement data of the same user, it functions as an association unit that associates the dwelling zones identified from the movement data of two or more wireless tags 2 with the same user. For example, in the example shown in Figure 9, dwelling zones Z12, Z14, Z22, Z24, Z31, Z32, Z33, Z34, and Z41 identified based on movement data FD1 and FD2 are associated with the same user. The mapping unit uses the group data and movement data set obtained by performing movement flow analysis processing to map group IDs to dwell zones by referring to a store map. Figure 10 is an example of data where group IDs and dwell zones are mapped.

[0053] By performing this processing, it becomes possible to cover a wider range of zones where the same user is thought to have stayed. In the example shown in Figure 9, analyzing user behavior based on movement data FD1 and FD2 allows for a broader understanding of user behavior than analyzing user behavior based solely on movement data FD1. In other words, user behavior can be grasped more comprehensively and with greater accuracy. For example, movement data FD2 covers zones Z14 and Z41 more comprehensively than movement data FD1, making it possible to obtain information such as the user's action of loading a basket onto a cart, or temporarily removing the basket from the cart and moving to a different location within those zones. In short, it becomes possible to analyze user behavior in a way that cannot be obtained with a single piece of movement data. Figure 9 is a relatively simple example consisting of 4x4 zones, but the finer the zones are, the more precisely the zones where the same user is thought to have stayed can be covered.

[0054] Figure 11 shows the zones assigned to a single user. When all dwelling zones identified based on two or more movement data sets are associated with the same user, binarization as shown in Figure 11 improves convenience. Figure 11 shows the dwelling zones covered and not covered by the movement data sets FD1 and FD2 shown in Figure 9 in different display modes. In the example shown in Figure 11, the dwelling zones covered by movement data set FD1 are zones Z11, Z13, Z21, Z23, Z42~Z44, and the dwelling zones covered by movement data set FD2 are zones Z12, Z14, Z22, Z24, Z31~Z34, Z41. Displaying this binarized information on, for example, a store terminal 4, makes it easier to visualize user behavior than simply displaying movement patterns. Furthermore, binarization enables digital processing based on the user's dwelling zone, which has the advantage of making it easier to analyze user behavior based on their zones of stay.

[0055] [Second example of post-processing] As illustrated in Figure 2, the movement data is data that associates the location data of the wireless tag 2 with time data, but the location of the wireless tag 2 cannot always be obtained for all times. For example, due to the sleep operation of the wireless tag 2 or the radio wave conditions, the receiver 3 may temporarily be unable to receive the beacon signal from the wireless tag 2 (the beacon signal is lost). In such cases, the server 5 cannot obtain the location information of the wireless tag 2, and therefore cannot analyze the user's behavior with high accuracy. In such cases, as described above, if two or more movement data sets are associated with individual users (for example, users identified by a group ID) as shown in Figure 6 (for example, tag IDs "xxx01" and "xxx65"), the location information for the period during which location information could not be obtained from the two or more movement data sets (for example, a portion of the movement data assigned to stay zone Z12 in Figure 5 from the movement data of tag ID "xxx01" (an example of the first movement information)) can be interpolated using other movement data (for example, a portion of the movement data assigned to stay zone Z12 in Figure 5 from the movement data of tag ID "xxx65") (i.e., the movement data for stay zone Z12 in Figure 5 of the user identified by the group ID) can be identified. As a result, even if a portion of the movement data of the wireless tag 2 associated with a user is missing, other movement data associated as movement data of the same user can be identified as the user's movement data, making it possible to analyze user behavior within the store with greater accuracy. In other words, the control unit 51 of the server 5 may function as an interpolation unit that, when it is determined that two or more movement data are movement data of the same user, and there is a period in the first movement data among the two or more movement data that does not include location information of the wireless tag 2, interpolates the location information of the wireless tag 2 corresponding to the period of the first movement data with the location information of the wireless tag 2 corresponding to the period of the movement data other than the first movement data among the two or more movement data.

[0056] [Example 3 of post-processing] By performing movement flow analysis processing, it is possible to determine the number of users who used the store during the period in which multiple movement flow data included in the movement flow dataset were acquired. The control unit 51 of the server 5 functions as a user count identification unit that identifies the number of users who stayed on the store floor from the acquired movement flow data of multiple wireless tags 2 by counting the movement flow data of multiple wireless tags 2 as movement flow data of one user when the movement flow data of multiple wireless tags 2 is analyzed to be the movement flow data of the same user. Specifically, the user count identification unit identifies the number of users by identifying the number of group IDs based on group data. This makes it possible to identify the number of users who used the store during a predetermined period.

[0057] Although embodiments of the information processing device, information processing method, and program have been described above, the present invention is not limited to the embodiments described above. Furthermore, the above embodiments can be improved or modified in various ways without departing from the spirit of the present invention.

[0058] For example, the above-described embodiment explains the case where data is exchanged between the store terminal 4 and the server 5 via a network NW, but this is not limited to that. Data can also be exchanged between the store terminal 4 and the server 5 via storage media such as a USB (Universal Serial Bus) memory, an SD (Secure Digital) memory card, an HDD device, or an SSD (Solid State Drive). The receiver 3 and the server 5 are not limited to communicating via a network NW, but may also communicate one-to-one via wired or wireless connections.

[0059] In the embodiment described above, processing may be distributed across multiple server devices to realize the functions of server 5, or the data stored in the storage 52 of server 5 may be distributed and managed across multiple external storage devices accessible from the control unit 51 of server 5. Functions may also be distributed between server 5 and store terminal 4 as appropriate. [Explanation of Symbols]

[0060] 1…User behavior analysis system 2… Wireless tags 21... Control Unit 22... Communications Department 3…Receiver 31...Radio wave receiving unit 32...Incidence angle measurement section 33... Communications Department 4…Store terminals 41... Control Unit 42...Display section 43… Communications Department 5…Server 51... Control Unit 511…Flow line acquisition section 512...First Data Acquisition Unit 513...Second Data Acquisition Unit 514...Third Data Acquisition Unit 515…Flow line analysis department 52...Storage 53... Communications Department BK...basket NW...Network CT... Cart RZ...Region Zone SH…Product shelf Z11~Z44... Zone

Claims

1. A movement path acquisition unit acquires movement path information, including the location and time of communication devices used by users within the area. A first acquisition unit acquires dwell time information indicating the dwell time of the communication device within the area based on the aforementioned movement information, A second acquisition unit acquires distance information indicating the distance traveled by the communication device within the area based on the aforementioned movement information, A third acquisition unit acquires dwelling area information indicating the dwelling area among a plurality of divided areas within the area where the communication device stayed, based on the aforementioned movement information. A movement path analysis unit analyzes whether two or more movement path information acquired by the movement path acquisition unit belong to the same user, based on the stay time information acquired by the first acquisition unit, the travel distance information acquired by the second acquisition unit, and the stay area information acquired by the third acquisition unit. Equipped with an information processing device.

2. The movement path analysis unit analyzes that the movement path information of the two or more movement path information belongs to the same user if the degree of matching of the stay time information, travel distance information, or stay area information of the two or more movement path information is above the respective threshold. The information processing apparatus described in claim 1.

3. The aforementioned movement path analysis unit, The degree of agreement between the reference movement information, which is the reference movement information among the two or more movement information pieces mentioned above, and the movement information other than the reference movement information, is set such that the degree of agreement between the two movement information pieces is greater the closer the two movement information pieces correspond to each of the two movement information pieces. The degree of matching between the two movement path information and the travel distance information is set to increase as the lengths of the two travel distances corresponding to each of the two movement path information become closer. The degree of matching between the two movement path information and the dwelling area information is set to increase as the number of dwelling areas common to each of the two movement path information becomes closer. The information processing apparatus according to claim 2.

4. The movement path analysis unit calculates a score based on the degree of matching of the stay time information, travel distance information, and stay area information of the two or more movement path information, such that the weighting of the stay area information is relatively larger, and analyzes whether the two or more movement path information belong to the same user based on the calculated score. An information processing apparatus according to any one of claims 1 to 3.

5. When the two or more pieces of movement information are analyzed to be the movement information of the same user, the system includes a mapping unit that associates the area of ​​stay identified based on the two or more pieces of movement information with the same user. An information processing apparatus according to any one of claims 1 to 4.

6. If the two or more movement path information sets are analyzed to be the movement path information of the same user, and there is a period in the movement path information set of the two or more movement path information sets that does not include the location information of a communication device, the interpolation unit is provided to interpolate the location information of the communication device corresponding to the aforementioned period in the first movement path information set of the first movement path information set with the location information of the communication device corresponding to the aforementioned period in the movement path information set of the other movement path information set of the two or more movement path information sets of the two or more movement path information sets, An information processing apparatus according to any one of claims 1 to 5.

7. The system includes a user count identification unit that identifies the number of users who stayed in the area from the multiple movement information acquired by the movement information acquisition unit, by counting the two or more movement information pieces as movement information based on one user when the two or more movement information pieces are analyzed to be movement information of the same user. An information processing apparatus according to any one of claims 1 to 6.

8. The aforementioned area includes stores that sell goods, The aforementioned communication device is provided in at least one of the shopping basket and the shopping cart. An information processing apparatus according to any one of claims 1 to 7.

9. An information processing method performed by an information processing device, A movement path acquisition step that acquires movement path information including the location and time of the communication device used by the user within the area, A first acquisition step involves acquiring dwell time information indicating the dwell time of the communication device within the area based on the aforementioned movement information, A second acquisition step involves acquiring distance information indicating the distance traveled by the communication device within the area, based on the aforementioned movement information. A third acquisition step involves acquiring dwelling area information, which indicates the dwelling area among a plurality of divided areas within the area where the communication device stayed, based on the aforementioned movement information. A movement path analysis step that analyzes whether two or more movement path information obtained in the movement path acquisition step belong to the same user, based on the stay time information obtained in the first acquisition step, the travel distance information obtained in the second acquisition step, and the stay area information obtained in the third acquisition step. Information processing methods including

10. Computers, A movement path acquisition unit acquires movement path information, including the location and time of communication devices used by users within the area. A first acquisition unit acquires dwell time information indicating the dwell time of the communication device within the area based on the aforementioned movement information. A second acquisition unit acquires distance information indicating the distance traveled by the communication device within the area based on the aforementioned movement information. A third acquisition unit acquires information on the area where the communication device stayed, based on the aforementioned movement information, and A movement path analysis unit analyzes whether two or more movement path information acquired by the movement path acquisition unit belong to the same user, based on the stay time information acquired by the first acquisition unit, the travel distance information acquired by the second acquisition unit, and the stay area information acquired by the third acquisition unit. A program designed to function as such.

Images