Analysis system, analysis device, and analysis method

Abstract

To provide an analysis system, an analysis device, and an analysis method that can lead to product purchase and can be used for marketing.SOLUTION: An analysis system includes a behavior acquisition device and an analysis device. The behavior acquisition device transmits information on behavior of a user in a store regarding a product. The analysis device receives the information on the behavior from the behavior acquisition device, and estimates, on the basis of the information on the behavior, interest degree of the user in the product. The interest degree indicates degree of association between the behavior and the product purchase of the user.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present invention relates to an analysis system, an analysis device, and an analysis method. [Background technology]

[0002] Conventionally, there have been information processing systems that promote user behavior. For example, there is the following information processing system. That is, there is an information processing system that accumulates user behavior as daily behavior data, classifies the user into a type (monetary reward-oriented type, social reward-oriented type, or altruistic type) based on the daily behavior data, and notifies the user of behavior promotion information according to the type, thereby promoting the user behavior (for example, energy-saving behavior). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5800184 Summary of the Invention [Problem to be solved by the invention]

[0004] However, for example, there are cases where a user takes the action of purchasing a certain product, and there are also cases where the user takes the action of not purchasing another product.

[0005] In the above-mentioned information processing system, the type of a user is uniformly determined based on whether or not the daily behavior data belongs to the data set for each type. Therefore, although the above-mentioned information processing system can classify users into types based on purchasing behavior and non-purchasing behavior, it does not take into consideration the fact that the types are classified into different types based on the target product.

[0006] Therefore, the above-described information processing system may not be able to encourage users to take action (for example, purchase) in accordance with the product, and may not lead to the purchase of the product.

[0007] Therefore, an object of the present disclosure is to provide an analysis system, an analysis device, and an analysis method that can lead to product purchases, and an analysis system, an analysis device, and an analysis method that can be used for marketing. [Means for solving the problem]

[0008] The analysis system according to a first aspect includes a behavior acquisition device and an analysis device. The behavior acquisition device transmits information about a user's behavior in a store regarding a product. The analysis device receives the behavior information from the behavior acquisition device and estimates the user's level of interest in the product based on the behavior information. The level of interest indicates the degree of association between the behavior and the user's purchase of the product.

[0009] An analysis device according to a second aspect includes a communication unit that receives information about a user's in-store behavior regarding a product from a behavior acquisition device. The analysis device also includes a control unit that estimates the user's level of interest in the product based on the information about the behavior. The level of interest indicates the degree of association between the behavior and the user's purchase of the product.

[0010] An analysis method according to a third aspect is an analysis method in an analysis system including a behavior acquisition device and an analysis device. The analysis method includes a step in which the behavior acquisition device transmits information about a user's in-store behavior with respect to a product. The analysis method also includes a step in which the analysis device receives the information about the behavior from the behavior acquisition device and estimates the user's level of interest in the product based on the information about the behavior. The level of interest indicates the degree of association between the behavior and the user's purchase of the product. [Effects of the Invention]

[0011] According to the present disclosure, it is possible to provide an analysis system, an analysis device, and an analysis method that can lead to product purchases. Also, according to the present disclosure, it is possible to provide an analysis system, an analysis device, and an analysis method that can be used for marketing. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an analysis system according to the first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of an application scenario of the analysis system according to the first embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of an application scenario of the analysis system according to the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of the appliance communication device according to the first embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of the configuration of a beacon transmitting device according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of a user terminal device according to the first embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of the configuration of the analysis device according to the first embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of operation according to the first embodiment. [Figure 9] 9(A) and 9(B) are diagrams showing examples of the relationship between behavior and interest level according to the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of operation according to the second embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of user attribute information and product attribute information according to the second embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of a learning model according to the second embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of learning data according to the second embodiment. [Figure 14] FIG. 14 is a diagram illustrating an example of data included in the learning model according to the second embodiment. [Figure 15] FIG. 15 is a diagram illustrating an example of data included in the learning model according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] [First embodiment] Hereinafter, the embodiments will be described in detail with reference to the drawings. In the description of the drawings, the same or similar parts are denoted by the same or similar reference numerals.

[0014] (Example of analysis system configuration) Next, a description will be given of an example of the configuration of an analysis system according to the first embodiment. Fig. 1 is a diagram showing an example of the configuration of an analysis system 10.

[0015] The analysis system 10 includes a plurality of instrument communication devices 100 (100-1, 100-2, 100-3, ...), a plurality of product tags 200 (200-1, 200-2, 200-3, ...), a plurality of beacon transmitting devices 300 (300-1, 300-2, 300-3, ...), a user terminal device 400, an analysis device 500, and a camera device 750.

[0016] In one embodiment, the appliance communication device 100, the product tag 200, and the camera device 750 are installed in a store S. In the following, an example will be described in which the store S is an apparel store, but the store S may be any store that sells the product P, such as a supermarket, a greengrocer, or a fishmonger.

[0017] Furthermore, in one embodiment, the appliance communication device 100 and the product tag 200 are provided in a display zone Z. In the following, a hanger rack and a display shelf will be described as examples of the display zone Z, but the display zone Z may be any zone that displays the product P, such as a showcase. In the following, an example will be described in which one display zone Z exists in the store S, but multiple display zones Z may exist in the store S.

[0018] The appliance communication device 100 is attached to a holding appliance H that holds the product P. The appliance communication device 100 may be incorporated into the holding appliance H or attached to the surface of the holding appliance H. The appliance communication device 100 is a communication device attached to the holding appliance H. In the following, a hanger will be used as an example of the holding appliance H. However, the holding appliance H may be any appliance capable of holding the product P, such as a tray or a product fixture. In the following, an example will be described in which a plurality of sets, each of which includes a holding appliance H and a product P, are provided in the display zone Z. However, the number of sets may be one. In the example shown below, an example will be described in which the appliance communication device 100 is attached to the holding appliance H, but the attachment of the appliance communication device 100 is not limited to the holding appliance H. For example, the appliance communication device 100 may be attached to the product tag 200 of the product P or to a string connecting the product tag 200 and the product P. Alternatively, the appliance communication device 100 may be attached to the price tag of the product P, or may be attached directly to the front or back of the product P.

[0019] The product tag 200 is a tag attached to the product P. In the following, an example of a wireless tag will be described as the product tag 200, but the product tag 200 may be a barcode or a QR code (registered trademark; the same applies below). A product identifier (product ID or product identification information) that distinguishes the product P from other products is written in the product tag 200. When the product tag 200 is a wireless tag, the wireless tag may be called an IC tag, RFID, or RF tag. The wireless tag may be a passive wireless tag or an active wireless tag. When the product tag 200 is a barcode or a QR code, a product identifier is written in the barcode or the QR code. The product tag 200 may be attached to the surface of the product P, or may be attached to a label attached to the product P.

[0020] The beacon transmitting device 300 is installed in a facility E located in the store S. The beacon transmitting device 300 constantly (or periodically) transmits a beacon. A beacon is a signal including an identifier (or ID). In the following, an example will be described in which there are multiple facilities E in the store S, but there may be only one facility E in the store S. The facility E is, for example, a full-length mirror (or stand mirror) or a fitting room. The beacon transmitting device 300 (e.g., 300-1) installed in the full-length mirror transmits a beacon including an identifier indicating the full-length mirror (hereinafter referred to as a "full-length mirror identifier"). Furthermore, the beacon transmitting device 300 (e.g., 300-2) installed in the fitting room transmits a beacon including an identifier indicating the fitting room (hereinafter referred to as a "fitting room identifier"). The beacon transmitting device 300 installed in the facility E transmits a beacon including an identifier indicating what type of facility the facility E is.

[0021] The camera device 750 is installed in the store S and captures images of the user's situation inside the store. In the following, an example in which the camera device 750 is installed near the display zone Z will be described, but the camera device 750 may also be installed in a location other than near the display zone Z, such as near the equipment E. The camera device 750 is connected to the network NW via a wired or wireless line. The camera device 400 transmits the captured image as image information to the analysis device 500 via the network NW.

[0022] The user terminal device 400 is a terminal device held or used by a user. Here, a user is a customer who can purchase a product P in the store S. Hereinafter, the terms user and customer may be used interchangeably. The user terminal device 400 can be connected to a network NW via a wireless line. The user terminal device 400 can communicate with the analysis device 500 via the network NW. The user terminal device 400 is a portable communication terminal device. Specifically, the user terminal device 400 is a smartphone, a tablet terminal, a wearable terminal, or the like. A program that can be used in the store S may be installed in the user terminal device 400. The user can receive various services within the store S via the user terminal device 400 with the program installed.

[0023] The analysis device 500 is an analysis device that analyzes the behavior of a user U in the user's store S. The analysis device 500 is connected to a network NW via a wired or wireless line and is capable of communicating with a user terminal device 400 and a camera device 750 via the network NW. Although an example in which the analysis device 500 is located outside the store S will be described below, the analysis device 500 may also be located inside the store S. The analysis device 500 may also be a cloud server. A cloud server is a server that can provide computer resources in the form of a service. The analysis device 500 may provide computer resources to the user terminal device 400 and the camera device 750 as a cloud server. The analysis device 500 may be a dedicated server or a general-purpose computer on which an analysis program is installed.

[0024] An external server 600 exists outside the analysis system 10. The external server 600 is connected to the user terminal device 400 and the analysis device 500 via a network NW. The external server 600 holds user attribute information representing user attributes. The external server 600 also holds product attribute information representing product attributes. In response to a request from the analysis device 500, the external server 600 transmits the user attribute information and product attribute information to the analysis device 500. The external server 600 may be a management server that manages the user attribute information and product attributes. The external server 600 may also be physically separated into a first management server that manages the user attribute information and a second management server that manages the product attribute information.

[0025] (An example of an application scenario for the analysis system) 2 and 3 are diagrams showing an example of an application scenario of the analysis system 10 according to the first embodiment. As shown in Fig. 3, the appliance communication device 100 and the beacon transmission device 300 function as a behavior acquisition device 700 (or a behavior acquisition system) that acquires information about the behavior of a user U. The behavior acquisition device 700 includes the appliance communication device 100 and the beacon transmission device 300.

[0026] As shown in Fig. 2, a user U carrying a user terminal device 400 enters a store S. In the store S, a plurality of sets of products P and holding devices H are arranged on a hanger rack L.

[0027] First, assume that a user U selects an item P of interest from among multiple items P on a clothes rack L, picks up the selected item P, looks at the price tag of the item P, and removes the holding device H from the clothes rack L.

[0028] In such a case, as shown in FIG. 3 , the appliance communication device 100 attached to the holding appliance H acquires posture information of the holding appliance H according to the user U's behavior with respect to the product P and the holding appliance H. The posture information is information that represents the posture of the holding appliance H. The posture information can take different values ​​according to the user U's behavior. Therefore, the posture information may be an example of information regarding the user U's behavior with respect to the product P.

[0029] The appliance communication device 100 has a product tag reader, and the product identifier written in the product tag 200 is read in advance by the product tag reader. The appliance communication device 100 acquires the product identifier.

[0030] Then, the appliance communication device 100 transmits a beacon (first beacon) including the posture information and the product identifier. The user terminal device 400 receives the beacon. The user terminal device 400 extracts the posture information and the product identifier from the beacon and transmits the posture information and the product identifier to the analysis device 500. At this time, the user terminal device 400 adds the member identifier (member ID or user identification information) of the user U to the beacon and transmits it.

[0031] Secondly, as shown in FIG. 2, a case is assumed in which a user U holds a product P and a holding tool H and approaches a full-length mirror E1 or a fitting room E2.

[0032] In such a case, as shown in FIG. 3 , the user terminal device 400 can receive a beacon (second beacon) transmitted from a beacon transmitting device 300-1 provided in the full-length mirror E1. Alternatively, the user terminal device 400 can receive a beacon (second beacon) transmitted from a beacon transmitting device 300-2 provided in the fitting room E2. The second beacon includes location information indicating the location where the equipment E is installed. The beacon transmitted from the beacon transmitting device 300-1 provided in the full-length mirror E1 includes different location information from the beacon transmitted from the beacon transmitting device 300-2 provided in the fitting room E2. Therefore, the location information can be used to detect the behavior of the user U, such as the user U bringing the product P to the full-length mirror E1 or the user U bringing the product P to the fitting room E2. The location information may be an example of information related to the user U's behavior regarding the product P. In such a case, the user terminal device 400 can save the time at which the first beacon and the second beacon were received and transmit them to the analysis device 500 at an appropriate timing. Transmission at an appropriate timing also enables intermittent transmission. The user terminal device 400 can transmit the posture information and product identifier included in the first beacon and the location information included in the second beacon to the analysis device 500 at the same time. Even in such a case, the user terminal device 400 adds the member identifier of the user U and transmits them.

[0033] Third, the camera device 750 can capture images of the user U's behavior in the store S and transmit the captured images to the analysis device 500 as image information. The analysis device 500 can detect a specific behavior of the user U based on the image information using an AI function. That is, the analysis device 500 stores image information of the user U performing a specific behavior in memory as training data, and performs deep learning using the training data and the image information received from the camera device 750 to detect the specific behavior of the user U. As a result, for example, the analysis device 500 can detect the specific behavior of the user U, such as "checking the fabric," "looking at the price tag," and / or "trying on the product P on the spot." The analysis device 500 may detect the specific behavior with respect to the product P having the product ID based on the timing of receiving the product ID from the user terminal device 400 and the timing of receiving the image information from the camera device 750. As a result, for example, the analysis device 500 can detect the specific behavior with respect to the product P, such as "checking the fabric of the product P," "looking at the price tag of the product P," and / or "trying on the product P on the spot."

[0034] The camera device 750 may have a detection function for detecting a predetermined behavior of the user U. That is, the camera device 750 may detect a predetermined behavior of the user U, such as "checking the fabric," "looking at the price tag," and / or "trying on clothes on the spot," from the acquired image information, and transmit information about the predetermined behavior of the user U to the analysis device 500 as an analysis result.

[0035] 3 illustrates an example in which the camera device 750 is included in the behavior acquisition device 700, but the camera device 750 may be included in a system (e.g., an imaging system) other than the analysis system 10. In this case, the analysis device 500 may detect a predetermined behavior of the user U based on image information acquired from the other system.

[0036] The analysis device 500 acquires information about the behavior of the user U in the store S with respect to the product P, based on the information (posture information and product ID) included in the first beacon and the information (location information) included in the second beacon received from the user terminal device 400. The analysis device 500 can also detect a predetermined behavior of the user U in the store S, based on image information acquired from the behavior acquisition device 700 (or the camera device 750). The image information may be an example of information about behavior.

[0037] For example, the analysis device 500 may detect user U's behavior of "pulling product P" and / or "holding product P" based on posture information, a product identifier, and a membership identifier. Furthermore, the analysis device 500 may detect user U's behavior of "bringing product P to the full-length mirror E1" and "bringing product P to the fitting room E2" based on location information, a product identifier, and a membership identifier. Furthermore, the analysis device 500 may detect user U's behavior of "checking the fabric," "looking at the price tag," and / or "trying on the item on the spot" based on image information acquired from the camera device 750.

[0038] In the first embodiment, the analysis device 500 estimates the degree of interest of the user U in a product P based on information about the user U's behavior regarding the product P in the store S. The degree of interest indicates, for example, the degree of association between the user U's behavior regarding the product P in the store S and the user U's purchase of the product P. A higher degree of interest may indicate a behavior with a higher probability of purchase, and a lower degree of interest may indicate a behavior with a lower probability of purchase.

[0039] In this way, by estimating the interest level using the analysis device 500, it is possible to, for example, encourage a store clerk to serve the behavior of a user U whose interest level is higher than a certain level, thereby leading to a purchase of the product. Also, by estimating the interest level using the analysis device 500, it is possible to, for example, suggest another product P to a user U whose interest level is lower than a certain level, thereby leading to a purchase of the product. Furthermore, by estimating the interest level using the analysis device 500, it is possible to use the relationship between the user U's behavior toward the product P and the interest level for marketing purposes. For example, it may be determined that the product P is a popular product simply because the number of times the user "possessed the product P" was performed is higher than a certain level. However, by evaluating the product P using the interest level as an index, it is possible to determine that the product P is not a particularly popular product, which can be used for marketing purposes.

[0040] (Configuration example of appliance communication device) Next, a description will be given of an example of the configuration of the appliance communication device 100 according to the first embodiment. As described above, the appliance communication device 100 is attached to the holding appliance H that holds the product P.

[0041] FIG. 4 is a diagram illustrating an example of the configuration of the appliance communication device 100 according to the first embodiment.

[0042] As shown in FIG. 4, the appliance communication device 100 includes a beacon transmitting unit 110, a product tag reader 120, a control unit 130, a detection unit 140, and a power supply unit 150.

[0043] The beacon transmitting unit 110 transmits a beacon (first beacon) under the control of the control unit 130. When the beacon transmitting unit 110 is instructed by the control unit 130 to transmit a beacon, the beacon transmitting unit 110 generates a beacon including information received from the control unit 130 and transmits the beacon. In one embodiment, the beacon transmitting unit 110 transmits a beacon including a product identifier read by the product tag reader 120 and posture information acquired by the detection unit 140.

[0044] In the following description, a beacon will be described as a BT beacon based on the Bluetooth (registered trademark) standard, but a beacon based on a standard other than Bluetooth may also be used.

[0045] In the following, an example will be described in which the appliance communication device 100 transmits a beacon using the beacon transmitting unit 110, but the appliance communication device 100 may use a signal other than a beacon. For example, the appliance communication device 100 may use a signal based on a short-range wireless communication method such as UWB (Ultra Wide Band) or NFC (Near Field Communication). In this case, the appliance communication device 100 may have a short-range wireless communication unit instead of the beacon transmitting unit 110.

[0046] Product tag reader 120, under the control of control unit 130, reads the product identifier from product tag 200 and outputs the read product identifier to control unit 130. Product tag reader 120 may read the product identifier from product tag 200 by a store clerk at store S bringing product tag 200 close to product tag reader 120.

[0047] The control unit 130 controls various functions of the appliance communication device 100. The control unit 130 has at least one memory 132 and at least one processor 131 electrically connected to the memory 132. The memory 132 includes a volatile memory and a non-volatile memory, and stores information used for processing in the processor 131 and programs executed by the processor 131. The processor 131 may perform various processes by executing the programs stored in the memory 132. In one embodiment, the memory 132 stores product identifiers read by the product tag reader 120. The memory 132 may also store posture information detected by the detection unit 140. The information stored in the memory 132 is read out as appropriate under the control of the processor 131. Note that in the following operation examples, the operations or processes performed in the appliance communication device 100 may be mainly performed by the control unit 130.

[0048] The detection unit 140 detects the posture of the holding device H under the control of the control unit 130. When the detection unit 140 detects the posture of the holding device H, it generates posture information. The detection unit 140 may include a sensor capable of detecting a change in a physical quantity according to the posture of the holding device H. An example of such a sensor is an acceleration sensor, but it is not limited to this. The detection unit 140 outputs the posture information to the control unit 130. The control unit 130 saves the time when it received the posture information, and outputs a beacon generation instruction to the beacon transmission unit 110 at an appropriate timing, and also outputs the posture information and the product identifier to the beacon transmission unit 110. Outputting the generation instruction at an appropriate timing enables intermittent transmission of beacons.

[0049] The power supply unit 150 supplies power to each unit of the appliance communication device 100 under the control of the control unit 130. The power supply unit 150 may be a battery (or a secondary battery) that can be repeatedly charged and discharged.

[0050] (Example of beacon transmitter configuration) Next, a configuration example of the beacon transmitting device 300 will be described.

[0051] FIG. 5 is a diagram illustrating an example of the configuration of the beacon transmitting device 300 according to the first embodiment.

[0052] As shown in FIG. 5, the beacon transmitting device 300 includes a beacon transmitting unit 310, a control unit 330, and a power supply unit 350.

[0053] The beacon transmitter 310 transmits a beacon (second beacon) under the control of the controller 330. In one embodiment, the beacon transmitter 310 transmits a beacon including location information. The location information indicates the location where the facility E is installed. For example, in the case of the beacon transmitter 300-1 installed in the full-length mirror E1, the location information indicates the location of the full-length mirror E1. Furthermore, in the case of the beacon transmitter 300-2 installed in the fitting room E2, the location information indicates the location of the fitting room E2.

[0054] The control unit 330 controls various functions of the beacon transmitting device 300. The control unit 330 has at least one memory 332 and at least one processor 331 electrically connected to the memory 332. The memory 332 includes a volatile memory and a non-volatile memory, and stores information used for processing in the processor 331 and programs executed by the processor 331. The processor 331 may perform various processes by executing the programs stored in the memory 332. In one embodiment, the memory 332 stores location information. The information stored in the memory 332 is read out as appropriate under the control of the processor 331.

[0055] The power supply unit 350 supplies power to each unit of the beacon transmitting device 300 under the control of the control unit 330. The power supply unit 350 may be a battery (or a secondary battery) that can be repeatedly charged and discharged.

[0056] (Example of user terminal device configuration) Next, an example of the configuration of the user terminal device 400 will be described.

[0057] FIG. 6 is a diagram illustrating an example of the configuration of the user terminal device 400 according to the first embodiment.

[0058] As shown in FIG. 6, the user terminal device 400 includes a beacon receiving unit 410, a wireless communication unit 420, a control unit 430, and a display unit 440.

[0059] The beacon receiving unit 410 receives a beacon (first beacon) transmitted from the appliance communication device 100 under the control of the control unit 430. The beacon receiving unit 410 also receives a beacon (second beacon) transmitted from the beacon transmitting device 300. The beacon receiving unit 410 extracts information included in the beacon and outputs the information to the control unit 430.

[0060] The wireless communication unit 420 is connected to the network NW via a wireless line under the control of the control unit 430, and is capable of communicating with the analysis device 500 via the network NW. The wireless communication unit 420 may perform communication using a wireless communication method based on the wireless LAN standard, or may perform communication using a wireless communication method based on a cellular system. Upon receiving the posture information and product identifier included in the first beacon, and the location information and member identifier included in the second beacon from the control unit 430, the wireless communication unit 420 transmits this information to the analysis device 500.

[0061] The posture information, product identifier, location information, and member identifier may be collectively referred to as "information regarding the user U's behavior" with respect to the product P. The "information regarding the behavior" includes the posture information, product identifier, location information, and member identifier.

[0062] The control unit 430 controls various functions of the user terminal device 400. The control unit 430 has at least one memory 432 and at least one processor 431 electrically connected to the memory 432. The memory 432 includes a volatile memory and a non-volatile memory, and stores information used for processing by the processor 431 and programs executed by the processor 431. The processor 431 may perform various processes by executing the programs stored in the memory 432. Note that in the following operation examples, the operations or processes performed by the user terminal device 400 may be mainly performed by the control unit 430. When the control unit 430 receives information from the beacon receiving unit 410, it reads the member identifier from the memory 432 and outputs the information received from the beacon receiving unit 410 and the member identifier to the wireless communication unit 420 as information related to the activity.

[0063] (Example of analytical equipment configuration) Next, an example of the configuration of the analysis device 500 will be described.

[0064] FIG. 7 is a diagram illustrating an example of the configuration of an analysis device 500 according to the first embodiment.

[0065] As shown in FIG. 7, the analysis device 500 includes a communication unit 510 and a control unit 530.

[0066] The communication unit 510 is connected to the network NW via a wired or wireless line. The communication unit 510 receives information about the behavior transmitted from the user terminal device 400 and outputs the received information to the control unit 530.

[0067] The control unit 530 controls various functions of the analysis device 500. The control unit 530 has at least one memory 532 and at least one processor 531 electrically connected to the memory 532. The processor 531 may perform various processes by executing programs stored in the memory 532. In the first embodiment, the control unit 530 estimates the user U's degree of interest in the product P based on information related to behavior. Note that in the following operation examples, the operations or processes performed in the analysis device 500 may be performed in the control unit 530 of the analysis device 500.

[0068] (Operation example according to the first embodiment) Next, an example of operation according to the first embodiment will be described.

[0069] In the first embodiment, an example will be described in which the control unit 530 of the analysis device 500 estimates the degree of interest by applying the behavior of a user U with respect to a product P in a store S to the degree of interest in the product P. Note that in the operation example according to the first embodiment, the analysis device 500 will be described as acquiring information about the behavior from the user terminal device 400.

[0070] FIG. 8 is a diagram illustrating an example of operation according to the first embodiment.

[0071] As shown in FIG. 8, in step S10, the control unit 530 of the analyzer 500 starts processing.

[0072] In step S11, the control unit 530 confirms (or verifies) the degree of association between the user U's behavior in the store S regarding the product P and the user U's purchase of the product P.

[0073] In step S12, the control unit 530 sets the degree of interest for each behavior.

[0074] FIG. 9(A) is a diagram showing an example of the relationship between each behavior and the degree of interest. The hypothesis shown in FIG. 9(A) is set between each behavior and the degree of interest. As shown in FIG. 9(A), the higher the degree of interest, the closer the behavior is to purchasing, and the lower the degree of interest, the further away the behavior is from purchasing. As shown in FIG. 9(A), the behavior of "taking the product to the fitting room" is closer to "purchase" than the behavior of "pulling the product," so the degree of interest is greater for the latter than for the former. For example, as shown in FIG. 9(A), the control unit 530 may confirm in step S11 that there are different levels of interest for each behavior.

[0075] FIG. 9(B) shows an example of a model constructed for the hypothesis shown in FIG. 9(A). As shown in FIG. 9(B), each behavior of user U in store S is assigned to a respective index of interest level. As shown in FIG. 9(B), the degree of interest may be expressed as "none," "low," "medium," or "high," or may be expressed as a numerical value. In step S12, the control unit 530 may assign each behavior to a respective index of interest level.

[0076] The control unit 530 may store, for example, the relationship shown in FIG. 9(A) or the relationship shown in FIG. 9(B) in the memory 532 as a table.

[0077] Returning to FIG. 7, in step S13, control unit 530 ends the series of processes.

[0078] Thereafter, each time the control unit 530 acquires (or detects) information regarding an action from the user terminal device 400, the control unit 530 may estimate the degree of interest corresponding to the action by using a table (e.g., Figure 9(A) or Figure 9(B)) stored in the memory 532.

[0079] The analysis device 500 may transmit the estimated degree of interest to a salesperson terminal device owned by a salesperson in the store S. The salesperson can serve the user U based on the degree of interest displayed on the salesperson terminal device. The analysis device 500 may also transmit the behavior and the degree of interest to a server of a manufacturer that produces and / or sells the product P. The relationship between the behavior and the degree of interest can be used for marketing.

[0080] [Second embodiment] Next, a second embodiment will be described, focusing on the differences from the first embodiment.

[0081] In the first embodiment, an example using the interest degree is described. In the second embodiment, an example using the purchase probability is described. That is, in the second embodiment, the purchase probability of the user U for the product P is obtained by further taking into account the user attribute information representing the attributes of the user U and the product attribute information representing the attributes of the product P in addition to the user U's behavior in the store S regarding the product P.

[0082] Specifically, first, the analysis device (e.g., analysis device 500) receives user attribute information and product attribute information from an external server (e.g., external server 600). Second, the analysis device inputs information about behavior, user attribute information, and product attribute information into a learning model, and obtains a purchase probability from the learning model.

[0083] For example, it is assumed that the probability of purchasing a product P varies depending on the attributes of the user U. The analysis device 500 according to the second embodiment can acquire a purchase probability that takes such assumptions into account, making it possible to suggest products according to the attributes of the user U, which may lead to a purchase of the product. Furthermore, the analysis device 500 can transmit user attribute information and product attribute information along with the purchase probability to a manufacturer's server, thereby enabling this information to be utilized for marketing. For example, it is possible to acquire the purchase probability for each attribute of the user U for a certain behavior m, which can be further utilized for marketing.

[0084] (Example of operation according to the second embodiment) Next, an example of operation according to the second embodiment will be described.

[0085] In the second embodiment, similarly to the first embodiment, the analysis device 500 can acquire (or detect) information about the behavior of the user U with respect to the product P in the store S from the user terminal device 400 (FIG. 3). The analysis device 500 can also acquire user attribute information and product attribute information from the external server 600 (FIG. 3). The external server 600 stores, for example, user attribute information for each member ID and product attribute information for each product ID. The analysis device 500 can acquire user attribute information from the external server 600 using the member ID acquired from the user terminal device 400. The analysis device 500 can also acquire product attribute information from the external server 600 using the product ID acquired from the user terminal device 400 (via the behavior acquisition device 700).

[0086] FIG. 10 is a diagram illustrating an example of operation according to the second embodiment.

[0087] As shown in FIG. 10, in step S20, the control unit 530 of the analysis device 500 starts the process.

[0088] In step S21, the control unit 530 inputs information related to behavior, user attribute information, and product attribute information.

[0089] FIG. 11 is a diagram illustrating examples of user attribute information and product attribute information according to the second embodiment. As illustrated in FIG. 11, the user attribute information includes gender and age. Age may be classified according to the manufacturer's customer base. Product attribute information includes product genre, product color, and product price. Specific classification of each attribute may depend on the manufacturer's classification. As illustrated in FIG. 11, the behavioral information is divided into four groups according to the grouping shown in FIG. 9(B). However, the behavioral information may also use the grouping shown in FIG. 9(A). Since the behavioral information may differ depending on the store S, behavioral information other than the behaviors shown in FIGS. 9(A) and 9(B) may be used, or a portion of the behavioral information shown in FIGS. 9(A) and 9(B) may be used. The control unit 530 may store the input information (behavioral information, user attribute information, and product attribute information) in the memory 532.

[0090] In step S22, the control unit 530 stores a certain amount of information (information about behavior, user attribute information, and product attribute information) in the memory 532.

[0091] In step S23, the control unit 530 generates a learning model from the information on the behavior, the user attribute information, and the product attribute information.

[0092] As described in the first embodiment, there is a certain relationship between "behavior" and "purchase." Furthermore, as described above, it is easily conceivable that, by taking user attribute information and product attribute information into account, it is possible to grasp a more detailed relationship between "behavior" and "purchase" (for example, the relationship between "behavior" and "purchase" according to the attributes of user U) in this relationship. That is, since it is assumed that the purchase probability is correlated with information about user U's behavior, the user attribute information, and the product attribute information, it is possible to estimate the purchase probability from the information about behavior, the user attribute information, and the product attribute information. Therefore, the control unit 530 can create a learning model from the information about behavior, the user attribute information, and the product attribute information, and acquire the purchase probability from the information about behavior, the user attribute information, and the product attribute information using the learning model.

[0093] FIG. 12 is a diagram showing an example of a learning model according to the second embodiment. In the second embodiment, an example will be described in which a Bayesian network is used as the learning model. A Bayesian network is a network (i.e., a weighted graph) in which the strength of the causal relationship is determined from the magnitude of the conditional probability and the causal relationships between a large number of events are graphically organized. Each node corresponds to information acquired by the analysis device 500. Furthermore, transitions between each node are possible using conditional probabilities. In the Bayesian network shown in FIG. 12, the conditional probability of "purchase" is ultimately expressed.

[0094] Here, a specific example of generating a learning model will be described.

[0095] FIG. 13 is a diagram showing an example of learning data according to the second embodiment. Data used when training a learning model is called learning data. In the second embodiment, information about behavior, user attribute information, product attribute information, and purchase probability are used as the learning data. However, in FIG. 13, of these, product attribute information ("color" and "genre"), user attribute information ("class" (or gender)), and purchase probability ("T" = purchased. "F" = not purchased) are shown as the learning data. Furthermore, FIG. 14 shows an example of learning data when user U takes a certain behavior m (a certain behavior represented by information about the behavior, for example, the behavior of "holding product P").

[0096] FIG. 14 shows an example of data included in a learning model trained using the learning data shown in FIG.

[0097] In Figure 14, "probability value" represents the purchase probability for behavior m when the product attribute information of product P and the user attribute information of user U are satisfied. This purchase probability represents the posterior probability that takes product attribute information and user attribute information into consideration. On the other hand, the purchase probability for behavior m that does not take product attribute information and user attribute information into consideration is the prior probability. This purchase probability is called the "marginal probability." The "lift value" in Figure 14 represents the probability value (posterior probability) / marginal probability (prior probability). Using a lift value of 1 as the base, the difference between the probability value "0.547109695" at this base and each probability value is the "probability difference." For example, for an item ranked "1," the probability value is "1," so when the difference from the probability value at the base is calculated, the value "0.452890305" shown in the "probability difference" is obtained.

[0098] As shown in Figure 14, when the product attribute is "jacket" and "white" and the user attribute is "female," the purchase probability is "1" (=100%). On the other hand, when the same product attribute and the user attribute is "male," the purchase probability is "0" (=0%).

[0099] FIG. 15 shows a summary of the attributes and probabilities shown in FIG. 14. That is, the attributes "jacket," "white," and "female" have a 100% purchase probability. In this case, the attributes "jacket" and "white" are factors that led user U ("female") to purchase product P. The factors that led user U to purchase product P may be referred to as positive factors. In this case, the positive factors are "jacket" and "white." In this way, the positive factors may include product attribute information of product P.

[0100] On the other hand, the attributes "jacket," "white," and "male" have a purchase probability of 0%. In this case, "jacket" and "white" are the reasons why user U ("male") did not purchase product P. The reasons why user U did not purchase product P may be referred to as negative factors. In this case, the negative factors are "jacket" and "white." The negative factors may also include product attribute information of product P.

[0101] In the second embodiment, when the control unit 530 obtains the purchase probability from the learning model, it can obtain positive or negative factors from the learning model. An attribute with a probability value higher than the reference probability value ("0.547109695") can be a positive factor. On the other hand, an attribute with a probability value lower than the reference probability value can be a negative factor. The control unit 530 may output product attribute information with a probability value higher than the reference probability value as a positive factor. Furthermore, the control unit 530 may output product attribute information with a probability value lower than the reference probability value as a negative factor.

[0102] Returning to FIG. 10, after generating a learning model (step S23), the control unit 530 inputs information related to behavior, user attribute information, and product attribute information in step S24.

[0103] In step S25, the control unit 530 inputs information related to the behavior, user attribute information, and product attribute information into the learning model and acquires a purchase probability from the learning model. The control unit 530 can also acquire positive or negative factors from the learning model. The control unit 530 may transmit the acquired purchase probability to a store clerk terminal held by the store clerk. Alternatively, the control unit 530 may transmit the positive or negative factors to the store clerk terminal. This makes it possible to promote the customer service behavior of the store clerk based on the purchase probability, leading to the purchase of product P. Furthermore, the control unit 530 may transmit the purchase probability to a server used by the manufacturer. This makes it possible to utilize the purchase probability for marketing.

[0104] In step S26, control unit 530 ends the series of processes.

[0105] [Other embodiments] In the above-described embodiment, an example has been described in which the appliance communication device 100 is attached to the holding appliance H that holds the product P. The appliance communication device 100 may be attached to the product P. Specifically, the appliance communication device 100 may be attached to the price tag of the product P. Alternatively, the appliance communication device 100 may be attached to the product tag 200. Alternatively, the appliance communication device 100 may be directly attached to the front (or back) of the product P. In this case, the appliance communication device 100 may transmit posture information of the product P instead of the posture information of the holding appliance H. The analysis device 500 may detect information about the behavior of the user U based on the posture information of the product P, similar to the posture information of the holding appliance H. Alternatively, similar to the posture information of the holding appliance H, the posture information of the product P may represent information about the behavior of the user U in the store S with respect to the product P.

[0106] Furthermore, a program (e.g., a customer service assistance program) may be provided that causes a computer to execute each process (or each operation) described in each of the above-described embodiments. The program can be installed on a computer using a computer-readable medium. Here, the computer-readable medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, and may be, for example, a recording medium such as a CD-ROM or a DVD-ROM. Such a recording medium may be included in the control unit 130 of the appliance communication device 100, the control unit 430 of the user terminal device 400, and the control unit 530 of the analysis device 500. Each of the control units 130, 430, and 530 may read the program from the recording medium and execute the program to realize the function (or process, or operation) described in the above-described embodiments.

[0107] Although the embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to the above, and various design changes can be made without departing from the spirit of the invention. Furthermore, the above-described embodiments, operations, or processes can be combined as appropriate within a consistent range.

[0108] (Addendum) Supplementary notes are provided below, but the supplementary notes are not limited to the embodiments, and do not limit the embodiments.

[0109] (Appendix 1) A behavior acquisition device; An analysis system having an analysis device, the behavior acquisition device transmits information about the user's behavior in the store regarding the product; the analysis device receives information about the behavior from the behavior acquisition device, and estimates a degree of interest of the user in the product based on the information about the behavior; The interest level indicates the degree of association between the behavior and the user's purchase of the product. Analysis system.

[0110] (Appendix 2) Further, the system has a user terminal device, the behavior acquisition device transmits a beacon including information about the user's behavior in the store regarding the product; The user terminal device receives the beacon and transmits information about the behavior included in the beacon to the analysis device. 1. The analytical system described in Appendix 1.

[0111] (Appendix 3) the behavior acquisition device includes an appliance communication device attached to a holding appliance for holding the product and a beacon transmission device provided in a facility within the store; the tool communication device transmits a first beacon including attitude information representing an attitude of the holding tool; the beacon transmitting device transmits a second beacon including location information indicating a location where the equipment is installed; the user terminal device receives the first beacon and the second beacon, and transmits the attitude information and position information to the analysis device; The analysis device receives the posture information and the position information, and acquires information about the behavior based on the posture information and the position information. 10. The analytical system of claim 1 or 2.

[0112] (Appendix 4) the degree of interest represents a probability of purchasing the product in response to the behavior; the analysis device receives user attribute information representing attributes of the user and product attribute information representing attributes of the product from an external server; The analysis device inputs the behavior information, the user attribute information, and the product attribute information into a learning model, and obtains the purchase probability from the learning model. An analysis system according to any one of Supplementary Note 1 to Supplementary Note 3.

[0113] (Appendix 5) The analysis device outputs, from the learning model, either positive factor information indicating a factor that caused the user to purchase the product or negative factor information indicating a factor that caused the user not to purchase the product. An analysis system according to any one of Supplementary Note 1 to Supplementary Note 4.

[0114] (Appendix 6) The positive factor information and the negative factor information include the product attribute information An analysis system according to any one of Supplementary Note 1 to Supplementary Note 5.

[0115] (Appendix 7) The analysis device receiving user identification information from the user terminal device, and receiving the user attribute information corresponding to the user identification information from the external server; receiving product identification information from the appliance communication device via the user terminal device, and receiving the product attribute information corresponding to the product identification information from the external server; An analysis system according to any one of Supplementary Note 1 to Supplementary Note 6.

[0116] (Appendix 8) the behavior acquisition device includes a price tag, a product tag, or a string for the product tag of the product, or an appliance communication device attached to the product, and a beacon transmission device provided in equipment within the store; the appliance communication device transmits a first beacon including posture information representing a posture of the attached component or product; the beacon transmitting device transmits a second beacon including location information indicating a location where the equipment is installed; the user terminal device receives the first beacon and the second beacon, and transmits the attitude information and position information to the analysis device; The analysis device receives the posture information and the position information, and acquires information about the behavior based on the posture information and the position information. An analysis system according to any one of Supplementary Note 1 to Supplementary Note 7.

[0117] (Appendix 9) In the analytical device, a communication unit that receives information about a user's behavior in a store with respect to a product from the behavior acquisition device; a control unit that estimates a degree of interest of the user in the product based on information about the behavior, The interest level indicates the degree of association between the behavior and the user's purchase of the product. Analyzer.

[0118] (Appendix 10) An analysis method in an analysis system having a behavior acquisition device and an analysis device, a step of transmitting information about the user's behavior regarding the product in the store by the behavior acquisition device; the analysis device receiving information about the behavior from the behavior acquisition device, and estimating a degree of interest of the user in the product based on the information about the behavior; The interest level indicates the degree of association between the behavior and the user's purchase of the product. Analysis method. [Explanation of symbols]

[0119] 10: Analysis system 100: Instrument communication device 110: Beacon transmitter 120: Product tag reader 130: Control unit 140: Detection unit 200: Product tag 300: Beacon transmitter 400: User terminal device 410: Beacon receiving unit 420: Wireless communication unit 430: Control unit 500: Analyzer 510: Communication Department 530: Control unit 600: External server 700: Behavior acquisition device H: Holding device L: Hanger rack P: Product S: Store U: User Z: Display Zone

Claims

1. A behavior acquisition device; An analysis system having an analysis device, the behavior acquisition device transmits information about the user's behavior in the store regarding the product; the analysis device receives information about the behavior from the behavior acquisition device, and estimates a degree of interest of the user in the product based on the information about the behavior; The interest level indicates the degree of association between the behavior and the user's purchase of the product. Analysis system.

2. Further, the system has a user terminal device, the behavior acquisition device transmits a beacon including information about the user's behavior in the store regarding the product; The user terminal device receives the beacon and transmits information about the behavior included in the beacon to the analysis device. The analytical system of claim 1 .

3. the behavior acquisition device includes an appliance communication device attached to a holding appliance for holding the product and a beacon transmission device provided in equipment within the store; the tool communication device transmits a first beacon including attitude information representing an attitude of the holding tool; The beacon transmitting device transmits a second beacon including location information indicating a location where the equipment is installed; the user terminal device receives the first beacon and the second beacon, and transmits the attitude information and position information to the analysis device; The analysis device receives the posture information and the position information, and acquires information about the behavior based on the posture information and the position information. The analytical system according to claim 2 .

4. the degree of interest represents a probability of purchasing the product in response to the behavior; the analysis device receives user attribute information representing attributes of the user and product attribute information representing attributes of the product from an external server; The analysis device inputs the behavior information, the user attribute information, and the product attribute information into a learning model, and obtains the purchase probability from the learning model. The analytical system of claim 1 .

5. The analysis device outputs, from the learning model, either positive factor information indicating a factor that caused the user to purchase the product or negative factor information indicating a factor that caused the user not to purchase the product. The analysis system according to claim 4.

6. The positive factor information and the negative factor information include the product attribute information The analytical system according to claim 5 .

7. The analysis device receiving user identification information from the user terminal device, and receiving the user attribute information corresponding to the user identification information from the external server; receiving product identification information from the appliance communication device via the user terminal device, and receiving the product attribute information corresponding to the product identification information from the external server; The analysis system according to claim 4.

8. the behavior acquisition device includes a price tag, a product tag, or a string for the product tag of the product, or an appliance communication device attached to the product, and a beacon transmission device provided in equipment within the store; the appliance communication device transmits a first beacon including posture information representing a posture of the attached component or product; The beacon transmitting device transmits a second beacon including location information indicating a location where the equipment is installed; the user terminal device receives the first beacon and the second beacon, and transmits the attitude information and position information to the analysis device; The analysis device receives the posture information and the position information, and acquires information about the behavior based on the posture information and the position information. The analytical system according to claim 2 .

9. In the analytical device, a communication unit that receives information about a user's behavior in a store with respect to a product from the behavior acquisition device; a control unit that estimates a degree of interest of the user in the product based on information about the behavior, The interest level indicates the degree of association between the behavior and the user's purchase of the product. Analyzer.

10. An analysis method in an analysis system having a behavior acquisition device and an analysis device, a step of transmitting information about the user's behavior regarding the product in the store by the behavior acquisition device; the analysis device receiving information about the behavior from the behavior acquisition device, and estimating a degree of interest of the user in the product based on the information about the behavior; The interest level indicates the degree of association between the behavior and the user's purchase of the product. Analysis method.

Images