Similar customer base estimation device, similar customer base estimation method, and similar customer base estimation program

Abstract

Provided are: a similar customer base estimation device capable of estimating a similar customer base by comparing different pieces of consumption behavior information; and a program for same. The similar customer base estimation device comprises: a first attribute information extraction means for extracting first attribute information about at least one of a customer base for which potential consumption orientation is to be estimated or similar customer candidate bases that may be a similar customer base similar to the customer base; a second attribute information specification means for specifying second attribute information expanded on the basis of the extracted first attribute information and matching the second attribute information with at least one of the customer base or the similar customer candidate bases; and a similar customer base estimation means for estimating a similar customer base similar to the customer base from among the similar customer candidate bases by collating the second attribute information expanded for one of the customer base or the similar customer candidate bases with information matched in advance with the other, or by collating the pieces of second attribute information expanded for both the customer base and the similar customer candidate bases.

Description

Similar customer group estimation device, similar customer group estimation method, and similar customer group estimation program

[0001] The present disclosure relates to a similar customer group estimation device, a similar customer group estimation method, and a similar customer group estimation program.

[0002] In recent years, technologies have been developed that attempt to analyze customer consumption behavior data and utilize the data for marketing. For example, Patent Literature 1 discloses a technology that automatically proposes services to customers by using purchase pattern information obtained from purchase history information.

[0003] Japanese Patent Application Laid-Open No. 2001-022826

[0004] By analyzing consumer behavior information, including the consumption behavior history of customers, it is expected that similar customer segments can be discovered and utilized for marketing. However, because the information contained in consumer behavior information is limited, it has been difficult to estimate similar customer segments by comparing different sets of consumer behavior information.

[0005] In view of the above-mentioned problems, an object of the present disclosure is to provide a similar customer segment estimation device, a similar customer segment estimation system, a similar customer segment estimation method, and a similar customer segment estimation program that are capable of estimating similar customer segments by comparing different consumption behavior information.

[0006] The similar customer segment estimation device according to the present disclosure includes: a first attribute information extraction means for extracting first attribute information for at least one of a customer segment whose latent consumption tendency is desired to be estimated and a similar customer segment that is similar to the customer segment; a second attribute information identification means for identifying second attribute information extended based on the extracted first attribute information and linking the second attribute information to at least one of the customer segment and the similar customer segment; and a similar customer segment estimation means for estimating a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the second attribute information extended for either the customer segment or the similar customer segment with information previously linked for the other, or by comparing the second attribute information extended for both the customer segment and the similar customer segment with each other.

[0007] The similar customer class estimation method according to the present disclosure includes a computer extracting first attribute information for at least one of a customer class whose latent consumption tendency is desired to be estimated and a similar customer candidate class that is similar to the customer class, specifying second attribute information extended based on the extracted first attribute information and linking the second attribute information to at least one of the customer class and the similar customer candidate class, and estimating a similar customer class that is similar to the customer class from the similar customer candidate class by comparing the second attribute information extended for either the customer class or the similar customer candidate class with second attribute information previously specified for the other, or by comparing the second attribute information extended for both the customer class and the similar customer candidate class.

[0008] The similar customer segment estimation program according to the present disclosure causes a computer to execute the following processes: extracting first attribute information for at least one of a customer segment whose latent consumption tendency is desired to be estimated and a similar customer segment that is similar to the customer segment; specifying second attribute information extended based on the extracted first attribute information and linking it to at least one of the customer segment and the similar customer segment; and estimating a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the second attribute information extended for either the customer segment or the similar customer segment with second attribute information specified in advance for the other, or by comparing the second attribute information extended for both the customer segment and the similar customer segment.

[0009] The present disclosure makes it possible to provide a similar customer segment estimation device, a similar customer segment estimation method, and a similar customer segment estimation program that are capable of estimating a similar customer segment by comparing different pieces of consumption behavior information.

[0010] 1 is a block diagram showing a configuration of a similar customer group estimation device according to the present disclosure. FIG. 2 is a flowchart showing an example of the flow of a similar customer group estimation method according to the present disclosure. FIG. 3 is a block diagram showing a configuration of a similar customer group estimation system according to the present disclosure. FIG. 4 is a block diagram showing a configuration of a service request device capable of communicating with the similar customer group estimation system according to the present disclosure. FIG. 5 is a block diagram showing a configuration of a similar customer group estimation device according to the present disclosure. FIG. 6 is a sequence diagram showing an example of operation of the similar customer group estimation system when linking attribute information. FIG. 7 is a diagram showing an example of consumption behavior information of a similar customer group candidate. FIG. 8 is a sequence diagram showing an example of operation of the similar customer group estimation system when estimating a similar customer group. FIG. 9 is a diagram showing an example of consumption behavior information of a customer group. FIG. 10 is a block diagram showing a configuration of a service request device capable of communicating with the similar customer group estimation system according to the present disclosure. FIG. 11 is a block diagram showing a configuration of a similar customer group estimation system according to the present disclosure. FIG. 12 is a block diagram showing a configuration of a service request device capable of communicating with the similar customer group estimation system according to the present disclosure.

[0011] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0012] First Embodiment An example of the configuration of a similar customer group estimation device 100 will be described below with reference to Fig. 1. The similar customer group estimation device 100 includes a first attribute information extraction unit 110, a second attribute information identification unit 120, and a similar customer group estimation unit 130.

[0013] The first attribute information extraction unit 110 extracts first attribute information of a customer segment and a similar customer candidate segment and associates it with the corresponding customer segment or similar customer candidate segment. A customer segment refers to multiple customers whose potential consumption tendencies are desired to be estimated by a client. For example, a customer segment refers to customers who repeatedly purchase products from a store operated by the client. Here, the client is a user of the similar customer segment estimation device 100. However, the client and the user of the similar customer segment estimation device 100 do not necessarily have to be the same person. A similar customer candidate segment refers to customers who are similar to a customer segment and could potentially become a similar customer segment. The number of customers constituting each of the customer segment and the similar customer segment may be one or more. The first attribute information extraction unit 110, for example, acquires consumption behavior information of the customer segment and the similar customer candidate segment and extracts first attribute information included in the consumption behavior information. Here, "consumption behavior information of the customer segment and the similar customer candidate segment" refers to a collection of consumption behavior information of each of the customers constituting the customer segment and the similar customer segment.

[0014] Consumption behavior information includes the consumption behavior history of a customer or a potential similar customer. Specifically, it is information linking a specific person to the consumption behavior history of that person. Consumption behavior information is not limited to information directly linking a specific person to the consumption behavior history of that person, but may also include information indirectly linking the specific person to the consumption behavior history. Consumption behavior, for example, refers to the purchase of goods, services, etc. Furthermore, such behavior is not limited to behavior performed in a physical store, but may also include online shopping performed on the Internet. Examples of consumption behavior information include information linking a person who has registered to use a specific payment service with the person's payment service usage history, and information linking a person who has registered as a member of a specific store with the person's purchase history at the specific store. Consumption behavior information may also be information linking a specific person to receipts from the person's purchases of goods, services, etc. at various stores.

[0015] The consumption behavior history is a history of consumption behavior, specifically, for example, the name of the store where the product was purchased, the date and time, the purchase amount, and the purchased product. The store name may include information indicating the store's location in addition to the store name. For example, the store's location may be printed on a receipt or may be obtained as information other than a receipt, such as a GNSS history. The GNSS (Global Navigation Satellite System) is a global positioning system using artificial satellites that measures customer location information. In other words, the consumption behavior information may further link information other than receipts to a specific person. The consumption behavior information may also include a customer ID for identifying the customer. If the consumption behavior information includes a customer ID, the ID is managed by linking the ID to basic attribute information, first attribute information, second attribute information, and the like. The consumption behavior information includes the customer's basic attribute information in addition to the customer's consumption behavior history. The basic attribute information is basic attribute information related to the customer, such as demographic attributes, geographic attributes, and behavioral attributes. Demographic attributes are demographic attributes, such as a customer's age and gender. Geographic attributes are geographic attributes, such as the climate, culture, and economy specific to the area where the customer lives. Behavioral attributes are behavioral attributes, such as the frequency, purpose, purchase history, and range of activity of a customer using a product or service.

[0016] The first attribute information is information that may relate to the customer's consumption behavior and is included in the consumption behavior information. The first attribute information is text information. Specifically, the first attribute information may include, for example, information about the store where the customer purchased the product, such as the name of the store, the location of the store, the type of business of the store, and the purchase amount at the store. The first attribute information may also include information about the product, such as the product name of the product purchased by the customer and product attribute information previously assigned to the product.

[0017] The second attribute information identification unit 120 is information based on the first attribute information extracted by the first attribute information extraction unit 110. The second attribute information is identified, for example, by performing one or a combination of extension, conversion, and estimation processing on the first attribute information. The second attribute information is then linked to a corresponding customer segment or similar candidate customer segment. Specifically, the second attribute information identification unit 120 may identify character information having a similar concept or meaning to the first attribute information, which is character information, as the second attribute information, and link the second attribute information to the corresponding customer segment or similar candidate customer segment. The second attribute information identification unit 120 may determine whether the character information identified as the second attribute information has a similar concept or meaning to the first attribute information by performing natural language processing.

[0018] The second attribute information identification unit 120 processes the first attribute information so that the similar customer segment estimation unit 130 (described later) can match the customer segment with the similar customer candidate segment. For example, one aspect of such second attribute information is a psychographic attribute expanded based on the first attribute information. In such a case, psychographic attributes are obtained based on the first attribute information of the customer segment. Furthermore, psychographic attributes are obtained based on the first attribute information of the similar customer candidate segment. If the first attribute information is the name of the store where the customer purchased the product, the second attribute information may be, for example, a word that indicates the image of the store, which is expanded from the name of the store where the customer purchased the product. Specifically, if the first attribute information is "home improvement store," the second attribute information may be "DIY," "pets," "tools," etc. The second attribute information identification unit 120 is configured to identify the second attribute information upon acquiring the first attribute information. The timing at which the second attribute information identification unit 120 identifies the second attribute information is not particularly limited.

[0019] The similar customer segment estimation unit 130 estimates a similar customer segment from the similar customer segment by comparing the second attribute information of the customer segment with the second attribute information of the similar customer candidate segment. The similar customer segment is a plurality of customers similar to the customer segment. For example, the similar customer segment estimation unit 130 compares the second attribute information of the customer segment with the second attribute information of the similar customer candidate segment, and extracts, as the similar customer segment, a similar customer segment associated with second attribute information similar to the second attribute information of the customer segment. The method of determining the similarity between the second attribute information of the customer segment and the second attribute information of the similar customer candidate segment may be performed using existing technology. For example, the similarity may be determined by calculating the degree of association between the second attribute information of the customer segment and the second attribute information of the similar customer candidate segment.

[0020] Here, the consumption behavior information of the similar customer candidate group typically includes information different from that of the customer group. Specifically, for example, the consumption behavior history of the customer group is information on receipts from point card members who purchase products at a specific retail store, including information such as the price, product name, and product category of the products purchased at the specific store. On the other hand, the consumption behavior history of the similar customer candidate group is, for example, a payment history of a member who uses a specific payment service, including information on payment history at various stores, but not information on the product name and product category of the products purchased at the time of payment. Because the information included in the consumption behavior information differs, it is difficult to directly compare the first attribute information of the customer group with the first attribute information of the similar customer candidate group. Therefore, the similar customer group estimation device 100 identifies second attribute information of the customer group and the similar customer candidate group, respectively, and compares the second attribute information to estimate the similar customer group from the similar customer candidate group.

[0021] Next, an example of a similar customer segment estimation method according to the present disclosure will be described with reference to FIG. 2 . First, the first attribute information extraction unit 110 extracts first attribute information of a customer segment and a similar customer segment (step S101). Next, the second attribute information identification unit 120 identifies expanded second attribute information based on the first attribute information extracted in step S101 and associates it with the corresponding customer segment or similar customer segment (step S102). Next, the similar customer segment estimation unit 130 compares the second attribute information of the customer segment with the second attribute information of the similar customer segment to estimate a similar customer segment from the similar customer segment (step S103).

[0022] In this way, in the similar customer segment estimation method using the similar customer segment estimation device 100, the expanded second attribute information is identified based on the first attribute information extracted from the consumption behavior information. Therefore, it is possible to compare a customer segment including different types of consumption behavior information with a similar customer segment. The order of steps shown in FIG. 2 is merely an example and can be changed as appropriate. For example, after extracting the first attribute information and identifying the second attribute information of the customer segment, the first attribute information of the similar customer segment and identifying the second attribute information of the similar customer segment may be extracted.

[0023] In the above example, the second attribute information of the customer segment and the similar customer candidate segment is respectively identified, and the similar customer segment is estimated from the similar customer candidate segment by comparing the second attribute information. However, the data held by the customer segment and the similar customer candidate segment may be expanded so that one data item is consistent with the other data item, and then the comparison may be performed. Specifically, for example, if the second attribute information is previously associated with the customer segment as a data item, the similar customer segment estimation device 100 may extract the first attribute information and identify the second attribute information only for the similar customer candidate segment.

[0024] The similar customer group estimation device 100 includes a processor, memory, and storage device (not shown). The storage device stores a computer program that implements the processing of the similar customer group estimation method according to this embodiment. The processor then loads the computer program from the storage device into the memory and executes the computer program. As a result, the processor realizes the functions of the first attribute information extraction unit 110, the second attribute information identification unit 120, and the similar customer group estimation unit 130.

[0025] Alternatively, each component of the similar customer group estimation device 100 may be realized by dedicated hardware. Furthermore, some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination thereof. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and a program. Furthermore, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), a quantum processor (quantum computer control chip), etc. may be used as the processor.

[0026] Furthermore, when some or all of the components of the similar customer group estimation device 100 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in a form in which each is connected via a communication network. Furthermore, the functions of the similar customer group estimation device 100 may be provided in a SaaS (Software as a Service) format.

[0027] <Embodiment 2> Next, an example configuration of a similar customer group estimation system 200 will be described with reference to Figure 3. The similar customer group estimation system 200 is an information system that estimates a similar customer group using the consumption behavior history of customers held by a payment service provider. Specifically, the similar customer group estimation system 200 estimates a similar customer group using the usage history of a predetermined payment service. The payment method for the predetermined payment service is not particularly limited, and may be, for example, credit card payment, debit card payment, electronic money payment, QR code (registered trademark) payment, etc.

[0028] The similar customer group estimation system 200 includes a similar customer group candidate database 300 and a similar customer group estimation device 400. The similar customer group candidate database 300 and the similar customer group estimation device 400 are communicably connected via a network 500. Here, the network 500 is a wired or wireless communication line, and may include the Internet.

[0029] The similar customer candidate database 300 is a database that stores information about similar customer candidate groups. In the example shown in FIG. 3 , the similar customer candidate group is a plurality of customers who have registered to use payment services provided by a payment service provider. The similar customer candidate database 300 stores basic attribute information 301, payment service usage history 302, first attribute information 303, and second attribute information 304, linked to the basic attribute information 301. The basic attribute information 301 is basic attribute information of each customer who has registered to use the payment service. The basic attribute information 301 may include a customer ID. The customer ID is information for identifying customers of the payment service provider, and is, for example, a unique number assigned to each customer. When the consumer behavior information includes a customer ID, the ID is linked to and managed with the basic attribute information 301, payment service usage history 302, first attribute information 303, second attribute information 304, etc. The payment service usage history 302 is a history of payments made by each customer using the payment service. The first attribute information 303 is information included in the usage history of the payment service, such as the name, address, and type of business of the store where the customer used the payment service, the purchase amount at the store, etc. The second attribute information 304 is a psychographic attribute expanded based on the first attribute information 303.

[0030] Next, an example configuration of a service request device 600 capable of communicating with the similar customer group estimation system 200 will be described with reference to Fig. 4. As shown in Fig. 4, the similar customer group estimation system 200 is connected to the service request device 600. The service request device 600 is an information processing device that requests the similar customer group estimation system 200 to estimate a similar customer group, and is installed, for example, in a receipt collection company. As will be described in detail later, the service request device 600 transmits consumption behavior information of a customer group whose latent consumption tendency is to be estimated to the similar customer group estimation system 200, and receives a latent consumption tendency list from the similar customer group estimation system 200.

[0031] The service request device 600 includes a consumer behavior information database 610, a consumer behavior information transmitting unit 620, and a latent consumer tendency list receiving unit 630. The consumer behavior information database 610 stores consumer behavior information that links basic attribute information 611 with receipts 612. The basic attribute information 611 is basic attribute information of customers of the receipt collection company, i.e., people participating in the receipt collection business. The consumer behavior information may include a customer ID to identify each customer. If the consumer behavior information includes a customer ID, the basic attribute information 611 and receipts 612 are linked to the ID and managed. The receipts 612 are receipts registered by each customer in the receipt collection business and include information written on the receipt, such as the name of the store where the product was purchased, the date and time, the product name, the product price, and the total price. The consumer behavior information transmitting unit 620 is a communication means that transmits the consumer behavior information stored in the consumer behavior information database 610 to the similar customer group estimation system 200. The similar customer group estimation system 200 is configured to output a latent consumption inclination list upon receiving the consumption behavior information. The latent consumption inclination list receiving unit 630 is a communication means for receiving the latent consumption inclination list from the similar customer group estimation system 200.

[0032] Next, an example configuration of a similar customer group estimation device 400 will be described with reference to FIG. 5 . The similar customer group estimation device 400 is an example of the similar customer group estimation device 100 described above. The similar customer group estimation device 400 is an information processing device that performs identification and linking of attribute information and similar customer group estimation processing, and is, for example, a server device realized by a computer. The similar customer group estimation device 400 may be redundantly configured with multiple servers, and each functional block may be realized by multiple computers. The similar customer group estimation device 400 includes a memory 410, a communication unit 420, a storage unit 430, and a control unit 440.

[0033] The memory 410 is a storage area that temporarily stores the processing contents of the control unit 440, and is a volatile storage device such as a RAM (Random Access Memory). The communication unit 420 is an interface that communicates with the outside of the similar customer group estimation device 400. The storage unit 430 is a storage device that stores a program 431 and the like. The program 431 is a computer program that implements the similar customer group estimation process according to the present disclosure.

[0034] The control unit 440 includes an input receiving unit 441, a first attribute information extraction unit 442, a second attribute information identification unit 443, a similar customer group estimation unit 444, and a latent consumption tendency estimation unit 445. The control unit 440 is a control device that controls the operation of the similar customer group estimation device 400, and is, for example, a processor such as a CPU. The control unit 440 loads the program 431 from the storage unit 430 into the memory 410 and executes it. In this way, the control unit 440 realizes the functions of the input receiving unit 441, the first attribute information extraction unit 442, the second attribute information identification unit 443, the similar customer group estimation unit 444, and the latent consumption tendency estimation unit 445.

[0035] As preprocessing for the similar customer layer estimation process, the similar customer layer estimation device 400 links first attribute information and second attribute information to a similar customer candidate layer. Specifically, the first attribute information extraction unit 442 extracts first attribute information from the consumption behavior information of the similar customer candidate layer stored in the similar customer candidate layer database 300, links the first attribute information to the basic attribute information 301, and stores the second attribute information in the similar customer candidate layer database 300. Then, the second attribute information identification unit 443 links the attribute information expanded based on the first attribute information extracted by the first attribute information extraction unit 442 as second attribute information to the basic attribute information 301 and stores the second attribute information in the similar customer candidate layer database 300.

[0036] When requesting estimation of a similar customer group, the service request device 600 transmits consumption behavior information, including receipts of a customer group whose latent consumption tendency is to be estimated, to the similar customer group estimation device 400. Upon receiving the consumption behavior information, the input receiving unit 441 accepts input of the consumption behavior information. The first attribute information extraction unit 442 extracts first attribute information from the consumption behavior information accepted by the input receiving unit 441 and associates the first attribute information with the corresponding customer group. The second attribute information identification unit 443 identifies attribute information expanded based on the first attribute information extracted by the first attribute information extraction unit 442 as second attribute information and associates the second attribute information with the corresponding customer group.

[0037] The similar customer segment estimation unit 444 compares the second attribute information of the customer segment with the second attribute information of the similar customer candidate segment and estimates a similar customer segment from the similar customer candidate segment. Specifically, the similarity between the second attribute information of the customer segment and the second attribute information of the similar customer candidate segment is calculated, and multiple individuals in the similar customer candidate segment with a predetermined similarity or higher are identified as the similar customer segment. For example, the similar customer segment estimation unit 444 first determines whether each of multiple words in the second attribute information of the customer segment is similar to each of multiple words in the second attribute information of the similar customer candidate segment. In this case, similar words are assigned a "1" and dissimilar words are assigned a "0." Next, for each of the multiple words in the second attribute information of the customer segment, the similar customer segment estimation unit 444 adds up the numerical values ​​assigned to each of the multiple words in the second attribute information of the similar customer candidate segment and divides the sum by the number of words in the second attribute information of the similar customer candidate segment. This calculates the relevance of the second attribute information of the similar customer candidate layer to each of the multiple words that are the second attribute information of the customer layer. Next, the similar customer layer estimation unit 444 calculates the similarity between the second attribute information of the customer layer and the second attribute information of the similar customer candidate layer by calculating the average value of the relevance assigned to the multiple words that are the second attribute information of the customer layer.

[0038] The similar customer segment estimation unit 444 may compare the first attribute information and the second attribute information of the customer segment with the first attribute information and the second attribute information of the similar customer candidate segment, and estimate a similar customer segment from the similar customer candidate segment. The similar customer segment estimation unit 444 may first narrow down the similar customer candidate segment to a certain extent based on the basic attribute information of the customer segment, and then compare the second attribute information of the customer segment with the second attribute information of the similar customer candidate segment. The similar customer segment estimation unit 444, for example, calculates the similarity between the basic attribute information of the customer segment and the basic attribute information of the similar customer candidate segment, and narrows down the similar customer candidate segment to similar customer candidate segments having a similarity equal to or greater than a predetermined value. The calculation of the similarity between the basic attribute information of the customer segment and the basic attribute information of the similar customer candidate segment may be performed using a procedure similar to that used for calculating the similarity between the second attribute information of the customer segment and the second attribute information of the similar customer candidate segment. The potential consumption inclination estimation unit 445 estimates the potential consumption inclination of the customer group based on the payment service usage history 302 of the similar customer group estimated by the similar customer group estimation unit 444. The potential consumption inclination estimation unit 445 transmits the estimation result to the service request device 600 as a potential consumption inclination list.

[0039] Next, an example of the operation of the similar customer group estimation system 200 during preprocessing, i.e., when linking attribute information to a similar customer group, will be described with reference to Figure 6. First, the similar customer group database 300 transmits the consumption behavior information of the similar customer group stored in the similar customer group database 300 to the similar customer group estimation device 400 (step S201). Here, the consumption behavior information of the similar customer group is obtained by linking the basic attribute information of the similar customer group with the payment service usage history.

[0040] FIG. 7 is an example of consumption behavior information stored in the similar customer candidate layer database 300. The consumption behavior information shown in FIG. 7 is an example of a usage history transmitted to the similar customer candidate layer estimation device 400 as consumption behavior information for one person. The consumption behavior information of the similar customer candidate layer shown in FIG. 7 is obtained by linking the history of purchases of products or services made by each similar customer candidate using a predetermined payment service within a predetermined period of time to the basic attribute information of the corresponding similar customer candidate layer. In the example shown in FIG. 7, only purchase histories at physical stores are listed, but the consumption behavior information of the similar customer candidate layer may also include purchase histories at online stores.

[0041] The basic attribute information of the similar customer candidate group typically includes information that cannot be used alone to identify an individual, such as the age and gender of each similar customer candidate. Furthermore, from the perspective of protecting personal information, the basic attribute information of the similar customer candidate group does not include personal information such as the address or name of each similar customer candidate. In the example shown in Figure 7, the payment service usage history of the similar customer candidate group is a history of payments made by each similar customer candidate using a specified payment service, and includes the name of the store where the payment was made, the payment amount, and the business type of the store where the payment was made. The business type is a business type assigned by a payment service provider to the store where the similar customer candidate made a payment. Payment service providers typically assign a business type category indicating the business type of each affiliated store to affiliated stores that have introduced a payment system using the payment service provided by the payment service provider.

[0042] Returning to Fig. 6, the explanation will be continued. The first attribute information extraction unit 442 extracts first attribute information from the consumption behavior information received in step S201 (step S202). For example, when the first attribute information extraction unit 442 receives the consumption behavior information shown in Fig. 7, it extracts the name of the store where the similar customer candidate made a payment and the business type of the store as the first attribute information. Next, the first attribute information extraction unit 442 links the first attribute information to the corresponding similar customer candidate and registers the first attribute information in the similar customer candidate database 300 (step S203).

[0043] Next, the second attribute information identification unit 443 identifies second attribute information based on the first attribute information extracted in step S202 (step S204). Specifically, the second attribute information identification unit 443 identifies keywords expanded based on the first attribute information as second attribute information. Next, the second attribute information identification unit 443 links the second attribute information to the corresponding similar customer candidate and registers them in the similar customer candidate database 300 (step S205). The similar customer group estimation device 400 performs each of the processes in steps S202 to S205 on the consumption behavior information of multiple similar customer candidates.

[0044] Next, with reference to FIG. 8 , an example of the operation of the similar customer group estimation system 200 during this process, i.e., when estimating a similar customer group, will be described. First, the consumption behavior information transmission unit 620 transmits consumption behavior information of a customer group whose latent consumption tendency is to be estimated to the similar customer group estimation device 400 (step S301). FIG. 9 shows an example of consumption behavior information of a customer group whose latent consumption tendency is to be estimated. The consumption behavior information shown in FIG. 9 is an example of a usage history transmitted to the similar customer group estimation device 400 as consumption behavior information for one person. The consumption behavior information of the customer group shown in FIG. 9 is receipts that each customer registered with a predetermined receipt collection business within a predetermined period. Specifically, the consumption behavior information of the customer group is obtained by linking receipt information to basic attribute information of the customer group.

[0045] The basic attribute information of the customer segment typically includes information that cannot be used alone to identify an individual, such as the age and gender of each customer. Furthermore, from the perspective of protecting personal information, the basic attribute information of the customer segment does not include personal information such as the address or name of each customer. In the example shown in FIG. 9, the receipt information of the customer segment is information on receipts registered by each customer in a designated receipt collection business, and includes the name of the store where the product or service was purchased, the total amount, the product name, and the product price. Furthermore, although the example shown in FIG. 9 only includes receipts from physical stores, the consumption behavior information of the customer segment may also include receipts from online stores.

[0046] Returning to FIG. 8 , the explanation will be continued. The first attribute information extraction unit 442 extracts first attribute information from the consumption behavior information received in step S301 (step S302). For example, when the first attribute information extraction unit 442 receives the consumption behavior information shown in FIG. 9 , it extracts the name of the store where the customer purchased the product or service, the product name, etc., as the first attribute information. Next, the second attribute information identification unit 443 identifies second attribute information based on the first attribute information extracted in step S302 (step S303). The similar customer group estimation device 400 performs each of the processes in steps S302 to S303 on the consumption behavior information of multiple customers that make up the customer group.

[0047] Next, the similar customer segment estimation unit 444 narrows down the similar customer segment based on the basic attribute information of the customer segment (step S304). Specifically, the similar customer segment estimation unit 444 compares the basic attribute information of the customer segment included in the consumption behavior information received in step S301 with the basic attribute information of the similar customer segment stored in the similar customer segment database 300, and extracts similar customer segments whose basic attribute information is similar to the customer segment. Next, the similar customer segment estimation unit 444 requests the similar customer segment database 300 to provide first attribute information and second attribute information of the similar customer segment narrowed down in step S304 (step S305). In response to the request received in step S305, the similar customer segment database 300 transmits the first attribute information and second attribute information of the similar customer segment narrowed down in step S304 to the similar customer segment estimation device 400 (step S306).

[0048] Next, the similar customer segment estimation unit 444 estimates a similar customer segment from the similar customer segment narrowed down in step S304 (step S307). Specifically, the similar customer segment estimation unit 444 compares the first attribute information and second attribute information of the customer segment with the first attribute information and second attribute information of the similar customer segment narrowed down in step S304, and estimates a similar customer segment with a high degree of similarity as a similar customer segment. In the examples shown in FIGS. 7 and 9 , the first attribute information of the customer segment and the similar customer segment both includes the store name. In this way, when the first attribute information of the customer segment and the similar customer segment includes common information, the similar customer segment estimation unit 444 may estimate a similar customer segment by comparing the first attribute information in addition to comparing the second attribute information.

[0049] Next, the latent consumption inclination estimation unit 445 estimates the latent consumption inclination of the customer group based on the consumption behavior information of the similar customer group estimated in step S307 (step S308). For example, the latent consumption inclination estimation unit 445 may estimate the consumption inclination of the customer group at a specific event based on the consumption behavior information of the similar customer group at the past specific event as the latent consumption inclination. In the example shown in FIG. 9 , the consumption behavior information of the similar customer group includes information on products purchased by the similar customer group. Therefore, the latent consumption inclination estimation unit 445 can output a list of products that the customer group is likely to purchase based on the information on products purchased by the similar customer group as a latent consumption inclination list. Specifically, for example, if the similar customer group purchased a baking kit during last year's Valentine's Day shopping season, the latent consumption inclination estimation unit 445 may estimate that the customer group is likely to purchase a baking kit during this year's Valentine's Day shopping season. The latent consumption inclination estimation unit 445 transmits the latent consumption inclination list estimated in step S308 to the service request device 600 (step S309).

[0050] In this way, the similar customer segment estimation method using the similar customer segment estimation system 200 identifies the second attribute information of the customer segment and the similar customer segment. Therefore, although the consumption behavior information linked to the customer segment and the similar customer segment is different, the customer segment and the similar customer segment can be compared.

[0051] Furthermore, the similar customer group estimation system 200 estimates similar customers linked to different types of consumption behavior information from the customer group, and is therefore able to estimate types of latent consumption tendencies that cannot be estimated from the customer group alone. Specifically, in the above example, the customer group is users of a payment service, and the consumption behavior information of the customer group does not include the product names of the individual products purchased. On the other hand, the similar customer group is participants in a receipt collection business, and the consumption behavior information of the similar customer group includes the product names of the individual products purchased. Therefore, the similar customer group estimation system 200 can estimate, as the latent consumption tendencies, a list of product names that the customer group is likely to purchase.

[0052] In the above example, the similar customer segment is estimated after narrowing down the similar customer candidate segments to some extent using basic attribute information. Therefore, the amount of calculation required to estimate the similar customer segment is smaller than when comparing all similar customer candidate segments with the customer segment.

[0053] In the above example, the estimated latent consumption propensity is transmitted as a list to the service request device 600, but the method for outputting the latent consumption propensity is not limited to this. For example, the similar customer group estimation system 200 may transmit the estimated latent consumption propensity to an external device. Here, an example of the external device is a policy generation device that generates management policies based on the latent consumption propensity.

[0054] In the above example, the first attribute information and the second attribute information of the similar customer candidate layer are stored in a database in advance, but the first attribute information and the second attribute information of the similar customer candidate layer may be extracted or identified when they become necessary for processing. For example, after receiving consumption behavior information of the customer layer from the service request device 600, the similar customer layer estimation device 400 may extract the first attribute information and identify the second attribute information of the similar customer candidate layer and compare it with the second attribute information of the customer layer.

[0055] <Embodiment 3> Next, an example configuration of a similar customer segment estimation system 800 will be described with reference to Fig. 10. The similar customer segment estimation system 800 is an information system that estimates similar customer segments using customer consumption behavior histories held by a receipt collection company. Specifically, the similar customer segment estimation system 200 estimates similar customer segments using receipts registered by participants in a specified receipt collection business.

[0056] The similar customer group estimation system 800 differs from the similar customer group estimation system 200 shown in FIG. 3 in that it includes a similar customer group database 1000 instead of the similar customer group database 300. The similar customer group database 1000 stores basic attribute information 1001, receipts 1002, first attribute information 1003, and second attribute information 1004 in association with each other. The basic attribute information 1001 is basic attribute information for each customer who has registered to participate in the receipt collection business. The receipts 1002 are receipts registered by participants in the receipt collection business. The first attribute information 1003 is information included in the receipts 1002, etc., such as the name of the store where the customer purchased the product included in the registered receipt, the date and time, the product name, the product price, and the total price. The second attribute information 1004 is a psychographic attribute expanded based on the first attribute information 1003.

[0057] Next, with reference to FIG. 11 , an example configuration of a service request device 1100 capable of communicating with the similar customer group estimation system 800 will be described. As shown in FIG. 11 , the similar customer group estimation system 800 is connected to the service request device 1100. The service request device 1100 differs from the service request device 600 shown in FIG. 4 in that it includes a consumer behavior information database 1110 instead of the consumer behavior information database 610. The consumer behavior information database 1110 stores consumer behavior information that is linked to basic attribute information 1111 and a payment service usage history 1112. The basic attribute information 1111 is basic attribute information of customers of the payment service provider, i.e., people who have registered to use the payment service. The payment service usage history 1112 is a history of payments made by each customer using the payment service, and includes, for example, the name, address, and business type of the store where the customer used the payment service, as well as the purchase amount at the store.

[0058] The similar customer group estimation system 800 performs pre-processing, i.e., linking attribute information to similar customer candidate groups, in the same procedure as that described in Fig. 6. The similar customer group estimation system 800 also performs main processing, i.e., estimating similar customer groups, in the same procedure as that described in Fig. 8.

[0059] In the above example, the customer group is comprised of participants in a receipt collection business, and the customer consumption behavior information includes only information on receipts registered by the customer. On the other hand, the similar customer group is comprised of users of a payment service, and the consumption behavior information of the similar customer group includes purchase histories from multiple stores. Therefore, the similar customer group estimation system 800 can estimate a list of products and services sold in multiple business categories as potential consumption tendencies.

[0060] Fourth Embodiment Next, an example configuration of a similar customer segment estimation system 1300 will be described with reference to FIG. 12 . The similar customer segment estimation system 1300 is an information system for linking a customer segment with a related customer segment that significantly differs in the types of data included in the consumption behavior information. The similar customer segment estimation system 1300 estimates a similar customer segment from a similar customer candidate segment whose consumption behavior information includes data similar to that of a customer segment, and estimates a related customer segment from a related customer candidate segment whose consumption behavior information includes data similar to that of a similar customer segment. Specifically, the similar customer segment estimation system 1300 is an information system that estimates a similar customer segment using customer consumption behavior histories held by a receipt collection company and estimates a related customer segment using customer consumption behavior histories held by a payment service provider. Specifically, the similar customer segment estimation system 1300 estimates a similar customer segment using receipts registered by participants in a specified receipt collection business and estimates a related customer segment similar to the similar customer segment using payment histories of payment service users who have used the payment service. The related customer group is a plurality of customers who are similar to the similar customer group.

[0061] The similar customer group estimation system 1300 differs from the similar customer group estimation system 800 shown in FIG. 10 in that it includes a similar customer group estimation device 1400 instead of the similar customer group estimation device 400, and further includes a related customer group candidate database 1500. The related customer group candidate database 1500 stores basic attribute information 1501, payment service usage history 1502, first attribute information 1503, and second attribute information 1504 in association with each other. The related customer group candidate is a plurality of customers who may be related customers similar to the similar customer group. The basic attribute information 1501 is basic attribute information of each related customer candidate who has registered to use the payment service. The payment service usage history 1502 is a history of payments made by each related customer candidate using the payment service. The first attribute information 1503 is information included in the payment service usage history, such as the name, address, and business type of the store where the related customer candidate used the payment service, and the purchase amount at the store. The second attribute information 1504 is a psychographic attribute expanded based on the first attribute information 1503 .

[0062] Next, a configuration example of a service request device 1600 capable of communicating with the similar customer group estimation system 1300 will be described with reference to FIG. 13 . As shown in FIG. 11 , the similar customer group estimation system 1300 is connected to the service request device 1600. The service request device 1600 differs from the service request device 1100 shown in FIG. 11 in that it includes a consumer behavior information database 1610 instead of the consumer behavior information database 1110. The consumer behavior information database 1610 stores consumer behavior information that is obtained by linking basic attribute information 1611 with receipts 1612. The basic attribute information 1611 is basic attribute information of customers of a retail store, i.e., people who are registered as members at the retail store. The receipts 1612 are receipts for purchases of goods and services by each customer at the retail store, and include information such as the price, product name, and product category of the goods purchased at the retail store.

[0063] Next, an example configuration of a similar customer group estimation device 1400 will be described with reference to Fig. 14. The similar customer group estimation device 1400 differs from the similar customer group estimation device 400 shown in Fig. 3 in that it includes a control unit 1440 instead of the control unit 440. The control unit 1440 includes a related customer group estimation unit 1446 in addition to the configuration of the control unit 440. The related customer group estimation unit 1446 estimates a related customer group similar to a similar customer group from a candidate related customer group.

[0064] Next, an example of the operation of the similar customer group estimation system 1300 during preprocessing, i.e., when linking attribute information to similar candidate customer groups and related candidate customer groups, will be described with reference to Figure 15. First, the similar candidate customer group database 1000 transmits the consumption behavior information of similar candidate customer groups stored in the similar candidate customer group database 1000 to the similar customer group estimation device 1400 (step S601). Here, the consumption behavior information of similar candidate customer groups is information in which receipts are linked to basic attribute information of similar candidate customer groups.

[0065] The first attribute information extraction unit 442 extracts first attribute information from the consumption behavior information received in step S601 (step S602). Next, the first attribute information extraction unit 442 associates the first attribute information with the corresponding similar customer candidate and registers them in the similar customer candidate database 1000 (step S603). Next, the second attribute information identification unit 443 identifies second attribute information based on the first attribute information extracted in step S602 (step S604). Next, the second attribute information identification unit 443 associates the second attribute information with the corresponding similar customer candidate and registers them in the similar customer candidate database 1000 (step S605). The similar customer group estimation device 1400 performs each of the processes in steps S602 to S605 on the consumption behavior information of multiple similar customer candidates.

[0066] Next, the related candidate customer database 1500 transmits the consumption behavior information of the related candidate customer stored in the related candidate customer database 1500 to the similar customer group estimation device 1400 (step S606). Here, the consumption behavior information of the related candidate customer is information in which the basic attribute information of the related candidate customer is linked to the payment service usage history.

[0067] The first attribute information extraction unit 442 extracts first attribute information from the consumption behavior information received in step S606 (step S607). Next, the first attribute information extraction unit 442 associates the first attribute information with the corresponding related customer candidate and registers them in the related customer candidate database 1500 (step S608). Next, the second attribute information identification unit 443 identifies second attribute information based on the first attribute information extracted in step S607 (step S609). Next, the second attribute information identification unit 443 associates the second attribute information with the corresponding related customer candidate and registers them in the related customer candidate database 1500 (step S610). The similar customer group estimation device 1400 performs each of the processes in steps S602 to S605 on the consumption behavior information of multiple related customer candidates.

[0068] Next, with reference to FIG. 16 , an example of the operation of the similar customer group estimation system 1300 during this process, i.e., when estimating a similar customer group and a related customer group, will be described. First, the consumer behavior information transmission unit 620 transmits consumer behavior information of a customer group whose latent consumption propensity is to be estimated to the similar customer group estimation device 1400 (step S701). FIG. 17 shows an example of consumer behavior information of a customer group whose latent consumption propensity is to be estimated. The consumer behavior information shown in FIG. 17 is an example of consumer behavior information transmitted to the similar customer group estimation device 1400 as consumer behavior information for one person. The consumer behavior information of the customer group shown in FIG. 17 is obtained by linking receipts from each customer who purchased goods or services at a specified retail store within a specified period of time with basic attribute information of the corresponding customer. In the example shown in FIG. 17 , the customer group is people who are registered members of the specified retail store.

[0069] 16 , the explanation will be continued. The first attribute information extraction unit 442 extracts and links first attribute information from the consumption behavior information received in step S701, and the second attribute information identification unit 443 identifies and links second attribute information based on the extracted first attribute information (step S702). The similar customer group estimation device 400 performs the process of step S702 for each of the consumption behavior information of multiple customers that make up the customer group.

[0070] Next, the similar customer layer estimation unit 444 narrows down the similar customer candidate layer based on the basic attribute information of the customer layer (step S703). Next, the similar customer layer estimation unit 444 requests the similar customer candidate layer database 1000 for first attribute information and second attribute information of the similar customer candidate layer narrowed down in step S703 (step S704). In response to the request received in step S704, the similar customer candidate layer database 1000 transmits the first attribute information and second attribute information of the similar customer candidate layer narrowed down in step S703 to the similar customer layer estimation device 1400 (step S705). Next, the similar customer layer estimation unit 444 estimates a similar customer layer from the similar customer candidate layer narrowed down in step S703 (step S706).

[0071] Next, the related customer segment estimation unit 1446 narrows down the related candidate customer segment based on the basic attribute information of the customer segment (step S707). Next, the related customer segment estimation unit 1446 requests the related candidate customer segment database 1500 for first attribute information and second attribute information of the related candidate customer segment narrowed down in step S707 (step S708). In response to the request received in step S707, the related candidate customer segment database 1500 transmits the first attribute information and second attribute information of the related candidate customer segment narrowed down in step S707 to the similar customer segment estimation device 1400 (step S709). Next, the related customer segment estimation unit 1446 estimates related customer segments from the related candidate customer segment narrowed down in step S707 (step S710).

[0072] Next, the latent consumption inclination estimation unit 445 estimates the latent consumption inclination of the customer segment based on the consumption behavior information of the related customer segment estimated in step S710 (step S711). For example, if the related customer segment is a user of a payment service, the consumption behavior information of the related customer segment includes the payment history of the related customer segment at various stores. Therefore, the latent consumption inclination estimation unit 445 can output a latent consumption inclination list of business types of products and services that the customer segment is likely to purchase, based on the business types of stores where the related customer segment has made payments. The latent consumption inclination estimation unit 445 transmits the latent consumption inclination list estimated in step S711 to the service request device 1600 (step S712).

[0073] In the above example, the customer segment is a registered member of a specific retail store, and the customer segment's consumer behavior information includes only receipt information from purchases made by the customer at the specific retail store. Meanwhile, the related customer segment is a user of a payment service, and the related customer segment's consumer behavior information includes purchase histories from multiple stores. Therefore, by estimating the potential consumer propensity using the consumer behavior information of the related customer segment, it is possible to estimate a list of products and services sold in multiple business categories as the potential consumer propensity. However, the consumer behavior information of the related customer segment does not include information such as the names of individual products purchased during payment, making it difficult to accurately determine the degree of similarity with the consumer behavior information of the customer segment. Therefore, by using a similar customer candidate segment, which includes receipt information from a small number of stores as consumer behavior information, to estimate a similar customer segment similar to the customer segment, and then estimating a related customer segment similar to the similar customer segment, the potential consumer propensity can be accurately estimated. Accurately estimating the potential consumer propensity in this way allows users to develop products in line with the potential consumer propensity.

[0074] <Other Embodiments, etc.> When performing output in each embodiment, the display content may be changed based on information about the display to which the output is made. Examples of display information include the size of the display and the ratio of the vertical length to the horizontal length of the display. Based on the display information, the display content may be changed, for example, so that the larger the display size, the larger the size of characters, graphs, and other figures. In this case, an upper limit may be set so that the display content is not displayed larger than a predetermined size on the display. Similarly, the smaller the display size, the smaller the size of characters, graphs, and other figures. Furthermore, a lower limit may be set so that the display content is not displayed smaller than a predetermined size on the display. In addition, the display position may be changed, or certain items may not be displayed on the same screen.

[0075] In another aspect, the display content may be changed depending on the processing power of the information processing device that performs the processing for displaying on the display. For example, when the processing power of the information processing device is low, the content to be displayed or the amount of information to be displayed may be reduced compared to when the processing power is high. Regarding the processing power, predetermined specifications such as the memory size of the information processing device may be referenced, or the operating status or task execution status of the processor of the information processing device may be referenced.

[0076] <Example of Hardware Configuration> Hereinafter, with reference to FIG. 18 , a case where each functional configuration of the similar customer group estimation device according to the present disclosure is realized by a combination of hardware and software will be described.

[0077] The similar customer group estimation device according to the present disclosure can achieve the above-described functions using a computer 11 including the hardware configuration shown in the figure. The computer 11 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 11 may be a dedicated computer designed to realize each device, or may be a general-purpose computer. The computer 11 can achieve the desired functions by installing a predetermined program.

[0078] The computer 11 has a bus 21, a processor 30, a memory 40, a storage device 50, an input / output interface 60 (an interface is also called an I / F (Interface)), and a network interface 70. The bus 21 is a data transmission path through which the processor 30, the memory 40, the storage device 50, the input / output interface 60, and the network interface 70 transmit and receive data to and from each other. However, the method of connecting the processor 30 and the like to each other is not limited to bus connection.

[0079] The processor 30 is a processor such as a CPU, a GPU, an FPGA, etc. The memory 40 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0080] The storage device 50 is an auxiliary storage device realized using a hard disk, SSD, memory card, ROM (Read Only Memory), etc. The storage device 50 stores programs for realizing desired functions. The processor 30 reads these programs into the memory 40 and executes them to realize the various functional components of each device.

[0081] The input / output interface 60 is an interface for connecting the computer 11 with input / output devices. For example, the input / output interface 60 is connected to an input device such as a keyboard and an output device such as a display device.

[0082] The network interface 70 is an interface for connecting the computer 11 to a network.

[0083] Although an example of a hardware configuration for the present disclosure has been described above, the above-described embodiment is not limited to this. Any processing in the present disclosure can also be realized by causing a processor to execute a computer program.

[0084] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0085] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0086] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0087] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0088] (Appendix A1) A similar customer segment estimation device comprising: a first attribute information extraction means for extracting first attribute information for at least one of a customer segment whose latent consumption tendency is desired to be estimated and a similar customer segment that may be a similar customer segment similar to the customer segment; a second attribute information identification means for identifying second attribute information extended based on the extracted first attribute information and linking the second attribute information to at least one of the customer segment and the similar customer segment; and a similar customer segment estimation means for estimating a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the second attribute information extended for either the customer segment or the similar customer segment with information previously linked for the other, or by comparing the second attribute information extended for both the customer segment and the similar customer segment.

[0089] (Appendix A2) The similar customer layer estimation device described in Appendix A1, wherein the first attribute information extraction means extracts first attribute information of the customer layer and the similar customer candidate layer; the second attribute information identification means identifies second attribute information based on the first attribute information of the customer layer and links it to the customer layer, and identifies second attribute information based on the first attribute information of the similar customer candidate layer and links it to the similar customer candidate layer; and the similar customer layer estimation means compares the second attribute information of the customer layer with the second attribute information of the similar customer candidate layer to estimate a similar customer layer similar to the customer layer from the similar customer candidate layer.

[0090] (Appendix A3) The similar customer segment estimation device according to Appendix A2, further comprising an input receiving means for receiving input of consumption behavior information of the customer segment, wherein the first attribute information extraction means extracts first attribute information included in the input consumption behavior information, and extracts first attribute information included in consumption behavior information of a similar customer candidate segment registered in a predetermined database.

[0091] (Appendix A4) The similar customer segment estimation device according to Appendix A3, further comprising: a latent consumption inclination estimation means for estimating a latent consumption inclination based on the consumption behavior information of the similar customer segment.

[0092] (Appendix A5) The similar customer segment estimation device according to any one of Appendices A1 to A4, wherein the similar customer segment estimation means narrows down the similar customer segment to a certain extent based on basic attribute information of the customer segment and the similar customer segment, and estimates the similar customer segment from the narrowed down similar customer segment.

[0093] (Appendix A6) The similar customer group estimation device according to any one of Appendices A2 to A5, wherein the similar customer group estimation means estimates the similar customer group from the similar customer group candidate by comparing the first attribute information and the second attribute information of the customer group with the first attribute information and the second attribute information of the similar customer group candidate.

[0094] (Appendix A7) A similar customer group estimation device described in any of Appendices A3 to A6, wherein the consumption behavior information of the customer group includes information indicating the business type of the store where the customer group performed consumption behavior, the consumption behavior information of the similar customer group includes information on products purchased by the similar customer group, and the latent consumption tendency estimation means estimates information on products that the customer group may purchase as the latent consumption tendency.

[0095] (Appendix A8) A similar customer group estimation device described in any of Appendices A3 to A6, wherein the consumption behavior information of the customer group includes information on products purchased by the customer group, the consumption behavior information of the similar customer candidate group includes information indicating the business type of the store where the similar customer candidate group has engaged in consumption behavior, and the latent consumption tendency estimation means estimates information on the business type where the customer group may engage in consumption behavior as the latent consumption tendency.

[0096] (Appendix A9) The similar customer segment estimation device according to any one of Appendices A3 to A8, further comprising a related customer segment estimation means for estimating a related customer segment similar to the similar customer segment based on the second attribute information, wherein the latent consumption tendency estimation means estimates the latent consumption tendency of the customer segment based on the consumption behavior information of the related customer segment.

[0097] (Supplementary Note A10) The similar customer group estimation device according to any one of Supplementary Notes A3 to A9, wherein the latent consumption inclination estimation means estimates a consumption inclination at a predetermined event as the latent consumption inclination based on consumption behavior information of the similar customer group at the past predetermined event.

[0098] (Appendix A11) A similar customer segment estimation device that, for either a customer segment whose latent consumption tendencies are to be estimated or a similar customer candidate segment that may be a similar customer segment similar to the customer segment, estimates a similar customer segment that is similar to the customer segment from among the similar customer candidate segments by extending the consumption behavior information of one segment to data items that are common to data items included in the consumption behavior information of the other segment and comparing the data items of the one segment with the data items of the other segment.

[0099] (Appendix B1) A similar customer segment estimation system comprising: a similar customer segment database that stores consumption behavior information, first attribute information, and second attribute information for each similar customer segment, linked to basic attribute information of similar customer segment candidates that are likely to be similar customer segments similar to a customer segment; and a similar customer segment estimation device that can communicate with the similar customer segment database, wherein the similar customer segment estimation device comprises: first attribute information extraction means that extracts first attribute information of the customer segment whose latent consumption tendency is to be estimated, and extracts the first attribute information of the similar customer segment; second attribute information identification means that identifies second attribute information based on the first attribute information of the customer segment and links it to the customer segment, and identifies second attribute information based on the first attribute information of the similar customer segment and links it to the similar customer segment; and similar customer segment estimation means that estimates a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the second attribute information of the customer segment with the second attribute information of the similar customer segment.

[0100] (Appendix B2) The similar customer segment estimation system described in Appendix B1, wherein the similar customer segment estimation device further includes an input receiving means for receiving input of consumption behavior information of the customer segment, and the first attribute information extraction means extracts first attribute information included in the input consumption behavior information, and extracts first attribute information included in consumption behavior information of a similar customer candidate segment registered in a predetermined database.

[0101] (Appendix C1) A similar customer segment estimation method, in which a computer extracts first attribute information for at least one of a customer segment whose latent consumption tendency is desired to be estimated and a similar customer segment that is similar to the customer segment; specifies second attribute information extended based on the extracted first attribute information and links the second attribute information to at least one of the customer segment and the similar customer segment; and estimates a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the second attribute information extended for either the customer segment or the similar customer segment with second attribute information previously specified for the other, or by comparing the second attribute information extended for both the customer segment and the similar customer segment.

[0102] (Appendix D1) A similar customer class estimation program that causes a computer to execute the following processes: a process of extracting first attribute information for at least one of a customer class whose latent consumption tendency is desired to be estimated and a similar customer candidate class that may be a similar customer class similar to the customer class; a process of specifying second attribute information extended based on the extracted first attribute information and linking it to at least one of the customer class and the similar customer candidate class; and a process of estimating a similar customer class that is similar to the customer class from the similar customer candidate class by comparing the second attribute information extended for either the customer class or the similar customer candidate class with second attribute information specified in advance for the other, or by comparing the second attribute information extended for both the customer class and the similar customer candidate class.

[0103] Some or all of the elements (e.g., configurations and functions) described in Appendixes A2 to A11 that are dependent on Appendix A1 may also be dependent on Appendix B2, Appendix C1, and Appendix D1 in the same dependency relationship as Appendixes A2 to A11. Some or all of the elements described in any appendix may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0104] This application claims priority based on Japanese Patent Application No. 2024-32784, filed March 5, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0105] REFERENCE SIGNS LIST 100 Similar customer group estimation device 110 First attribute information extraction unit 120 Second attribute information identification unit 130 Similar customer group estimation unit 200, 800, 1300 Similar customer group estimation system 300, 1000 Similar customer candidate group database 301, 1001 Basic attribute information 302 Payment service usage history 1002 Receipt 303, 1003 First attribute information 304, 1004 Second attribute information 400, 1400 Similar customer group estimation device 410 Memory 420 Communication unit 430 Storage unit 431 Program 440, 1440 Control unit 441 Input reception unit 442 First attribute information extraction unit 443 Second attribute information identification unit 444 Similar customer group estimation unit 445 Latent consumption tendency estimation unit 1446 Related customer group estimation unit 500 Network 600, 1100, 1600 Service request device 610, 1110, 1610 Consumption behavior information database 611, 1111, 1611 Basic attribute information 612, 1612 Receipt 1112 Payment service usage history 620 Consumption behavior information transmission unit 630 Latent consumption intention list reception unit 1500 Related customer candidate group database 1501 Basic attribute information 1502 Payment service usage history 1503 First attribute information 1504 Second attribute information 11 Computer 21 Bus 30 Processor 40 Memory 50 Storage device 60 Input / output interface 70 Network interface

Claims

1. A similar customer segment estimation device comprising: a first attribute information extraction means for extracting first attribute information for at least one of a customer segment whose latent consumption tendency is desired to be estimated and a similar customer segment that is similar to the customer segment; a second attribute information identification means for identifying second attribute information extended based on the extracted first attribute information and linking the second attribute information to at least one of the customer segment and the similar customer segment; and a similar customer segment estimation means for estimating a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the second attribute information extended for either the customer segment or the similar customer segment with information previously linked for the other, or by comparing the second attribute information extended for both the customer segment and the similar customer segment.

2. The similar customer segment estimation device according to claim 1, wherein the first attribute information extraction means extracts first attribute information of the customer segment and the similar customer segment; the second attribute information identification means identifies second attribute information based on the first attribute information of the customer segment and links it to the customer segment, and identifies second attribute information based on the first attribute information of the similar customer segment and links it to the similar customer segment; and the similar customer segment estimation means compares the second attribute information of the customer segment with the second attribute information of the similar customer segment, thereby estimating a similar customer segment that is similar to the customer segment from the similar customer segment.

3. The similar customer segment estimation device according to claim 2, further comprising an input receiving means for receiving input of consumption behavior information of the customer segment, wherein the first attribute information extraction means extracts first attribute information included in the input consumption behavior information and extracts first attribute information included in consumption behavior information of a similar customer candidate segment registered in a predetermined database.

4. The similar customer segment estimation device according to claim 3, further comprising a latent consumption tendency estimation means for estimating a latent consumption tendency based on the consumption behavior information of the similar customer segment.

5. A similar customer segment estimation device according to any one of claims 1 to 4, wherein the similar customer segment estimation means narrows down the similar customer segment based on basic attribute information of the customer segment and the similar customer segment candidate, and estimates the similar customer segment from the narrowed down similar customer segment candidate.

6. A similar customer segment estimation device according to any one of claims 2 to 4, wherein the similar customer segment estimation means estimates the similar customer segment from the similar customer segment by comparing the first attribute information and the second attribute information of the customer segment with the first attribute information and the second attribute information of the similar customer segment candidate.

7. A similar customer segment estimation device as described in any one of claims 3 to 6, wherein the consumption behavior information of the customer segment includes information indicating the type of store where the customer segment performed consumption behavior; the consumption behavior information of the similar customer segment includes information on products purchased by the similar customer segment; and the latent consumption tendency estimation means estimates information on products that the customer segment may purchase as the latent consumption tendency.

8. A similar customer segment estimation device as described in any one of claims 3 to 6, wherein the consumption behavior information of the customer segment includes information on products purchased by the customer segment, the consumption behavior information of the similar customer candidate segment includes information indicating the business types of stores in which the similar customer candidate segment has engaged in consumption behavior, and the latent consumption tendency estimation means estimates information on business types in which the customer segment may engage in consumption behavior as the latent consumption tendency.

9. A similar customer segment estimation device as described in claim 3 or 4, further comprising a related customer segment estimation means for estimating a related customer segment similar to the similar customer segment based on the second attribute information, wherein the latent consumption tendency estimation means estimates the latent consumption tendency of the customer segment based on the consumption behavior information of the related customer segment.

10. The similar customer group estimation device according to claim 4, wherein the latent consumption inclination estimation means estimates the consumption inclination at a specified event as the latent consumption inclination based on consumption behavior information at the specified event in the past of the similar customer group.

11. A similar customer segment estimation method in which a computer extracts first attribute information for at least one of a customer segment whose latent consumption tendency is to be estimated and a similar customer segment that is similar to the customer segment; specifies second attribute information expanded based on the extracted first attribute information and links it to at least one of the customer segment and the similar customer segment; and estimates a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the expanded second attribute information for either the customer segment or the similar customer segment with second attribute information previously specified for the other, or by comparing the expanded second attribute information for both the customer segment and the similar customer segment.

12. A similar customer segment estimation program that causes a computer to execute the following processes: extracting first attribute information for at least one of a customer segment whose latent consumption tendency is to be estimated and a similar customer segment that is similar to the customer segment; specifying second attribute information extended based on the extracted first attribute information and linking it to at least one of the customer segment and the similar customer segment; and estimating a similar customer segment that is similar to the customer segment from the similar customer segment by comparing the second attribute information extended for either the customer segment or the similar customer segment with second attribute information previously specified for the other, or by comparing the second attribute information extended for both the customer segment and the similar customer segment.

Images