Purchaser class analysis support device and program

Abstract

To provide a purchaser class analysis support device and a program capable of grasping a purchaser class in more detail, compared to a case of grasping a purchaser class by performing classification on data showing purchase results according to purchasers of the same attribute.SOLUTION: A purchaser class analysis support device 10 includes an acquisition unit 11A that acquires data which is about purchasers who purchased a target item and is of a plurality of original data groups obtained under different conditions, an integration unit 11B that integrates the data of the plurality of original data groups acquired by the acquisition unit 11A by using a connection degree which indicates the intensity of connection between the plurality of original data groups, and a presentation unit 11C that presents purchaser class information indicating a purchaser class of the target item by using an integration result obtained by the integration unit 11B.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a purchasing group analysis support device and a program. [Background technology]

[0002] Conventionally, the following techniques have been available as techniques that can contribute to the analysis of purchasing groups in areas such as commercial districts, tourist destinations, and urban areas where purchasing activities for various products and services take place.

[0003] Patent Document 1 discloses a purchasing situation analysis support device that aims to analyze at least one characteristic of a person's emotions and behavior patterns when carrying out purchasing activities.

[0004] This purchasing situation analysis support device includes an acquisition unit that acquires purchasing information including at least one of purchase items and purchase prices by a plurality of people in a space to be analyzed, acquires at least one of emotion information indicating an emotional state and behavior pattern information indicating a behavior pattern, and acquires attribute information indicating attributes of each of the plurality of people.The purchasing situation analysis support device includes a classification unit that classifies the purchasing information for each attribute indicated by the attribute information using each piece of information acquired by the acquisition unit, and classifies at least one of the emotion information and the behavior pattern information, and an association unit that associates the classification result of the purchasing information with the classification result of at least one of the emotion information and the behavior pattern information for each common attribute using the classification result by the classification unit. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2022-061882 Summary of the Invention [Problem to be solved by the invention]

[0006] However, the technology disclosed in Patent Document 1 can analyze at least one of the characteristics of a person's emotions and behavior patterns when making purchases, but it identifies purchasing demographics by classifying data showing purchase records into purchasers with the same attributes. Therefore, this technology cannot combine data that does not have the same attributes, and as a result, there is a problem in that it is not always possible to identify detailed purchasing demographics.

[0007] The present invention has been made in consideration of the above circumstances, and aims to provide a purchasing demographic analysis support device and program that can grasp purchasing demographics in more detail than when purchasing demographics are grasped by classifying data indicating purchasing history by purchasers with the same attributes. [Means for solving the problem]

[0008] The purchasing demographic analysis support device of the present invention as described in claim 1 comprises an acquisition unit that acquires data from a plurality of original data groups obtained under mutually different conditions, the data being related to purchasers who have purchased an object, a fusion unit that fuses the data from the plurality of original data groups using a degree of association indicating the strength of association between each of the plurality of original data groups acquired by the acquisition unit, and a presentation unit that presents purchasing demographic information indicating the purchasing demographic for the object, using the result of the fusion by the fusion unit.

[0009] According to the purchasing demographic analysis support device of the present invention as described in claim 1, data from multiple original data groups, which are data on purchasers who purchased an object and were obtained under mutually different conditions, is acquired, and the data from the multiple original data groups is fused using a degree of association indicating the strength of association between each of the acquired multiple original data groups, and the result of the fusion is used to present purchasing demographic information indicating the purchasing demographic for the object.As a result, even original data groups that do not have the same attributes can be fused according to the degree of association, making it possible to grasp the purchasing demographic in more detail than when grasping the purchasing demographic by classifying data indicating purchasing history by purchasers with the same attributes.

[0010] The purchasing demographic analysis support device of the present invention as described in claim 2 is the purchasing demographic analysis support device as described in claim 1, wherein the fusion unit derives the degree of association for each combination between the multiple original data groups, and fuses the data of the original data group with the combination having the highest overall score, which is the sum of the derived degrees of association.

[0011] According to the purchasing demographic analysis support device of the present invention as described in claim 2, by deriving the degree of association for each combination between multiple original data groups and fusing the data of the original data group with the combination having the highest overall score, which is the total value of the derived degrees of association, it is possible to more appropriately fuse the data of multiple original data groups compared to fusing the data of multiple original data groups without using the overall score.

[0012] The purchasing demographic analysis support device of the present invention as described in claim 3 is a purchasing demographic analysis support device as described in claim 1, wherein the original data group is a data group obtained by clustering data regarding purchasers who purchased the target item.

[0013] According to the purchasing demographic analysis support device of the present invention as described in claim 3, by making the original data group a data group obtained by clustering data related to purchasers who purchased the target product, it is possible to treat data belonging to each of multiple original data groups as similar data, and as a result, it is possible to more appropriately fuse data from multiple original data groups.

[0014] The purchasing demographic analysis support device of the present invention as described in claim 4 is the purchasing demographic analysis support device as described in claim 1, wherein the degree of coupling is a degree to which a machine learning model is constructed using data between each of the multiple original data groups, and the higher the estimation accuracy of the machine learning model, the higher the value becomes.

[0015] According to the purchasing demographic analysis support device of the present invention as described in claim 4, by constructing a machine learning model using data between each of a plurality of original data groups and setting the degree of coupling to a higher value as the estimation accuracy of the machine learning model is higher, it is possible to fuse data from a plurality of original data groups more accurately than when the above estimation accuracy is not used.

[0016] A purchasing demographic analysis support device according to the present invention as set forth in claim 5 is the purchasing demographic analysis support device as set forth in claim 1, in which the object is at least one of a product and a service.

[0017] According to the purchasing demographic analysis support device of the present invention as set forth in claim 5, by setting the target object to at least one of a product and a service, it is possible to grasp more detailed purchasing demographics for at least one of various products and services.

[0018] The program of the present invention as described in claim 6 causes a computer to execute a process of acquiring data from a plurality of original data groups obtained under mutually different conditions, fusing the data from the plurality of original data groups using a degree of association indicating the strength of association between each of the acquired plurality of original data groups, and presenting demographic information indicating the purchasing demographic for the object using the result of the fusion.

[0019] According to the program of the present invention as described in claim 6, data from multiple original data groups, which are data on purchasers who purchased an object and were obtained under mutually different conditions, is acquired, and the data from the multiple original data groups is fused using a degree of association indicating the strength of association between each of the acquired multiple original data groups, and the fusion result is used to present purchasing demographic information indicating the purchasing demographic for the object.As a result, even original data groups that do not have the same attributes can be fused according to the degree of association, making it possible to grasp the purchasing demographic in more detail than when grasping the purchasing demographic by classifying data indicating purchasing history by purchasers with the same attributes. Effect of the Invention

[0020] As described above, according to the present invention, it is possible to grasp purchasing demographics in more detail than when the purchasing demographics are grasped by classifying data indicating purchasing history into purchasers with the same attributes. [Brief description of the drawings]

[0021] [Figure 1] 1 is a block diagram showing an example of a hardware configuration of a purchasing group analysis support system according to an embodiment. [Diagram 2] 1 is a block diagram showing an example of a functional configuration of a purchasing group analysis support system according to an embodiment. [Diagram 3] FIG. 1 is a diagram for explaining a method for fusing data from a plurality of original data groups by the purchase layer analysis support system according to the embodiment, and is a schematic diagram showing an example of a data fusion state by a conventional technique. [Figure 4] FIG. 13 is a diagram for explaining a method for fusing data from multiple original data groups by a purchasing layer analysis support system according to an embodiment, and is a schematic diagram showing an example of a data fusion state according to the disclosed technology. [Diagram 5] FIG. 2 is a schematic diagram showing an example of a configuration of a target area information database according to the embodiment. [Figure 6] FIG. 2 is a schematic diagram showing an example of a configuration of a first base data group database according to the embodiment. [Figure 7] FIG. 4 is a schematic diagram showing an example of a configuration of a second base data group database according to the embodiment. [Figure 8] FIG. 2 is a schematic diagram showing an example of a configuration of a fusion information database according to the embodiment. [Figure 9] 11 is a flowchart illustrating an example of a purchasing group analysis support process according to the embodiment. [Figure 10] FIG. 13 is a diagram showing an example of the configuration of a district designation screen according to the embodiment. [Figure 11] 11 is a flowchart illustrating an example of a purchasing demographic information presentation process according to the embodiment. [Figure 12] 10 is a flowchart illustrating an example of a demographic information display process according to the embodiment. [Figure 13]FIG. 4 is a diagram showing an example of a configuration of an initial screen according to the embodiment. [Figure 14] FIG. 13 is a diagram showing an example of a configuration of a demographic information presentation screen according to the embodiment. [Figure 15] FIG. 13 is a diagram showing another example of the configuration of the demographic information presentation screen according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. In this embodiment, the present invention will be described as being applied to a purchasing demographic analysis support system including a purchasing demographic analysis support device configured by a server computer or the like, and a plurality of target user terminals, which are terminals used individually by each target user.

[0023] First, the configuration of a purchasing demographic analysis support system 90 according to this embodiment will be described with reference to Figures 1 and 2. Figure 1 is a block diagram showing an example of the hardware configuration of the purchasing demographic analysis support system 90 according to this embodiment. Also, Figure 2 is a block diagram showing an example of the functional configuration of the purchasing demographic analysis support system 90 according to this embodiment.

[0024] 1, a purchasing demographic analysis support system 90 according to this embodiment includes a purchasing demographic analysis support device 10 and a plurality of target person terminals 30, each of which is capable of accessing a network 80. Examples of the purchasing demographic analysis support device 10 include information processing devices such as personal computers and server computers. Examples of the target person terminals 30 include portable terminals such as smartphones, tablet terminals, and PDAs (Personal Digital Assistants, mobile information terminals).

[0025] The subject terminal 30 according to this embodiment is a terminal possessed by each of a plurality of subjects (hereinafter, simply referred to as "subjects") who are the users of the purchase demographic analysis support system 90. The subject terminal 30 includes a CPU (Central Processing Unit) 31, a memory 32 as a temporary storage area, a non-volatile storage unit 33, an input unit 34 such as a touch panel, a display unit 35 such as a liquid crystal display, and a medium reading and writing device (R / W) 36. The subject terminal 30 also includes a camera 38, a microphone 39, a GPS (Global Positioning Systems) 40, and a wireless communication unit 42. The CPU 31, the memory 32, the storage unit 33, the input unit 34, the display unit 35, the medium reading and writing device 36, the camera 38, the microphone 39, the GPS 40, and the wireless communication unit 42 are connected to each other via a bus B1. The medium reading and writing device 36 reads information written in the recording medium 37 and writes information to the recording medium 37.

[0026] The storage unit 33 is realized by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. A demographic information display program 33A is stored in the storage unit 33 as a storage medium. The demographic information display program 33A is stored (installed) in the storage unit 33 by setting a recording medium 37, on which the program 33A is written, in the medium reading and writing device 36, and the medium reading and writing device 36 reading the program 33A from the recording medium 37. The CPU 31 reads the demographic information display program 33A from the storage unit 33, expands it in the memory 32, and sequentially executes the processes of the demographic information display program 33A.

[0027] On the other hand, the purchasing demographic analysis support device 10 is a device that collectively stores and manages various information handled by the purchasing demographic analysis support system 90. The purchasing demographic analysis support device 10 includes a CPU 11, a memory 12 as a temporary storage area, a non-volatile storage unit 13, an input unit 14 such as a keyboard and a mouse, a display unit 15 such as a liquid crystal display, a medium reading and writing device 16, and a communication interface (I / F) unit 18. The CPU 11, the memory 12, the storage unit 13, the input unit 14, the display unit 15, the medium reading and writing device 16, and the communication interface (I / F) unit 18 are connected to each other via a bus B2. The medium reading and writing device 16 reads information written in a recording medium 17 and writes information to the recording medium 17.

[0028] The storage unit 13 is realized by an HDD, an SSD, a flash memory, or the like. The storage unit 13 as a storage medium stores a purchasing demographic analysis support program 13A and a purchasing demographic information presentation program 13B. The purchasing demographic analysis support program 13A is stored (installed) in the storage unit 13 by setting a recording medium 17 in which the program 13A is written to the medium reading and writing device 16, and the medium reading and writing device 16 reading the program 13A from the recording medium 17. The purchasing demographic information presentation program 13B is stored (installed) in the storage unit 13 by setting a recording medium 17 in which the program 13B is written to the medium reading and writing device 16, and the medium reading and writing device 16 reading the program 13B from the recording medium 17. The CPU 11 reads each of the purchasing demographic analysis support program 13A and the purchasing demographic information presentation program 13B from the storage unit 13, expands them in the memory 12, and sequentially executes the processes that each of the programs has.

[0029] Further, a target area information database 13C, a first original data group database 13D, a second original data group database 13E, and a fusion information database 13F are stored in the storage unit 13. The target area information database 13C, the first original data group database 13D, the second original data group database 13E, and the fusion information database 13F will be described in detail later.

[0030] Next, the functional configuration of the purchase layer analysis support device 10 and the target person terminal 30 according to this embodiment will be described with reference to FIG.

[0031] 2, the purchasing demographic analysis support device 10 includes an acquisition unit 11A, a fusion unit 11B, and a presentation unit 11C. The CPU 11 of the purchasing demographic analysis support device 10 executes a purchasing demographic analysis support program 13A and a purchasing demographic information presentation program 13B to function as the acquisition unit 11A, the fusion unit 11B, and the presentation unit 11C.

[0032] The acquisition unit 11A according to the present embodiment acquires data on a plurality of original data groups, which are data on consumers who have purchased an object and are obtained under mutually different conditions. The fusion unit 11B according to the present embodiment fuses the data of the plurality of original data groups acquired by the acquisition unit 11A using a degree of association indicating the strength of association between the plurality of original data groups. The presentation unit 11C according to the present embodiment presents purchasing demographic information indicating the purchasing demographic for the object, using the result of the fusion by the fusion unit 11B.

[0033] That is, as shown in FIG. 3 as an example, in the past, when data of a plurality of original data groups is merged, a method of fusing data having common attribute data among the plurality of original data groups was generally used. Note that the example shown in FIG. 3 illustrates a case where the data of the plurality of original data groups is data of two types of original data groups. Also, the example shown in FIG. 3 illustrates a case where one original data group (hereinafter referred to as the "first original data group") is configured with purchase data including data indicating gender, age, and family structure as attribute data, and data indicating the purchasing pattern of the subject (hereinafter referred to as the "purchase pattern data"). Furthermore, the example shown in FIG. 3 illustrates a case where the other original data group (hereinafter referred to as the "second original data group") is configured with data indicating gender and age as attribute data, and data indicating the behavior pattern of the subject (hereinafter referred to as the "behavior pattern data").

[0034] In the example shown in Fig. 3, in each of the first and second original data groups, a plurality of clusters are formed by clustering the data belonging to the original data group, and the data group for each cluster is treated as the original data group. The reason why the data of the first and second original data groups are clustered here is that if the data belonging to these original data groups are a collection of data with low correlation with each other, even if the data of each original data group is fused, it is highly likely that it will not contribute to the analysis of the desired purchasing demographic. Therefore, if the data of the first and second original data groups have been clustered, further clustering is not necessarily required.

[0035] In this case, the two data of gender and age in the attribute data between the original data group for each cluster in the first original data group and the original data group for each cluster in the second original data group are the same type of data. For this reason, in conventional technologies, a method of fusing the two attribute data that are identical or similar has often been adopted.

[0036] However, the attribute data does not necessarily include the same type of data between the original data groups, and when all the attribute data is different between the original data groups, this method cannot be adopted.

[0037] Therefore, in the fusion unit 11B according to the present embodiment, data of a plurality of original data groups is not fused using attribute data, but rather, data of the plurality of original data groups is fused using a degree of association indicating the strength of association between the plurality of original data groups, as shown in Fig. 4 as an example. Note that the example shown in Fig. 4 illustrates a case in which data indicating gender, age, and family structure are applied as attribute data in the first original data group, and data indicating place of residence and annual income are applied as attribute data in the second original data group.

[0038] This embodiment allows for appropriate fusion of multiple original data groups in which all attribute data are different. In the following, an example will be described in which the data of each cluster in the first original data group and the data of each cluster in the second original data group shown in FIG. 4 are applied as the data of the original data group of the technology disclosed herein.

[0039] Here, the fusion unit 11B according to this embodiment derives the degree of connectivity for each combination between the above-mentioned multiple original data groups, and fuses the data of the original data group with the combination having the highest total score, which is the sum of the derived degrees of connectivity.

[0040] In addition, in the purchasing demographic analysis support system 90 of this embodiment, as the original data group, a data group obtained by clustering data (in this embodiment, the above-mentioned purchasing data and people flow data) regarding the purchaser who purchased the target item (in this embodiment, the target person) as described above is applied.

[0041] In the purchasing layer analysis support system 90 according to the present embodiment, the target data is qualitative data, so a clustering method targeted at qualitative data is applied, but this is not limited to this. For example, when the target data is mixed quantitative and qualitative data that includes both qualitative and quantitative data, a clustering method targeted at mixed quantitative and qualitative data may be applied, and when the target data is only quantitative data, a clustering method targeted at only quantitative data may be applied.

[0042] In addition, in the purchasing demographic analysis support system 90 according to this embodiment, a machine learning model is constructed using data between each of the above-mentioned multiple original data groups, and the degree of coupling is determined by a value that increases as the estimation accuracy of the machine learning model increases.

[0043] Specifically, the fusion unit 11B first generates a machine learning model for each combination of each cluster belonging to the first elemental data group and each cluster belonging to the second elemental data group.

[0044] Next, for each of the generated machine learning models, the fusion unit 11B uses a portion of the data of the cluster belonging to the first original data group (hereinafter referred to as "first cluster data") as input data and a portion of the data of the cluster belonging to the second original data group (hereinafter referred to as "second cluster data") as output data to train the corresponding machine learning model.

[0045] Next, for each of the trained machine learning models, the fusion unit 11B derives the degree of agreement between the output data obtained by inputting the remaining data in the corresponding first cluster data and the remaining data in the corresponding second cluster data as the above-mentioned degree of association.

[0046] Then, the fusion unit 11B fuses the first cluster data and the second cluster data of the combination that results in the largest overall score, which is the sum of the degrees of connectivity, among all the combinations in which each cluster belonging to the first elemental data group is combined one-to-one with each cluster belonging to the second elemental data group.

[0047] In this way, in the purchasing layer analysis support system 90 according to the present embodiment, a machine learning model is used to derive the degree of association from the high prediction accuracy of the machine learning model, but the present invention is not limited to this. For example, the inverse of the distance between the distribution of data belonging to the first cluster data and the distribution of data belonging to the second cluster data may be applied as the degree of association. In short, any value indicating the strength of association between the first cluster data and the second cluster data, in other words, the strength of the degree of association, may be applied as the degree of association.

[0048] In the purchasing demographic analysis support system 90 according to the present embodiment, both products and services are applied as the above-mentioned target, but the present invention is not limited to this. For example, only one of products and services may be applied as the above-mentioned target. Furthermore, the products referred to here may include all purchasable tangible items such as bags, shoes, clothes, tickets, etc., and the services referred to here may include all purchasable intangible items such as beauty services, medical services, logistics services, etc.

[0049] The presentation unit 11C according to the present embodiment presents the purchasing demographic information by transmitting information relating to the purchasing demographic information to the requested target person terminal 30 and displaying it on the display unit 35 of the target person terminal 30, but is not limited to this. For example, the purchasing demographic information may be presented by displaying it on the display unit 15 of the purchasing demographic analysis support device 10. Presentation of the purchasing demographic information by the presentation unit 11C is not limited to display on the display unit, and may be presented by voice or by printing on an image forming device (so-called printer).

[0050] Furthermore, the presentation unit 11C according to this embodiment combines the purchasing demographic information with a map image and presents it. In particular, in this embodiment, a social heat map image is applied as the map image. The social heat map image is an image showing a map in which a place where there is a lot of information that matches the target person's category is emphasized by displaying areas with different densities or colors superimposed on a map image that is normally displayed in the corresponding area. That is, in this embodiment, each target person is asked to answer a plurality of questions in advance, and the answer results are analyzed and classified to determine the category of each target person in advance. Then, the social heat map image according to this embodiment is displayed superimposed on the map image so that the density increases as the number of places where there is a lot of information that matches the target person's category (information posted on SNS (Social Networking Service) in this embodiment). However, this is not limited to a form of changing the density, and a form of changing the color in order from high density to low density, such as red → yellow → green, may be used.

[0051] In this embodiment, the purchasing demographic analysis support device 10 is connected to a server that provides the latest social heat map images of the areas (hereinafter referred to as "target areas") that are handled by the purchasing demographic analysis support system 90 via a network 80 or the like. The purchasing demographic analysis support device 10 then obtains the latest social heat map images from this server and sequentially updates the social heat map images stored in the target area information database 13C (see also FIG. 5) described below. However, this is not the only possible form, and the purchasing demographic analysis support device 10 itself may sequentially update the social heat map images corresponding to each target person.

[0052] 2, the target user terminal 30 according to the present embodiment includes a receiving unit 31A and a display control unit 31B. The CPU 31 of the target user terminal 30 executes a demographic information display program 33A to function as the receiving unit 31A and the display control unit 31B.

[0053] The receiving unit 31A according to the present embodiment receives information relating to the purchasing demographic information presented by the presentation unit 11C of the purchasing demographic analysis support device 10 from the purchasing demographic analysis support device 10. The display control unit 31B controls the display of the information relating to the purchasing demographic information received by the receiving unit 31A on the display unit 35.

[0054] Next, the target area information database 13C according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a schematic diagram showing an example of the configuration of the target area information database 13C according to this embodiment.

[0055] The target area information database 13C according to the present embodiment is a database in which information related to the above-mentioned target area is registered. As shown in Fig. 5, the target area information database 13C according to the present embodiment stores information on the target area name, the social heat map image, the target district name, and the target district position.

[0056] The target area name is information indicating the name of each of the target areas, and the social heat map image is information indicating the above-mentioned social heat map image for each subject in the target area indicated by the corresponding target area name. The target district name is information indicating the name of a district (hereinafter referred to as "target district") that exists within the corresponding target area, and the target district position is information indicating the position where the corresponding target district exists.

[0057] In this embodiment, the target area is an area divided by block in each town in the corresponding target area. Also, in this embodiment, the target area position is defined as a coordinate position in a two-dimensional coordinate system of a pair of diagonal corners of a circumscribing rectangular frame of the corresponding target area. However, this is not limited to these forms, and for example, the target area may be an area divided by an address in each town in the corresponding target area, or the target area position may be the coordinate position in the two-dimensional coordinate system of the center point of the circumscribing rectangular frame, or further, latitude and longitude may be applied instead of the coordinate position in the two-dimensional coordinate system.

[0058] Next, the first base data group database 13D according to this embodiment will be described with reference to Fig. 6. Fig. 6 is a schematic diagram showing an example of the configuration of the first base data group database 13D according to this embodiment.

[0059] The first original data group database 13D according to this embodiment is the one in which the above-mentioned purchase data is registered. As shown in Fig. 6, the first original data group database 13D according to this embodiment stores each data of purchase district, cluster, attribute data, and purchase pattern data.

[0060] The purchasing district is information indicating the district where each subject purchased the object, and in this embodiment, districts in the target district excluding blocks are applied. The cluster is information indicating the classification of clusters in the first source data group. The attribute data and the purchasing pattern data are information indicating the attribute data and purchasing pattern data themselves in the purchasing data described above for the corresponding subject, respectively.

[0061] In this embodiment, the information registered in the first element data group database 13D is information acquired from an electronic payment system when the payment method for the purchase price when each subject purchases an object is by an electronic payment system with the subject's consent, but the information is not limited to this. For example, information acquired from a POS (Point Of Sale) system used in various stores in each subject area may be used.

[0062] In the example shown in FIG. 6, for example, data belonging to cluster a1 indicates that a single man in his 30s living in Otemachi purchased an item in the high price range, which is a predetermined price range.

[0063] Next, the second base data group database 13E according to this embodiment will be described with reference to Fig. 7. Fig. 7 is a schematic diagram showing an example of the configuration of the second base data group database 13E according to this embodiment.

[0064] The second original data group database 13E according to the present embodiment is a database in which the above-mentioned people flow data is registered. As shown in Fig. 7, the second original data group database 13E according to the present embodiment stores each data of clusters, attribute data, and behavior pattern data.

[0065] The cluster is information indicating the classification of the cluster in the second source data group. The attribute data and the behavior pattern data are data indicating the attribute data and the behavior pattern data themselves in the people flow data, respectively, regarding the corresponding subject.

[0066] In the example shown in FIG. 7, for example, data belonging to cluster b1 indicates that the behavior pattern of a person who lives in Tokyo and has an annual income of A is a pattern of returning home directly from the station.

[0067] Next, the fusion information database 13F according to this embodiment will be described with reference to Fig. 8. Fig. 8 is a schematic diagram showing an example of the configuration of the fusion information database 13F according to this embodiment.

[0068] The fusion information database 13F according to the present embodiment is a database in which information indicating the fusion result of the original data group by the fusion unit 11B is registered. As shown in Fig. 8, the fusion information database 13F according to the present embodiment stores data indicating the purchase area and fusion information.

[0069] The above purchasing area is the same information as the purchasing area in the first original data group database 13D, and the above fusion information is data corresponding to the corresponding purchasing area and is information indicating a combination of the first cluster data and the second cluster data fused by the fusion unit 11B.

[0070] In the example shown in FIG. 8, for example, it is shown that data relating to Otemachi, data of cluster a1 in the first data group and data of cluster b3 in the second data group are fused together.

[0071] Next, the operation of the purchasing demographic analysis support system 90 according to this embodiment will be described with reference to Figs. 9 to 14. Fig. 9 is a flowchart showing an example of a purchasing demographic analysis support process according to this embodiment. Fig. 10 is a diagram showing an example of the configuration of a district designation screen according to this embodiment. Fig. 11 is a flowchart showing an example of a purchasing demographic information presentation process according to this embodiment. Fig. 12 is a flowchart showing an example of a purchasing demographic information display process according to this embodiment. Fig. 13 is a diagram showing an example of the configuration of an initial screen according to this embodiment. Furthermore, Fig. 14 is a diagram showing an example of the configuration of a purchasing demographic information presentation screen according to this embodiment.

[0072] First, the operation of the purchasing demographic analysis support device 10 according to this embodiment when the purchasing demographic analysis support process is executed will be described with reference to Fig. 9. When a user of the purchasing demographic analysis support device 10 (for example, an administrator of the purchasing demographic analysis support system 90) inputs an instruction to start the execution of the purchasing demographic analysis support process via the input unit 14, the CPU 11 of the purchasing demographic analysis support device 10 executes the purchasing demographic analysis support program 13A, thereby executing the purchasing demographic analysis support process shown in Fig. 9. Note that, in order to avoid confusion, a case will be described here where the first original data group database 13D and the second original data group database 13E have already been constructed.

[0073] In step 100 of FIG. 9, the CPU 11 controls the display unit 15 to display a district designation screen having a predetermined configuration, and in step 102, the CPU 11 waits until predetermined information is input.

[0074] As an example, as shown in FIG. 10, the district designation screen according to this embodiment displays a message prompting the user to input the name of the district to be processed (hereinafter, referred to as the "processing target district"), and also displays an input area 15A for inputting the name of the processing target district. When the district designation screen shown in FIG. 10 is displayed by the display unit 15, the user inputs the name of the district to be the target of merging data of the original data group into the input area 15A using the input unit 14, and then selects the end button 15C. In response to this, step 102 is judged to be positive, and the process proceeds to step 104. Note that, in this embodiment, the input of the name of the processing target district on the district designation screen is in a form in which the name of the processing target district itself is directly input, but this is not limited thereto. For example, the names of all districts targeted by the purchasing layer analysis support system 90 may be displayed in a pull-down format, and the name of the desired processing target district may be selected from the displayed district names.

[0075] In step 104, CPU 11 reads out data of all clusters corresponding to the processing area input by the user (hereinafter referred to as "first target data") from the first original data group database 13D, and also reads out all data (hereinafter referred to as "second target data") from the second original data group database 13E.

[0076] In step 106, the CPU 11 uses the read first target data and second target data to generate a machine learning model for each combination of clusters and perform machine learning, as described above.

[0077] In step 108, the CPU 11 uses each trained machine learning model to derive a coupling factor as described above, and in step 110, the CPU 11 uses the derived coupling factors to derive a total score as described above.

[0078] In step 112, the CPU 11 uses the derived total score to execute a fusion process, which is a process of fusing the data of each cluster of the first original data group corresponding to the area to be processed with the data of each cluster of the second original data group as described above, and then terminates this purchasing demographic analysis support process.

[0079] In the present embodiment, as an example of the fusion process, as shown in Fig. 8, information indicating the area to be processed is registered as a purchasing area in the fusion information database 13F, and information indicating a cluster of the first elemental data group to be fused and information indicating a cluster of the second elemental data group are registered in association with the purchasing area, but the fusion process is not limited to this. For example, a new data group may be created by combining data of the cluster of the first elemental data group to be fused and data of the cluster of the second elemental data group, and the data of the data group itself may be registered together with information indicating the area to be processed.

[0080] By the above-mentioned purchase group analysis support process, an integrated information database 13F shown in FIG. 8 is constructed as an example.

[0081] Next, the operation of the purchasing layer analysis support device 10 according to this embodiment when performing the purchasing layer information presentation process will be described with reference to FIG.

[0082] In the purchasing demographic analysis support system 90 according to this embodiment, when a target person wants to refer to purchasing demographic information created using data fused in a fusion process by the purchasing demographic analysis support process for a certain area, the purchasing demographic information display process described later is executed using the target person's terminal 30. In this purchasing demographic information display process, the target person transmits reference request information including information (hereinafter referred to as "designated target area information") indicating the area (hereinafter referred to as "designated target area") for which the target person wants to refer to the purchasing demographic information to the purchasing demographic analysis support device 10. When this reference request information is received, the CPU 11 of the purchasing demographic analysis support device 10 executes the purchasing demographic information presentation program 13B, thereby executing the purchasing demographic information presentation process shown in FIG. 11. In addition, in order to avoid confusion, a case will be described here in which the target area information database 13C and the fusion information database 13F have already been constructed.

[0083] 11, the CPU 11 extracts the designated area information from the received reference request information. In step 152, the CPU 11 reads information corresponding to the designated area indicated by the designated area information (hereinafter, referred to as "integrated information") from the integrating information database 13F.

[0084] In step 154, the CPU 11 reads out from the target area information database 13C a target area position corresponding to the specified target area and a social heat map image corresponding to the target area that includes the specified target area and corresponding to the target person who is the access source.

[0085] In step 156, CPU 11 reads out data of each cluster of the first and second original data groups indicated to be fused by the read fusion information from first and second original data group databases 13D and 13E, and fuses the read out data for each cluster to be fused. CPU 11 then uses the read out social heatmap image and the fused data to create information showing a predetermined configuration of a demographic information presentation screen (hereinafter referred to as "demand information presentation screen information"). In step 158, CPU 11 transmits the created demographic information presentation screen information to the target user terminal 30 from which the access originated, and then ends this demographic information presentation process.

[0086] Next, the operation of the target person terminal 30 according to this embodiment when executing the above-mentioned purchasing demographic information display process will be described with reference to Fig. 12. The purchasing demographic information display process shown in Fig. 12 is executed by the CPU 31 of any of the target person terminals 30 executing the purchasing demographic information display program 33A. The purchasing demographic information display process shown in Fig. 12 is executed, for example, when an instruction to execute the purchasing demographic information display process is input from any of the targets (hereinafter referred to as "target person") via the input unit 34 of his / her target person terminal 30.

[0087] In step 200 of FIG. 12, the CPU 31 controls the display unit 35 to display an initial screen having a predetermined configuration, and in step 202, the CPU 31 waits until predetermined information is input.

[0088] As an example, as shown in FIG. 13, the initial screen according to this embodiment displays a message prompting the user to input the name of the target district, and also displays an input area 35A for inputting the name of the district for which the user wishes to refer to the above-mentioned customer demographic information, i.e., the above-mentioned designated target district. When the initial screen shown in FIG. 13 is displayed on the display unit 35, the user inputs the name of the designated target district into the input area 35A using the input unit 34, and then selects the end button 35C. In response to this, step 202 is judged to be positive, and the process proceeds to step 204. In this embodiment, the name of the designated target district is input on the initial screen by directly inputting the name of the designated target district, but this is not limited to this. The names of all districts for which the customer demographic information can be referred to may be displayed in a pull-down format, and the user may select the name of the desired designated target district from the displayed district names.

[0089] In step 204, the CPU 31 transmits the above-mentioned reference request information to the purchasing demographic analysis support device 10. In response to this, the purchasing demographic analysis support device 10 executes the purchasing demographic information presentation process as described above, and transmits purchasing demographic information presentation screen information to the target user terminal 30 that is the access source.

[0090] Therefore, in step 206, the CPU 31 waits until the purchasing demographic information presentation screen information is received from the purchasing demographic analysis support device 10. In step 208, the CPU 31 controls the display unit 35 to display the purchasing demographic information presentation screen indicated by the received purchasing demographic information presentation screen information, and in step 210, the CPU 31 waits until predetermined information is input, and then ends this purchasing demographic information display process.

[0091] As an example, as shown in Fig. 14, the purchase demographic information presentation screen according to this embodiment displays fusion result information 35B indicating attribute data, purchase patterns, behavior patterns, and the percentage of the total number of purchasers of the target item, regarding people who purchased the target item in the designated target area, at a corresponding position on the social heat map image of the target area including the designated target area. Note that the corresponding position is the position indicated by the designated target area.

[0092] Therefore, by referring to the demographic information presentation screen, the target person can grasp demographic information regarding the target object in the desired designated target area together with the social heat map image.

[0093] As described above, according to this embodiment, data on consumers who have purchased an object is obtained from a plurality of original data groups obtained under mutually different conditions, and the data from the plurality of original data groups is fused using the degree of association indicating the strength of association between each of the plurality of original data groups obtained, and the fusion result is used to present consumer demographic information indicating the consumer demographic for the object. Therefore, even if the original data groups do not have the same attributes, they can be fused according to the degree of association, and as a result, a more detailed consumer demographic can be identified compared to identifying the consumer demographic by classifying data indicating purchase history into consumers with the same attributes.

[0094] Furthermore, according to this embodiment, a degree of association is derived for each combination between multiple original data groups, and the data of the original data group with the highest total score, which is the sum of the derived degrees of association, is fused. Therefore, the data of multiple original data groups can be fused more appropriately than when the data of multiple original data groups is fused without using the total score.

[0095] According to the present embodiment, the original data group is a data group obtained by clustering data related to purchasers who purchased the target product. Therefore, data belonging to each of the multiple original data groups can be treated as similar data, and as a result, data from the multiple original data groups can be more appropriately merged.

[0096] According to the present embodiment, the degree of coupling is a degree that is determined by constructing a machine learning model using data between each of a plurality of original data groups, and the higher the estimation accuracy of the machine learning model, the higher the value of the degree of coupling. Therefore, the data of a plurality of original data groups can be fused with higher accuracy than when the estimation accuracy is not used.

[0097] Furthermore, according to this embodiment, the target object is at least one of a product and a service, so that it is possible to grasp more detailed purchasing groups for at least one of various products and services.

[0098] In the above embodiment, the case where the purchase demographic information presentation screen includes a social heat map image has been described, but is not limited to this. For example, the purchase demographic information presentation screen may display information showing the data fusion results of the purchase demographic analysis support process and analysis results obtained from the fusion results without displaying the social heat map image.

[0099] An example of a purchase group information presentation screen in this form is shown in Fig. 15. In the example shown in Fig. 15, information on major personas, which are personas that occupy the majority in Otemachi, and unique personas, which are personas that are unique to Otemachi, are displayed together with information showing the analysis results. Therefore, in this example, this information can be grasped.

[0100] In the above embodiment, the subject himself / herself designates the designated target area, but the present invention is not limited to this. For example, the GPS 40 built into the subject terminal 30 held by the subject may be used to automatically apply the area including the location of the subject terminal 30 as the designated target area. In addition, the purchase layer analysis support device 10 may acquire information indicating the subject's taste tendency in advance, and provide the subject with information on areas according to the subject's taste at any time.

[0101] In the above embodiment, the case where the purchasing demographic analysis support process is executed in the purchasing demographic analysis support device 10 has been described, but the present invention is not limited to this. For example, the purchasing demographic analysis support process may be executed by each target person terminal 30. In this case, the purchasing demographic analysis support device of the present invention is included in the target person terminal 30.

[0102] In the above embodiment, the input of the designated area is performed on the initial screen using the input unit 34, but the present invention is not limited to this. For example, the designated area may be input as voice information using the microphone 39.

[0103] In the above embodiment, the multiple original data groups are only two types of original data groups, the first original data group and the second original data group, but the present invention is not limited to this. For example, three or more types of original data groups may be used as the multiple original data groups.

[0104] In the above embodiment, for example, the hardware structure of the processing unit that executes each process of the acquisition unit 11A, the fusion unit 11B, and the presentation unit 11C may be the various processors shown below. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as a processing unit, as well as a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture such as an FPGA (Field-Programmable Gate Array), a dedicated electric circuit, which is a processor having a circuit configuration designed specifically for executing a specific process such as an ASIC (Application Specific Integrated Circuit), etc.

[0105] The processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA).The processing unit may also be configured with a single processor.

[0106] As an example of configuring the processing unit with one processor, first, there is a form in which one processor is configured with a combination of one or more CPUs and software, as represented by computers such as client and server, and this processor functions as the processing unit. Second, there is a form in which a processor is used that realizes the functions of the entire system including the processing unit with one IC (Integrated Circuit) chip, as represented by System On Chip (SoC), etc. In this way, the processing unit is configured using one or more of the above various processors as a hardware structure.

[0107] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. [Explanation of symbols]

[0108] 10 Purchasing demographic analysis support device 11 CPU 11A Acquisition Department 11B Fusion section 11C Presentation section 12. Memory 13 Storage section 13A Customer Analysis Support Program 13B Customer Information Presentation Program 13C Subject Area Information Database 13D First Data Group Database 13E Second Data Group Database 13F Fusion Information Database 14 Input section 15 Display 15A input range 16 Media Read / Write Device 17 Recording media 18 Communication I / F section 30 Target device 31 CPU 31A Receiver 31B Display control unit 32 Memory 33 Storage section 33A Customer Profile Display Program 34 Input section 35 Display section 35A input range 35B Fusion result information 36 Media Read / Write Device 37 Recording media 38 Camera 39. Mike 40 GPS 42 Wireless Communication Section 80 Network 90 Customer Analysis Support System

Claims

1. an acquisition unit that acquires a plurality of original data groups, the data being related to purchasers who have purchased an object and obtained under mutually different conditions; a fusion unit that fuses data of the plurality of original data groups using a degree of association indicating a strength of association between each of the plurality of original data groups acquired by the acquisition unit; a presentation unit that presents customer demographic information indicating a customer demographic for the object by using a result of the fusion by the fusion unit; A purchasing group analysis support device equipped with the above.

2. the fusion unit derives the degree of connectivity for each combination between the plurality of original data groups, and fuses the data of the original data group having the highest total score, which is the sum of the derived degrees of connectivity; 2. The purchasing demographic analysis support device according to claim 1.

3. The original data group is a data group obtained by clustering data related to purchasers who purchased the target product.

2. The purchasing demographic analysis support device according to claim 1.

4. The degree of coupling is a degree to which a machine learning model is constructed using data between each of the plurality of original data groups, and the higher the estimation accuracy of the machine learning model, the higher the value of the degree of coupling is.

2. The purchasing demographic analysis support device according to claim 1.

5. The object is at least one of a product and a service.

2. The purchasing demographic analysis support device according to claim 1.

6. Acquire a plurality of groups of original data relating to purchasers who have purchased the target item and obtained under mutually different conditions; fusing data of the plurality of original data groups using a degree of association indicating a strength of association between each of the plurality of original data groups; Using the fusion result, presenting demographic information indicating a demographic for the object; A program that causes a computer to carry out processing.

Images