Information processing device, information processing method, and program

Abstract

Provided are an information processing device, an information processing method, and a program for suitably inferring a non-customer attribute. In this information processing device, a store information acquisition means acquires target store information including a word indicating the tendency of the consumption behavior of customers of a target store. An area information acquisition means acquires target area information including a word indicating a feature of consumers in a target area where the target store exists. The non-customer information generation means causes, by inputting the target store information and the target area information to a trained model, the trained model to infer a non-customer attribute which is a word indicating a feature of a non-customer of the target store, and generates non-customer information including the non-customer attribute. The trained model has been trained to infer features of non-customers of a sample store from sample area information and sample store information. An output means outputs the non-customer information.

Description

Information processing device, information processing method, and program

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

[0002] Methods for conducting marketing by analyzing and utilizing various data have been developed.

[0003] For example, the technology described in Patent Document 1 generates analogous pattern data using randomly sampled customer evaluation data and behavioral history data, records this, and generates total customer evaluation data using the purchasing history data of the population.

[0004] In addition, the purchase-related information management system described in Patent Document 2 includes a communication terminal for online purchases, a communication terminal for physical stores, and an online server, and stores customer information, purchase information, etc., and the communication terminal for physical stores accesses the online server to input or view information.

[0005] The generation device described in Patent Document 3 includes a learning data acquisition unit and a learning processing unit that have the function of generating an estimation model that uses learning data including attributes of other objects related to a known object and the relationship between the two, and estimates the attributes of an unknown object based on the relationship between the known object and the unknown object.

[0006] JP 2003-208506 A JP 2014-085718 A JP 2016-118865 A

[0007] However, it is difficult to develop new customers who are not yet customers using only your own customer data. For this reason, methods such as collecting and analyzing personal attribute information other than your own customer data can be considered. However, from the perspective of protecting personal information, it is difficult to collect attributes of non-customers.

[0008] In view of the above-mentioned problems, the present disclosure aims to provide an information processing device and the like that suitably estimates non-customer attributes.

[0009] The information processing device according to the present disclosure includes a store information acquisition unit, a region information acquisition unit, a non-customer information generation unit, and an output unit. The store information acquisition unit acquires target store information including words indicating trends in consumption behavior of customers of the target store. The region information acquisition unit acquires target region information including words indicating characteristics of consumers in the target region where the target store is located. The non-customer information generation unit inputs the target store information and the target region information into a trained model to estimate non-customer attributes, which are words indicating characteristics of non-customers of the target store, and generates non-customer information including the non-customer attributes. The trained model has learned to estimate characteristics of non-customers of the sample store from sample region information indicating characteristics of consumers in the sample region and sample store information indicating characteristics of customers of the sample store in the sample region. The output unit outputs the non-customer information.

[0010] The information processing method according to the present disclosure is executed by a computer as follows. The computer acquires target store information including words that indicate trends in consumption behavior of customers of the target store. The computer acquires target area information including words that indicate characteristics of consumers in the target area where the target store is located. The computer inputs the target store information and the target area information into a trained model to estimate non-customer attributes, which are words that indicate the characteristics of non-customers of the target store, and generates non-customer information including non-customer attributes. The trained model has learned to estimate the characteristics of non-customers of the sample store from sample area information that indicates the characteristics of consumers in the sample area and sample store information that indicates the characteristics of customers of the sample store in the sample area. The computer outputs the non-customer information.

[0011] A program according to the present disclosure causes a computer to execute the following information processing method. The computer acquires target store information including words that indicate trends in the consumption behavior of customers of the target store. The computer acquires target area information including words that indicate characteristics of consumers in the target area where the target store is located. The computer inputs the target store information and the target area information into a trained model to estimate non-customer attributes, which are words that indicate the characteristics of non-customers of the target store, and generates non-customer information including non-customer attributes. The trained model has learned to estimate the characteristics of non-customers of the sample store from sample area information that indicates the characteristics of consumers in the sample area and sample store information that indicates the characteristics of customers of the sample store in the sample area. The computer outputs the non-customer information.

[0012] According to the present disclosure, it is possible to provide an information processing device, an information processing method, and a program that suitably estimate non-customer attributes.

[0013] 1 is a first block diagram of an information processing device according to the present disclosure. FIG. 2 is a flowchart of an information processing method according to the present disclosure. FIG. 3 is a block diagram of an information processing device according to the present disclosure. FIG. 4 is a block diagram of an information provider terminal. FIG. 5 is a diagram showing an example of consumption behavior information 321. FIG. 6 is a first block diagram of an information processing device according to the present disclosure. FIG. 7 is a flowchart of an information processing method according to the present disclosure. FIG. 8 is a second block diagram of an information processing device according to the present disclosure. FIG. 9 is a block diagram of a user terminal. FIG. 10 is a diagram showing the relationship between target area information, target store information, and non-customer information. FIG. 11 is a diagram showing the learning state of a learning model. FIG. 12 is a diagram showing information processing of a trained model. FIG. 13 is a diagram showing processing performed by a store information acquisition unit. FIG. 14 is a diagram showing processing performed by a region information acquisition unit. FIG. 15 is a block diagram of an information provider terminal. FIG. 16 is a diagram showing an example of consumption behavior information 321. FIG. 17 is a first diagram showing the flow of information processed by an information processing device. FIG. 18 is a fourth block diagram of an information processing device according to the present disclosure. FIG. 19 is a diagram showing processing performed by a bias processing unit. FIG. 20 is a second diagram showing the flow of information processed by an information processing device. FIG. 21 is a diagram showing an overview of information generated using an information processing device. FIG. 22 is a diagram showing non-customer information including classification conditions. FIG. 23 is a block diagram illustrating an example of the hardware configuration of a computer.

[0014] The present invention will be described below through embodiments of the invention, but the invention according to the claims is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential means for solving the problems. For clarity of explanation, the following description and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are assigned the same reference numerals, and duplicate explanations are omitted as necessary.

[0015] First Embodiment An information processing device 10 will be described with reference to FIG. 1. FIG. 1 is a block diagram of the information processing device 10 according to the present disclosure. The information processing device 10 is, for example, a computer or a server having a communication function. The information processing device 10 estimates non-customers of a target store in a target area and outputs information on the estimated non-customers to a user. The information processing device 10 mainly includes a store information acquisition unit 111, a region information acquisition unit 112, a non-customer information generation unit 113, and an output unit 114.

[0016] The store information acquisition unit 111 acquires target store information. The target store information is information including words that indicate trends in the consumption behavior of customers at the target store. The target store is, for example, a retail store such as a retail store, supermarket, home improvement store, or department store. The target store may also be, for example, a service provider store such as a beauty salon, dry cleaner, or repair shop. The target store may also be a wholesale store or a restaurant. Words that indicate trends in customer consumption behavior may include, for example, information regarding the amount of money spent by the customer at the target store. Words that indicate trends in customer consumption behavior may include demographic attributes of the customer. Words that indicate trends in customer consumption behavior may also include information indicating what the customer paid for. The store information acquisition unit 111 receives the target store information from the user, for example, via communication means.

[0017] The area information acquisition unit 112 acquires target area information for the target area where the target store is located. The target area where the target store is located is an area with pre-defined divisions and includes the target store. The target area may be set, for example, as an area where people who use a specific station live. The target area information is information including words that indicate the characteristics of consumers in the target area. The consumer characteristics may include the consumer's demographic attributes. The consumer characteristics may also include the consumer's psychographic attributes. The area information acquisition unit 112 receives the target area information from a user, for example, via a communication means.

[0018] The non-customer information generation unit 113 inputs the target store information and the target area information into the trained model to estimate non-customer attributes and generate non-customer information including non-customer attributes. The non-customer attributes are multiple words that indicate the characteristics of non-customers of the target store. The non-customer information may be the non-customer attributes as they are, or may be information in which predetermined processing has been applied to the non-customer attributes. In this case, the predetermined processing is, for example, processing performed for the purpose of allowing the user to easily understand the non-customer attributes. In other words, the predetermined processing in this case may include, for example, processing to aggregate or summarize the non-customer attributes.

[0019] The trained model described above is configured to estimate non-customer attributes of stores in a specified area by learning from specified training data. The training data learned by the trained model includes sample area information indicating the characteristics of consumers in the sample area, sample store information indicating the characteristics of customers of a sample store in the sample area, and information indicating the characteristics of non-customers of the sample store. The trained model may be included in the non-customer information generation unit 113 or may exist outside the information processing device 10.

[0020] Here, the trained model is realized by, for example, a neural network. The neural network includes a plurality of artificial neurons and has synapses connecting the neurons. Each synapse has a weight. When such a neural network receives an input, it performs a calculation using the weight associated with each synapse and produces an output according to the input.

[0021] A model representing the connection relationship between neurons and synapses is stored in memory, for example, in the form of software. Alternatively, the model may be realized as a dedicated circuit. Similarly, the weights of each synapse are also stored in memory in the form of software. Alternatively, a circuit representing the weights may be implemented in a dedicated circuit. Note that when a trained model is constructed using multiple models, all of the models do not necessarily need to be stored in the same memory.

[0022] There are a variety of models using such neural networks, and a wide variety of models, such as Transformer, convolutional neural networks (CNN), and recurrent neural networks (RNN), may be adopted or replaced to create a trained model.

[0023] The output unit 114 outputs the non-customer information generated by the non-customer information generating unit 113 via a predetermined communication means.

[0024] Next, a process executed by the information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a flowchart of an information processing method according to the present disclosure. In the information processing method according to the present disclosure, the information processing device 10 executes the following method.

[0025] First, the store information acquisition unit 111 of the information processing device 10 acquires target store information including words that indicate the tendency of consumption behavior of customers of the target store (step S11). The store information acquisition unit 111 supplies the acquired target store information to the non-customer information generation unit 113.

[0026] Next, the area information acquisition unit 112 acquires target area information including words that indicate characteristics of consumers in the target area where the target store is located (step S12). The area information acquisition unit 112 supplies the acquired target area information to the non-customer information generation unit 113.

[0027] Next, the non-customer information generation unit 113 inputs the target store information and the target area information into the trained model. By inputting the target store information and the target area information, the trained model estimates non-customer attributes, which are words that indicate the characteristics of non-customers of the target store. The non-customer information generation unit 113 generates non-customer information including the non-customer attributes estimated by the trained model (step S13). The non-customer information generation unit 113 supplies the generated non-customer information to the output unit 114.

[0028] Next, the output unit 114 outputs the non-customer information received from the non-customer information generation unit 113 (step S14).

[0029] The above describes the information processing method executed by the information processing device 10. By the above method, the information processing device 10 outputs non-customer information to the user.

[0030] The information processing device 10 may include a processor and a storage device (not shown). In this case, the storage device may include a nonvolatile memory such as a flash memory or a solid-state drive (SSD). In this case, the storage device may store a computer program (hereinafter simply referred to as a program) for executing the above-described method. The processor loads the computer program from the storage device into a buffer memory such as a dynamic random access memory (DRAM) and executes the program.

[0031] Each component of the information processing device 10 may be realized by dedicated hardware. Furthermore, some or all of the components 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 may be realized by a combination of the above-mentioned circuits, etc., and a program. Furthermore, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), etc. may be used as the processor. Furthermore, at least some of the functions of this embodiment may be provided in the form of infrastructure as a service (IaaS), platform as a service (PaaS), software as a service (SaaS), etc.

[0032] As described above, according to the present embodiment, it is possible to provide an information processing device, an information processing method, and a program for suitably estimating non-customer attributes.

[0033] <Second Embodiment> Next, a second embodiment will be described. Fig. 3 is a block diagram of an information processing device 20 according to the present disclosure. The information processing device 20 is communicably connected to a user terminal 200 via a network N1. The user terminal 200 is, for example, a computer or server that manages sales information and the like of a target store. Upon receiving target store information from the user terminal 200, the information processing device 20 generates non-customer information for the target store and outputs the information to the user terminal 200.

[0034] In the information processing device 20 according to this embodiment, the store information acquisition unit 111 has a function of expanding the target store information received from the user terminal 200. Here, "expanding information" refers to adding words (expanded words) associated with words as given information. In this case, the expanded words are, for example, words having a similar concept or meaning to the given word. The expanded words may also include words that have a different meaning from the given word but are closely related. The function of expanding the target store information is a function of adding words having a similar concept or meaning to the given word from among the words included in the target store information to the target store information. In this case, the store information acquisition unit 111 performs natural language processing to determine whether the concepts or meanings of the words are similar.

[0035] Similarly, in the information processing device 20 according to this embodiment, the regional information acquisition unit 112 has a function of expanding the target regional information received from the user terminal 200. The function of expanding the target regional information is a function of adding words having similar concepts or meanings to words included in the target regional information to the target regional information. In this case, the regional information acquisition unit 112 performs natural language processing to determine whether the concepts or meanings of the words are similar.

[0036] The store information acquisition unit 111 and the area information acquisition unit 112 have the above-described extended functions, which enables the information processing device 20 to appropriately match the target store information with the target area information. This also enables the information processing device 20 to appropriately generate non-customer attributes.

[0037] The information processing device 20 has a trained model 121. The trained model 121 has learned to estimate characteristics of non-customers of a sample store from sample area information indicating characteristics of consumers in the sample area and sample store information indicating characteristics of customers of a sample store in the sample area. The non-customer information generation unit 113 inputs target store information and target area information into the trained model 121, estimates non-customer attributes of the target store, and generates non-customer information including non-customer attributes.

[0038] The information processing device 20 has a storage unit 130. The storage unit 130 is a storage device including a non-volatile memory such as a flash memory. The storage unit 130 stores, for example, a program for executing the functions of the present disclosure. The storage unit 130 may also store, for example, target area information related to a target area in which a target store is located.

[0039] The storage unit 130 may also store, for example, regional information relating to any number of regions. In this case, the regional information stored in the storage unit 130 is configured to enable extraction of target regional information corresponding to the target store. More specifically, for example, the regional information includes information on commercial areas centered around stations and main roads. In other words, the regional information is configured to enable extraction of target regional information including words that indicate the characteristics of consumers in the commercial area linked to the location of the target store. In this case, the regional information acquisition unit 112 reads the target regional information corresponding to the target store from the storage unit 130.

[0040] Next, the user terminal 200 will be described with reference to Fig. 4. Fig. 4 is a block diagram of the user terminal 200. The user terminal 200 mainly includes an operation reception unit 211, a display unit 212, a communication unit 213, a control unit 214, and a storage unit 220.

[0041] The operation reception unit 211 is an interface that receives operations from the user. The user performs various operations using information input devices such as buttons, switches, and touch panels that are provided on the user terminal 200. The operation reception unit 211 supplies signals related to the received operations to the control unit 214.

[0042] The display unit 212 includes a display device such as a liquid crystal panel or organic electroluminescence. The display unit 212 displays non-customer information supplied from the information processing device 20. The communication unit 213 is an interface for communication between the user terminal 200 and the information processing device 20. The control unit 214 includes a calculation device such as a CPU, and controls each component of the user terminal 200.

[0043] The storage unit 220 is a storage device including a non-volatile memory. The storage unit 220 stores store information 221. The store information 221 includes target store information. The store information 221 may be the target store information itself. The store information 221 may include, for example, customer demographic attributes or customer purchasing history.

[0044] With the above-described configuration, the user terminal 200 may accept target area information input by the user. In this case, the user terminal 200 supplies the accepted target area information to the information processing device 20 together with target store information.

[0045] Next, the concept of non-customer information will be described with reference to Fig. 5. Fig. 5 is a diagram showing the relationship between target area information A, target store information B, and non-customer information C. Fig. 5 shows the target area information A, target store information B, and non-customer information C using a Venn diagram.

[0046] Target area information A exists inside the ellipse drawn by a dashed line. In other words, target area information A includes target store information B. Target area information A also includes non-customer information C. Target store information B exists inside the ellipse drawn by a solid line. Target store information B is part of target area information A.

[0047] Non-customer information C is the area indicated by hatching. In other words, non-customer information C is the area inside the dashed ellipse and outside the solid ellipse. In other words, non-customer information C is part of target area information A, and is information excluding target store information B. In other words, the relationship between these can be expressed as A ⊇ B and A - B = C.

[0048] Next, the state of the learning stage of the trained model 121 will be described with reference to Fig. 6. Fig. 6 is a diagram showing the learning state of the training model 120. The training model 120 shown in Fig. 6 shows the state of the learning stage of the trained model 121. The training model 120 is, for example, an LLM (Large Language Model).

[0049] In the training data shown in Figure 6, sample area information includes "cafe," "clothing," "pets," "furniture," etc. Sample store information includes "middle-aged and elderly," "furniture," "tools," "pet supplies," etc. Non-customer attributes include "leisure," "female," "luxury," "single," etc.

[0050] The learning model 120 receives sample area information, sample store information, and non-customer attributes as training data. The sample area information, sample store information, and non-customer attributes are each text data. The sample store information has a concept that is the same as or similar to part of the sample area information. The non-customer attributes have a concept that is the same as or similar to part of the sample area information. Furthermore, the non-customer attributes do not include a concept that is the same as or similar to the sample store information. Therefore, the sample area information, sample store information, and non-customer attributes have the relationship shown in FIG. 5.

[0051] In the learning stage, the learning model 120 learns to exclude sample store information such as "middle-aged and elderly," "furniture," "tools," and "pet supplies" and words with concepts or meanings similar to those of the sample store information from sample area information such as "cafe," "clothing," "pets," and "furniture." When the learning model 120 receives sample area information and sample store information as input, it learns to output non-customer information such as "leisure," "female," "luxury," and "single" as inferred results.

[0052] As a result, the learning model 120 learns to output information from the sample area information that does not correspond to the sample store information as non-customer information. Note that the learning model 120 may also learn to select words corresponding to non-customer attributes from a database of multiple preset words.

[0053] 7 is a diagram showing information processing of the trained model 121. When the training model 120 completes training, it becomes available as the trained model 121. When the trained model 121 receives local information such as "cafe," "clothing," "pets," and "furniture," and store information such as "middle-aged and elderly," "furniture," "tools," and "pet supplies," it outputs words such as "leisure," "women," "luxury," and "single."

[0054] In addition to the learning content described above, the trained model 121 may have a predetermined filter function. For example, the predetermined filter function is a function to suppress the output of preset words. For example, the predetermined filter function is a function to output preset words in different expressions. By having such a function, the trained model 121 can output information that more appropriately corresponds to the characteristics of the store, etc.

[0055] Next, the expansion process executed by the store information acquisition unit 111 will be described with reference to FIG. 8 . The "expansion process" refers to a process for executing the above-mentioned "information expansion" process. FIG. 8 is a diagram showing the process executed by the store information acquisition unit 111. For example, the store information acquisition unit 111 acquires words such as "middle-aged and elderly," "furniture," "tools," and "pet supplies" from the target store information. The store information acquisition unit 111 performs a process for expanding these words. Specifically, for example, as the expansion process, the store information acquisition unit 111 adds words such as "family," "education," and "travel" to the word "middle-aged and elderly." Similarly, the store information acquisition unit 111 adds "family," "housing," and "moving" to "furniture," adds "DIY," "cost," and "art" to "tools," and adds "collar," "insurance," and "veterinarian" to "pet supplies."

[0056] Next, the expansion process executed by the regional information acquisition unit 112 will be described with reference to FIG. 9 . FIG. 9 is a diagram showing the process executed by the regional information acquisition unit 112. The regional information acquisition unit 112 acquires, for example, words such as "cafe," "clothing," "pets," and "furniture" as target regional information. The regional information acquisition unit 112 performs a process of expanding these words. Specifically, for example, the regional information acquisition unit 112 adds words such as "twenties" and "business" to "cafe." Similarly, the regional information acquisition unit 112 adds words such as "women," "trends," and "brands" to "clothing," adds words such as "walks," "training," and "exercise" to "pets," and adds words such as "family," "DIY," and "residence" to "furniture."

[0057] As described above, as shown in Figures 8 and 9, the store information acquisition unit 111 expands the target store information. Furthermore, the local area information acquisition unit 112 expands the target local area information. In order for the store information acquisition unit 111 and the local area information acquisition unit 112 to perform such expansion processing, the storage unit 130 of the information processing device 20 may store candidate words to be expanded in advance. Furthermore, when performing the expansion processing, the store information acquisition unit 111 and the local area information acquisition unit 112 may acquire candidate words to be expanded from an external database.

[0058] The information processing device 20 has been described above. In the information processing device 20, the store information acquisition unit 111 may acquire target store information including a customer's product purchase history at the target store. In this case, the customer's product purchase history is, for example, POS (Point of Sales) data. The target store information may include, for example, the names of products sold and the prices of those products. The target store information may also include the age group and gender of customers who purchased products, and the date and time when the customers purchased the products.

[0059] As described above, according to the present embodiment, it is possible to provide an information processing device, an information processing method, and a program for suitably estimating non-customer attributes.

[0060] <Third Embodiment> Next, a third embodiment will be described. Fig. 10 is a block diagram of an information processing device 30 according to the present disclosure. The information processing device 30 is communicably connected to a user terminal 200 via a network N1. The information processing device 30 is also communicably connected to an information provider terminal 300 via the network N1.

[0061] The user terminal 200 according to this embodiment requests non-customer information from the information processing device 30. At this time, the user terminal 200 also supplies information on a target store linked to the user terminal 200 to the information processing device 30. The information on the target store is, for example, the name of the target store or a unique identifier of the target store.

[0062] The information provider terminal 300 is configured to be able to output regional information indicating the characteristics of consumers in a plurality of regions. The information provider terminal 300 is also configured to be able to output target store information including words indicating the tendency of consumption behavior of customers at the store of the user terminal 200.

[0063] In response to a request from the user terminal 200, the information processing device 30 generates non-customer information for a target store linked to the user terminal 200, and outputs the generated non-customer information to the user terminal 200. At this time, the information processing device 30 acquires target store information and target area information from the information provider terminal 300 in order to generate the non-customer information.

[0064] 11 is a block diagram of the information provider terminal 300. The information provider terminal 300 is, for example, a computer or a server having a communication function. The information provider terminal 300 mainly includes an operation reception unit 311, a display unit 312, a communication unit 313, a control unit 314, and a storage unit 320.

[0065] The operation reception unit 311 is an interface that receives operations from an administrator who manages the information provider terminal 300. The display unit 312 includes a display device such as a liquid crystal panel or an organic electroluminescence device. The communication unit 313 is an interface for communication between the information provider terminal 300 and the information processing device 30. The control unit 314 includes a calculation device such as a CPU, and controls each component of the information provider terminal 300.

[0066] The memory unit 320 is a storage device including a non-volatile memory. The memory unit 320 stores consumer consumption behavior information 321. The consumption behavior information 321 includes at least the demographic attributes of multiple consumers and the amounts paid by these consumers. The consumption behavior information 321 may also include information about products or services for which the consumers paid. The consumption behavior information 321 also includes information about stores linked to the consumption behavior. The information about the stores includes the store's name or unique identifier and information about the store's location. The consumption behavior information 321 is linked to each of multiple consumers. Therefore, the consumption behavior information 321 is configured so that the consumption behavior of each consumer can be extracted. The consumption behavior information 321 is also linked to each of multiple stores.

[0067] FIG. 12 is a diagram showing an example of consumer behavior information 321. The consumer behavior information 321 shown in FIG. 12 includes information related to a store identifier, a consumer identifier, consumer attributes, a date, and an amount. These pieces of information exist in a linked state. Specifically, for example, the consumer behavior information 321 includes information that consumer CS001 paid 2,600 yen on February 1, 2026 at a store with identifier SH001. The consumer behavior information 321 also includes attribute information such as the fact that consumer CS001 is a woman in her twenties.

[0068] Similarly, the consumption behavior information 321 includes information that consumer CS002 paid 10,800 yen at the store with identifier SH001 on February 9, 2026. The consumption behavior information 321 also includes attribute information such as the fact that consumer CS002 is a woman in her 40s.

[0069] Similarly, the consumption behavior information 321 includes information that consumer CS003 paid 1,700 yen at the store with identifier SH001 on February 4, 2026. The consumption behavior information 321 also includes attribute information such as the fact that consumer CS003 is a man in his 30s.

[0070] Similarly, consumer behavior information 321 includes information such as that consumer CS002 paid 4,200 yen on February 7, 2026 at the store with identifier SH002, that consumer CS003 paid 3,100 yen on January 19, 2026 at the store with identifier SH002, and that consumer CS004 paid 1,100 yen on February 14, 2026 at the store with identifier SH003.

[0071] In addition to the above information, the consumption behavior information 321 also includes store attribute information, etc. The store attribute information includes information about the store category and the store location.

[0072] The consumption behavior information 321 is configured so that this information can be extracted for each item. Therefore, the information provider terminal 300 can extract information linked to store SH001 from the consumption behavior information 321 as target store information for store SH001, for example, and provide this information to the information processing device 30. Similarly, the information provider terminal 300 can provide information on stores located in the trade area where store SH001 is located to the information processing device 30 as target area information corresponding to store SH001, for example.

[0073] Next, information processed by the information processing device 30 will be described with reference to Fig. 13. Fig. 13 is a diagram showing the flow of information processed by the information processing device 30.

[0074] The store information acquisition unit 111 acquires target store information via the network N1. The store information acquisition unit 111 executes extension processing on the acquired information. As a result, the store information acquisition unit 111 acquires target store information B. The store information acquisition unit 111 supplies the target store information B to the non-customer information generation unit 113.

[0075] The regional information acquisition unit 112 acquires target store information via the network N1. The regional information acquisition unit 112 performs an expansion process on the acquired information. As a result, the regional information acquisition unit 112 acquires target regional information A. The regional information acquisition unit 112 supplies the target regional information A to the non-customer information generation unit 113.

[0076] The non-customer information generation unit 113 receives target store information B from the store information acquisition unit 111 and target area information A from the area information acquisition unit 112, and supplies the received information to the trained model 121. The trained model 121 estimates non-customer attributes C from the target area information A and the target store information B, and supplies the estimation result to the non-customer information generation unit 113.

[0077] The non-customer information generation unit 113 supplies the non-customer attribute C received from the trained model 121 as non-customer information to the output unit 114. The output unit 114 outputs the non-customer information to the user terminal 200 via the network N1.

[0078] In addition to the target store information, the store information acquisition unit 111 may also receive a request signal from the user terminal 200 to request non-customer information. In this case, the request signal can serve as a trigger for starting processing executed by the information processing device 30. For example, when the information processing device 30 receives the request signal from the user terminal 200, the information processing device 30 requests the target store information and target area information from the information provider terminal 300 in response to the received request signal. Then, in response to the request from the information processing device 30, the information provider terminal 300 supplies the target store information linked to the user terminal 200 and the target area information corresponding to the target store to the information processing device 30.

[0079] As described above, the area information acquisition unit 112 acquires target area information including words that indicate characteristics of consumers at other stores in the area where the target store is located. This allows the information processing device 30 to preferably generate non-customer information.

[0080] The store information acquisition unit 111 also acquires target store information including consumption behavior trends of customers who use the target store at stores other than the target store. With this function, the information processing device 30 can preferably acquire target store information and also acquire consumption behavior trends of customers in a target area as target area information.

[0081] As described above, according to the present embodiment, it is possible to provide an information processing device, an information processing method, and a program for suitably estimating non-customer attributes.

[0082] <Fourth Embodiment> Next, a fourth embodiment will be described. Fig. 14 is a block diagram of an information processing device 40. The information processing device 40 has a bias processing unit 115. The information processing device 40 can also access an information network 400 via a network N1. The information network 400 is a communication system configured to be able to collect information and data. The information network 400 is, for example, the Internet or a predetermined intranet. In the information network 400, a computer can search for words related to various words and collect desired information as search results.

[0083] The information processing device 40 collects various information from the information network 400. More specifically, for example, the store information acquisition unit 111 may collect information about a target store as part of the target store information from the information network 400. Furthermore, the area information acquisition unit 112 may collect information about the consumption behavior of consumers in a target area from the information network 400 as part of the target area information.

[0084] The bias processing unit 115 performs bias processing on at least one of the target store information and the target area information. The bias processing sets word priorities for multiple words based on a predetermined bias setting. The bias processing unit 115 may also distinguish between multiple words or combine multiple words into one representative word in accordance with the set priorities. The bias processing unit 115 may also discard words with low priorities in accordance with the set priorities. Through this processing, the bias processing unit 115 performs preprocessing to appropriately generate non-customer information.

[0085] In this case, the non-customer information generating unit 113 generates non-customer information using the target store information or target area information after the bias processing, thereby enabling the information processing device 40 to generate non-customer information more preferably.

[0086] The bias processing unit 115 may be configured so that the user can adjust the bias parameters used in the bias processing. In this case, the parameters are, for example, the values ​​of language vectors. The parameters may also be the content of the words for which the relevance is set. The parameters may also be thresholds set for the relevance with the words for which the relevance is set. By the user adjusting the parameters, the information processing device 40 can optimize the non-customer information. The bias processing unit 115 may also be configured so that multiple bias processing operations can be performed using multiple parameters. This allows the information processing device 40 to generate non-customer information from multiple perspectives.

[0087] One example of bias processing from multiple perspectives is processing that prioritizes attributes associated with non-customer "people." By performing such processing, demographic attributes or psychographic attributes of non-customers may become apparent.

[0088] Another example of bias processing from multiple perspectives is processing that prioritizes attributes associated with stores frequented by non-customers. By performing such processing, it is possible that store attributes that attract non-customers become apparent.

[0089] The processing of the bias processing unit 115 will be further described with reference to Fig. 15. Fig. 15 is a diagram showing the processing performed by the bias processing unit. The bias processing unit 115 receives the expanded target area information and performs bias processing on the received target area information. The "expanded target area information" shown in the figure includes words such as "cafe," "20s," "business," "clothing," "women," "trend," "brand," "pet," "walk," "insurance," "veterinarian," "furniture," "family," "DIY," and "housing."

[0090] The bias processing condition set in the bias processing unit 115 is that attributes associated with "people" are prioritized and words with low priority are discarded. As a result, the biased target area information includes words such as "twenties," "business," "social," "autonomy," "women," "brand," "family," "children," "health," "outdoors," "luxury," "safety," "DIY," "middle-aged and elderly," "comfort," and "design." In this way, the words after bias processing include words that are closely related to the demographic and psychographic attributes of consumers in the target area.

[0091] Next, information processed by the information processing device 40 will be described with reference to Fig. 16. Fig. 16 is a diagram showing the flow of information processed by the information processing device 40.

[0092] The store information acquisition unit 111 acquires target store information via the network N1. The target store information may include information acquired from the information network 400 in addition to information acquired from the information provider terminal 300. The store information acquisition unit 111 acquires target store information B by performing an extension process on the acquired information. The store information acquisition unit 111 supplies the target store information B to the bias processing unit 115.

[0093] The regional information acquisition unit 112 acquires target regional information via the network N1. The target regional information may include information acquired from the information provider terminal 300 as well as information acquired from the information network 400. The regional information acquisition unit 112 acquires target regional information A by performing an extension process on the acquired information. The regional information acquisition unit 112 supplies the target regional information A to the bias processing unit 115.

[0094] The bias processing unit 115 performs bias processing on the received target store information B and target area information A. Here, the model of the bias processing performed by the bias processing unit 115 is defined as model F(n). Here, n is the number of model F, and is, for example, any natural number. Model F(n) executes an algorithm according to a predetermined condition for each n. For example, the bias processing unit 115 performs processing to increase the priority of attributes linked to "person" as shown in FIG. 15 using model F(1) based on condition 1. Furthermore, for example, the bias processing unit 115 performs processing to increase the priority of attributes linked to "store" using model F(2) based on condition 2.

[0095] In this case, for example, the information obtained after model F(1) has processed target area information A is referred to as target area information A(1). That is, generally, target area information A(n) is generated as a result of the bias processing unit 115 processing target area information A using model F(n). Similarly, the bias processing unit 115 processes target store information B using model F(n) to generate target store information B(n). The bias processing unit 115 supplies the target area information A(n) and target store information B(n) generated by performing the bias processing to the non-customer information generation unit 113.

[0096] The non-customer information generation unit 113 supplies the target area information A(n) and target store information B(n) received from the bias processing unit 115 to the trained model 121 for each model F number. As a result, the non-customer information generation unit 113 receives non-customer attributes C(n) for each model F number from the trained model 121. For example, when the information processing device 40 executes a process to increase the priority of attributes associated with "people" using model F(1), it receives non-customer attributes C(1) that reflect the profile of a non-customer from the trained model 121. Furthermore, when the information processing device 40 executes a process to increase the priority of attributes associated with "stores" using model F(2), it receives non-customer attributes C(2) that reflect the attributes of stores related to non-customers from the trained model 121.

[0097] The non-customer information generation unit 113 supplies the non-customer information including the non-customer attribute C(n) to the output unit 114. The output unit 114 outputs the non-customer information including the non-customer attributes C(1), C(2), etc. to the user terminal 200 via the network N1.

[0098] Fig. 17 is a diagram showing an overview of information generated using the information processing device 40. Fig. 17 is composed of a matrix of target area information A, target store information B, and non-customer attributes C arranged horizontally, and model F(1), model F(2), and statistical data arranged vertically.

[0099] Target area information A(1) is generated by executing model F(1) processing on target area information A. In FIG. 17, this is shown as A×F(1)=A(1). Similarly, FIG. 17 shows target store information B(1) as B×F(1)=B(1). Non-customer attribute C(1) generated by model F(1) is A(1)-B(1)=C(1). In other words, information processing device 40 generates non-customer attribute C(1) from target area information A, target store information B, and model F(1).

[0100] Similarly, the information processing device 40 generates target area information A(2) from target area information A and model F(2), and generates target store information B(2) from target store information B and model F(2). These are shown as A x F(2) = A(2) and B x F(2) = B(2). The information processing device 40 generates non-customer attribute C(2) from the target area information A(2) and target store information B(2). The non-customer attribute C(2) is shown as A(2) - B(2) = C(2).

[0101] The information processing device 40 generates the above-mentioned non-customer attributes C(1) and non-customer attributes C(2) from the target area information A and the target store information B. Both the non-customer attributes C(1) and non-customer attributes C(2) are supplied to the user terminal 200 in a form that can be used for marketing activities, etc.

[0102] Statistical data A13 and statistical data B13 are shown in the lower part of FIG. 17. Statistical data A13 is statistical data that can be generated from target area information A. Statistical data B13 is statistical data that can be generated from target store information B. In addition to the above-mentioned processing, the information processing device 40 may perform predetermined statistical processing to generate statistical data A13 and statistical data B13 and supply the generated statistical data to the user terminal 200. The predetermined statistical processing is, for example, classification or ranking of words included in the target area information A or target store information B, or calculation of the average value of language vectors. With this configuration, the information processing device 40 can provide the user with information that can be suitably used for marketing activities.

[0103] Next, variations of non-customer information will be described with reference to Fig. 18. Fig. 18 is a diagram showing non-customer information including classification conditions. The non-customer information shown in Fig. 18 includes non-customer attributes, likelihoods, and attribute categories.

[0104] Non-customer attributes include words such as "leisure," "female," "luxury," and "single." The likelihood is a value associated with each word, indicating the likelihood of a non-customer estimated by the trained model 121. The likelihoods shown in FIG. 18 range from 0 to 1, with the likelihood increasing as the likelihood approaches 1. In FIG. 18, the likelihood of "leisure" is 0.63, "female" is 0.27, "luxury" is 0.34, and "single" is 0.41. In this case, for example, the user can conduct marketing related to "leisure" and "female," which are words with relatively high likelihoods. In other words, the information processing device 40 can provide the user with non-customer information that enables efficient marketing activities.

[0105] The attribute category is a value preset for each non-customer attribute and is an index for identifying similar attributes. In FIG. 18 , the attribute category for "leisure" is C12, for "female" is C20, for "luxury" is C21, and for "single" is C20. In this case, for example, the user can conduct marketing targeting "female" and "single" who share the same attribute category. In other words, the information processing device 40 can provide the user with non-customer information that enables efficient marketing activities.

[0106] As described above, the non-customer information generation unit 113 may generate non-customer information including classification conditions associated with non-customer attributes. The non-customer information generation unit 113 may also generate non-customer information including the likelihood of non-customer attributes as classification conditions. The non-customer information generation unit 113 may also generate non-customer information including classification conditions that classify non-customer attributes based on preset attribute categories. Note that the classification conditions are not limited to those described above. The classification conditions may be, for example, filtering using a preset dictionary.

[0107] As described above, according to the present disclosure, it is possible to provide an information processing device, an information processing method, and a program that suitably estimate non-customer attributes.

[0108] <Example of Hardware Configuration> Hereinafter, an example will be described in which each functional configuration of an information processing device according to the present disclosure is realized by a combination of hardware and software.

[0109] FIG. 19 is a block diagram illustrating an example of a hardware configuration of a computer. The information processing device of the present disclosure can realize the above-described functions by a computer 500 including the hardware configuration shown in the figure. The computer 500 may be a portable computer such as a smartphone or tablet terminal, or a stationary computer such as a PC. The computer 500 may be a dedicated computer designed to realize each device, or may be a general-purpose computer. The computer 500 can realize desired functions by installing a predetermined application.

[0110] The computer 500 has a bus 502, a processor 504, a memory 506, a storage device 508, an input / output interface (I / F) 510, and a network interface (I / F) 512. The bus 502 is a data transmission path for the processor 504, the memory 506, the storage device 508, the input / output interface 510, and the network interface 512 to transmit and receive data to and from each other. However, the method of connecting the processor 504 and the like to each other is not limited to bus connection.

[0111] The processor 504 is a processor such as a CPU, a GPU, an FPGA, etc. The memory 506 is a main storage device realized using a RAM (Random Access Memory) or the like.

[0112] The storage device 508 is an auxiliary storage device realized using a hard disk, an SSD, a memory card, a ROM (Read Only Memory), etc. The storage device 508 stores programs for realizing desired functions. The processor 504 reads the programs into the memory 506 and executes them to realize the respective functional components of each device.

[0113] The input / output interface 510 is an interface for connecting the computer 500 to input / output devices. For example, an input device such as a keyboard and an output device such as a display device are connected to the input / output interface 510. The network interface 512 is an interface for connecting the computer 500 to a network.

[0114] The above-described 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 in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, 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 media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0115] 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.

[0116] When performing output in each embodiment, the information processing devices 10, 20, 30, and 40 may change the display content based on information about the display device to which the output is directed. The display device information may include, for example, the screen size of the display device and the ratio of its vertical length to its horizontal length. Based on such information, the display content may be changed so that, for example, the larger the screen size of the display device, the larger the size of characters and figures such as graphs. In this case, an upper limit may be set so that the display size does not exceed a predetermined size.

[0117] Similarly, the display content may be changed so that the size of characters and graphs and other figures becomes smaller as the screen size of the display device becomes smaller. Also, a lower limit may be set so that the display size does not fall below a predetermined size. In addition, the display position may be changed, or certain items may not be displayed on the same screen.

[0118] In another aspect, the information processing devices 10, 20, 30, and 40 may change the content of the display depending on the processing power required to perform processing for displaying on the display device. For example, when the processing power 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 memory size may be referenced, or the operating status of the processor or the execution status of tasks may be referenced.

[0119] 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.

[0120] Some or all of the above embodiments may be described as in the following supplementary notes, but are not limited to the following: (Supplementary Note 1) An information processing device comprising: a store information acquisition unit that acquires target store information including words that indicate trends in consumption behavior of customers of a target store; a region information acquisition unit that acquires target region information including words that indicate characteristics of consumers in a target region where the target store is located; a non-customer information generation unit that estimates non-customer attributes, which are words that indicate the characteristics of non-customers of the target store, by inputting the target store information and the target region information into a trained model that has learned to estimate characteristics of non-customers of the sample store from sample region information that indicates characteristics of consumers in the sample region and sample store information that indicates characteristics of customers of the sample store in the sample region, thereby generating non-customer information including the non-customer attributes; and an output unit that outputs the non-customer information. (Supplementary Note 2) The information processing device according to Supplementary Note 1, further comprising a bias processing unit that performs bias processing to set priorities of words based on a predetermined bias setting for at least one of the target store information or the target area information, and the non-customer information generation unit generates the non-customer information based on the target store information or the target area information after the bias processing. (Supplementary Note 3) The information processing device according to Supplementary Note 2, wherein the bias processing unit is set so that a bias parameter used in the bias processing is adjustable by a user. (Supplementary Note 4) The information processing device according to Supplementary Note 1, wherein the store information acquisition unit also acquires the target store information including trends in consumption behavior at stores other than the target store for customers who use the target store. (Supplementary Note 5) The information processing device according to Supplementary Note 1, wherein the area information acquisition unit acquires the target area information including words that indicate characteristics of consumers at other stores in the area where the target store is located. (Supplementary Note 6) The information processing device according to any one of Supplements 1 to 5, wherein the non-customer information generation unit generates the non-customer information including classification conditions associated with the non-customer attributes. (Supplementary Note 7) The information processing device according to Supplementary Note 6, wherein the non-customer information generation unit generates the non-customer information including a likelihood of the non-customer attribute as the classification condition.(Supplementary Note 8) The information processing device according to Supplementary Note 6, wherein the non-customer information generation unit generates the non-customer information including the classification conditions that classify the non-customer attributes based on preset attribute categories. (Supplementary Note 9) An information processing method, wherein a computer: acquires target store information including words that indicate trends in consumption behavior of customers of the target store; acquires target area information including words that indicate characteristics of consumers in the target area where the target store is located; inputs the target store information and the target area information into a trained model that has learned to estimate characteristics of non-customers of the sample store from sample area information that indicates characteristics of consumers in the sample area and sample store information that indicates characteristics of customers of the sample store in the sample area, thereby estimating non-customer attributes that are words that indicate the characteristics of non-customers of the target store, generates non-customer information including the non-customer attributes, and outputs the non-customer information. (Supplementary Note 10) A program that causes a computer to execute an information processing method, which includes: acquiring target store information including words that indicate the consumption behavior trends of customers of the target store; acquiring target area information including words that indicate the characteristics of consumers in the target area where the target store is located; inputting the target store information and the target area information into a trained model that has learned to estimate the characteristics of non-customers of the sample store from sample area information that indicates the characteristics of consumers in the sample area and sample store information that indicates the characteristics of customers of the sample store in the sample area, thereby estimating non-customer attributes, which are words that indicate the characteristics of non-customers of the target store, generating non-customer information including the non-customer attributes; and outputting the non-customer information.

[0121] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 may also be dependent on Supplementary Notes 9 and 10 in the same dependency relationship as Supplementary Notes 2 to 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0122] This application claims priority based on Japanese Patent Application No. 2024-28156, filed February 28, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0123] 10 Information processing device 20 Information processing device 30 Information processing device 40 Information processing device 111 Store information acquisition unit 112 Area information acquisition unit 113 Non-customer information generation unit 114 Output unit 115 Bias processing unit 120 Learning model 121 Learned model 130 Memory unit 200 User terminal 211 Operation acceptance unit 212 Display unit 213 Communication unit 214 Control unit 220 Memory unit 221 Store information 300 Information provider terminal 311 Operation acceptance unit 312 Display unit 313 Communication unit 314 Control unit 320 Memory unit 321 Consumption behavior information 400 Information network 500 Computer 502 Bus 504 Processor 506 Memory 508 Storage device 510 Input / output I / F 512 Network I / F A13 Regional statistical data B13 Store statistical data N1 Network

Claims

1. An information processing device comprising: a store information acquisition means for acquiring target store information including words that indicate the consumption behavior trends of customers of a target store; a region information acquisition means for acquiring target region information including words that indicate the characteristics of consumers in the target region where the target store is located; a non-customer information generation means for inputting the target store information and the target region information into a trained model that has learned to estimate the characteristics of non-customers of the sample store from sample region information that indicates the characteristics of consumers in the sample region and sample store information that indicates the characteristics of customers of the sample store in the sample region, thereby estimating non-customer attributes, which are words that indicate the characteristics of non-customers of the target store, and generating non-customer information including the non-customer attributes; and an output means for outputting the non-customer information.

2. An information processing device as described in claim 1, further comprising a bias processing means for performing bias processing to set word priorities based on a predetermined bias setting for at least one of the target store information or the target area information, and the non-customer information generation means generates the non-customer information based on the target store information or the target area information after the bias processing.

3. The information processing device according to claim 2, wherein the bias processing means is set so that a bias parameter used in the bias processing can be adjusted by a user.

4. The information processing device according to claim 1, wherein the store information acquisition means also acquires target store information including the consumption behavior trends of customers who use the target store at stores other than the target store.

5. The information processing device according to claim 1, wherein the regional information acquisition means acquires the target regional information including words that indicate characteristics of consumers at other stores in the region where the target store is located.

6. The information processing device according to any one of claims 1 to 5, wherein the non-customer information generating means generates the non-customer information including classification conditions associated with the non-customer attributes.

7. The information processing device according to claim 6, wherein the non-customer information generating means generates the non-customer information including the likelihood of the non-customer attribute as the classification condition.

8. The information processing device according to claim 6, wherein the non-customer information generating means generates the non-customer information including the classification conditions that classify the non-customer attributes based on preset attribute categories.

9. An information processing method in which a computer: acquires target store information including words that indicate trends in the consumption behavior of customers of the target store; acquires target area information including words that indicate the characteristics of consumers in the target area where the target store is located; inputs the target store information and the target area information into a trained model that has learned to estimate the characteristics of non-customers of the sample store from sample area information that indicates the characteristics of consumers in the sample area and sample store information that indicates the characteristics of customers of the sample store in the sample area, thereby estimating non-customer attributes, which are words that indicate the characteristics of non-customers of the target store, generates non-customer information including the non-customer attributes, and outputs the non-customer information.

10. A program that causes a computer to execute an information processing method that acquires target store information including words that indicate the consumption behavior trends of customers of the target store, acquires target area information including words that indicate the characteristics of consumers in the target area where the target store is located, estimates non-customer attributes, which are words that indicate the characteristics of non-customers of the target store, by inputting the target store information and the target area information into a trained model that has learned to estimate the characteristics of non-customers of the sample store from sample area information that indicates the characteristics of consumers in the sample area and sample store information that indicates the characteristics of customers of the sample store in the sample area, generates non-customer information including the non-customer attributes, and outputs the non-customer information.

Images