Information processing device, information processing method, and information processing program

Abstract

To enable provision of appropriate services regarding the purchase of receivables. [Solution] The information processing device according to the present application includes an estimation unit and a determination unit. The estimation unit estimates a store closure probability, which is the probability that a target store, which is a store opening on a commerce site on a network, will close the commerce site after a predetermined period of time. The determination unit determines a collection mode of accounts receivable corresponding to the target store's future receivable, based on the target store's store closure probability estimated by the estimation unit, the collection mode including a lower limit of the collection rate of the accounts receivable corresponding to the target store's future receivable. For example, the estimation unit estimates the target store's store closure probability using a learning model that has learned characteristics of the association between stores opening on the commerce site and store closures from the commerce site.

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, various technologies related to purchasing receivables (hereinafter also referred to as "factoring") have been provided. For example, a technology has been provided that predicts the future amount of receivables and provides funds according to the predicted future amount of receivables. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6836255 [Patent Document 2] Patent Publication No. 2021-033762 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is room for improvement in the above conventional technology. For example, the above conventional technology only predicts the future amount of the claim and provides funds according to that amount, making it difficult to flexibly purchase claims. Therefore, it is desirable to be able to provide an appropriate service for purchasing claims.

[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that enable the provision of appropriate services related to the purchase of bonds. [Means for solving the problem]

[0006] The information processing device of the present application is characterized by comprising an estimation unit that estimates a store closure probability, which is the probability that a target store, which is a store opening on a commercial trading site on a network, will close the commercial trading site after a specified period of time, and a determination unit that determines a collection mode of accounts receivable corresponding to future receivables of the target store based on the store closure probability of the target store estimated by the estimation unit, the collection mode including a lower limit of the collection rate of accounts receivable corresponding to future receivables of the target store. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide an appropriate service regarding the purchase of receivables. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of information processing executed by the information processing device. [Diagram 3] FIG. 3 is a diagram illustrating an example of information processing executed by the information processing device. [Figure 4] FIG. 4 is a diagram illustrating an example of information processing executed by the information processing device. [Diagram 5] FIG. 5 is a diagram illustrating an example of information processing executed by the information processing device. [Figure 6] FIG. 6 is a diagram illustrating an example of information processing executed by the information processing device. [Figure 7] FIG. 7 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of a shop owner information storage unit according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of a model information storage unit according to the embodiment. [Figure 11]FIG. 11 is a diagram illustrating an example of a threshold information storage unit according to the embodiment. [Figure 12] FIG. 12 is a diagram illustrating an example of a group information storage unit according to the embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of a social situation information storage unit according to the embodiment. [Figure 14] FIG. 14 is a diagram illustrating an example of the commercial transaction site information storage unit according to the embodiment. [Figure 15] FIG. 15 is a diagram illustrating an example of the factoring information storage unit according to the embodiment. [Figure 16] FIG. 16 is a flowchart showing an example of the flow of information processing executed by the information processing device. [Figure 17] FIG. 17 is a flowchart showing an example of the flow of information processing executed by the information processing device. [Figure 18] FIG. 18 is a flowchart showing an example of the flow of information processing executed by the information processing device. [Figure 19] FIG. 19 is a flowchart showing an example of the flow of information processing executed by the information processing device. [Figure 20] FIG. 20 is a flowchart showing an example of the flow of information processing executed by the information processing device. [Figure 21] FIG. 21 is a flowchart showing an example of the flow of information processing executed by the information processing device. [Figure 22] FIG. 22 is a flowchart showing an example of the flow of information processing executed by the information processing device. [Diagram 23] FIG. 23 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments. In addition, the same parts in the following embodiments are denoted by the same reference numerals, and duplicated descriptions are omitted.

[0010] (Embodiment) [1. Information Processing] An example of information processing executed by the information processing system 1 will be described below with reference to FIG. 1. FIG. 1 is a diagram showing an example of information processing according to an embodiment. The information processing system 1 executes information processing on electronic commerce (EC) services. For example, the information processing device 100 of the information processing system 1 executes information processing on the purchase of receivables of a business operator who opens a store on a commercial transaction site on a network (for example, the Internet). The commercial transaction site is, for example, an electronic shopping mall (online mall). Note that the commercial transaction site is not limited to an electronic shopping mall, and may be, for example, various types of commercial transaction sites such as an online shopping site, an auction site, or a flea market site, as long as the information processing described below is applicable. In addition, hereinafter, a business operator who opens a store on a commercial transaction site may be described as a store owner, and a business operator who opens a store on a commercial transaction site and then leaves the commercial transaction site may be described as a store leaver.

[0011] The information processing described below illustrates a case where future receivables are processed as an example of receivables. The future receivables referred to here are, for example, future sales that have not yet occurred for a store that has opened on a commercial transaction site. The future receivables may also be sales that a store that has opened on a commercial transaction site is expected to generate in the future on the commercial transaction site. Note that the processing for future receivables described below is merely an example, and the receivables are not limited to future receivables, and may be any receivables as long as the information processing described below is applicable. For example, the receivables may be any receivables as long as they are permitted by law or other regulations to be subject to factoring.

[0012] [1-1. Configuration of information processing system] Prior to the description of the processes shown in FIGS. 1 to 6, the configuration of the information processing system 1 will be described with reference to FIGS. 1 and 7. FIG. 7 is a diagram showing a configuration example of the information processing system according to the embodiment. As shown in FIG. 7, the information processing system 1 includes a user terminal 10, a store device 20, a web server 30, and an information processing device 100. The user terminal 10, the store device 20, the web server 30, and the information processing device 100 are connected to each other via a predetermined network N so as to be able to communicate with each other by wire or wirelessly. Note that the information processing system 1 shown in FIG. 7 may include a plurality of user terminals 10, a plurality of store devices 20, a plurality of web servers 30, and a plurality of information processing devices 100.

[0013] The user terminal 10 is a computer used by a user. The user terminal 10 is a device (terminal device) that can be carried by the user. For example, the user terminal 10 is used by the user to access content such as a web page displayed in a browser or content for an application. For example, the user terminal 10 is used by the user to browse content (web pages, etc.) of a commercial transaction site, to purchase products on the commercial transaction site, and to post evaluations (so-called reviews) of product information.

[0014] The user terminal 10 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a mobile phone, a PDA (Personal Digital Assistant), or the like. FIG. 1 shows a case where the user terminal 10 is a smartphone. In the following, the user terminal 10 may be referred to as a user. That is, in the following, a user can also be read as a user terminal 10.

[0015] The store device 20 is a computer used by a business operator who conducts a store-related business. For example, the store device 20 is used by a business operator (store owner) of a store (shop) that opens a shop on a commercial transaction site. The store device 20 transmits and receives information to and from the web server 30. The business operator uses the store device 20 to open a shop on the commercial transaction site provided by the web server 30. The store device 20 transmits various information related to the store that the business operator opens on the commercial transaction site to the web server 30. For example, the store device 20 transmits various information related to the store to the information processing device 100. The store device 20 transmits information requested by the information processing device 100 to the information processing device 100.

[0016] The store device 20 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (notebook computer), a desktop PC, a mobile phone, a PDA, or the like. FIG. 1 shows a case where the store device 20 is a notebook computer. In the following, the store device 20 may be written as a store or a business operator (store owner) that has opened the store. In other words, in the following, the store or business operator (store owner) may be read as the store device 20.

[0017] The web server 30 is a server device that provides an electronic commerce service to a user. The web server 30 provides a commerce site, such as an online shopping mall, on a network. The web server 30 provides an online shopping service at the commerce site to a user. For example, the web server 30 provides various information about the commerce site in response to a request from a user terminal 10 used by the user, and executes a purchase process for a product that the user wishes to purchase.

[0018] In the commercial transaction site provided by the web server 30, each business opens a shop (store) that handles various categories of products. The web server 30 accepts a request from the store device 20 used by the business to open a store on the commercial transaction site. The web server 30 receives various information on the store that the business opens on the commercial transaction site from the store device 20. The web server 30 adds the store opened by the business that made the request to the commercial transaction site. Note that the information communication between the web server 30, the store device 20, and the user terminal 10 described above is similar to that in the case of online shopping in a general electronic commerce service, so a detailed description will be omitted.

[0019] The web server 30 provides information to the information processing device 100. The web server 30 transmits various pieces of information required for processing by the information processing device 100 to the information processing device 100. The web server 30 provides information related to a commercial transaction site to the information processing device 100. For example, the web server 30 provides various pieces of information collected at the commercial transaction site to the information processing device 100. For example, the web server 30 provides various pieces of information such as sales history of each store at the commercial transaction site and purchase history of each user to the information processing device 100. The web server 30 provides information collected from the store device 20 and the user terminal 10 to the information processing device 100.

[0020] The information processing device 100 is a computer that executes information processing regarding the purchase of receivables of businesses that have stores on a commercial transaction site. For example, the information processing device 100 is a decision device that uses various information to decide conditions for purchasing receivables (also called "factoring conditions"). The information processing device 100 also uses various information to decide the upper limit of the purchase price of a store's receivables. The information processing device 100 also decides the mode of collection of accounts receivable corresponding to the store's future receivables based on the estimated (predicted) probability of the store closing. The information processing device 100 also decides a proposed store to which the purchase of receivables will be proposed, from among multiple stores that have stores on the commercial transaction site.

[0021] [1-2. Overview of processing in information processing systems] From here, an example of information processing performed by the information processing system 1 will be described with reference to Figures 1 to 6. First, an overview of the processing in the information processing system 1, including the transmission and reception of information between each device of the information processing system 1, will be described with reference to Figure 1, and then each information processing will be described in detail with reference to Figures 2 to 6. Note that the electronic commerce service provided by the information processing system 1 is similar to a general electronic commerce service except for points related to the purchase of receivables, and therefore detailed explanations of points other than the processing related to the purchase of receivables will be omitted as appropriate.

[0022] First, the store device 20 used by the business operator performs a process to open a store of the business operator (step S1). For example, the store device 20 requests the web server 30 to open a store in response to an operation of the business operator, and the web server 30 adds the store of the business operator to a commercial transaction site in response to the request from the store device 20.

[0023] Furthermore, a user using the user terminal 10 uses a commercial transaction site provided by the web server 30 (step S2). For example, the web server 30 provides the user with an online shopping service at the commercial transaction site in response to a request from the user terminal 10 used by the user. For example, the web server 30 provides various information related to the commercial transaction site to the user terminal 10, and executes a purchasing process for a product that the user wishes to purchase.

[0024] Then, the information processing device 100 acquires information to be used for processing from the web server 30 (step S3). The information processing device 100 receives information related to the commercial transaction site from the web server 30. For example, the information processing device 100 acquires various information collected by the web server 30 through the services of the commercial transaction site from the web server 30. For example, the information processing device 100 acquires various information such as sales history of each store on the commercial transaction site and purchase history of each user from the web server 30. Note that the information processing device 100 may acquire information from the store device 20 or the user terminal 10.

[0025] Then, the information processing device 100 executes various information processes using the acquired information (step S4). The information processing device 100 executes a decision process using the acquired information. For example, the information processing device 100 executes a decision process for determining conditions regarding the purchase of a bond using the acquired information, which will be described in detail later.

[0026] Then, the information processing device 100 provides a service to the business operator using the information determined by the determination process (step S5). For example, the information processing device 100 provides an information provision service to the business operator using the information determined by the determination process. The information processing device 100 transmits the information determined by the determination process to the store device 20 used by the business operator. For example, the information processing device 100 transmits information indicating the upper limit of the purchase amount of the receivables of the store based on the information determined by the determination process to the store device 20 used by the business operator. In this way, the information processing device 100 can provide an appropriate service related to the purchase of receivables by providing information to the business operator using the information determined by the determination process. Details of the service provided by the information processing device 100 to the store will be described later.

[0027] [1-3. Details of information processing] Based on the information processing performed by the information processing system 1 described above, various information processing operations executed by the information processing device 100 will be described in detail. Note that the same points as those described above will not be described as necessary. In addition, various types of processing operations described below may be combined as appropriate.

[0028] [1-3-1. Classification-based processing] For example, the information processing device 100 may perform the determination process using a grouping result obtained by grouping (classifying) a plurality of stores into a plurality of groups. In this case, the information processing device 100 groups the stores based on information indicating the probability of non-recovery calculated based on the store data (store information), and determines factoring conditions such as the upper limit of purchase months, which is an example of an index value, for each group. Then, the information processing device 100 determines the upper limit of purchase amount by multiplying the upper limit of purchase months by a value based on the store's sales performance (the most recent month, etc.). An example of such a process based on classification will be described with reference to FIG. 2. FIG. 2 is a diagram showing an example of information processing executed by the information processing device. Note that in the example of FIG. 2, only some stores such as stores SP1, SP2, SP12, and SP15 are illustrated as examples of stores opened on the commercial transaction site, but it is assumed that many stores are opened on the commercial transaction site.

[0029] FIG. 2 shows an example of a case where the information processing device 100 performs grouping using model M1, which is a learning model (hereinafter also simply referred to as "model") that outputs a score (also referred to as "store closure score") indicating the probability (likelihood) that a store will close from a trading site. Model M1 is a store closure model, and is a model that is learned by machine learning. Note that grouping using information regarding store closures is merely an example, and the information processing device 100 may perform grouping of stores using information regarding the risk of uncollecting receivables, not limited to store closures.

[0030] For example, the risk of uncollectible receivables includes negative events (also referred to as "negative events") for a commercial transaction site. Negative events include various actions (also referred to as "negative actions") that may cause negative events depending on the store. For example, negative events include violation of terms and conditions, inability to contact, sale of illegal items, malicious advertising, sale of counterfeit goods, non-payment of store opening fees, sudden drop in store evaluation, frequent cancellations, delivery delays, etc. For example, the information processing device 100 may group stores using information on various risks including the negative events described above. Furthermore, the information processing device 100 may group stores using information on the future prospects of the stores, not limited to information on risks such as store closure.

[0031] Furthermore, the information processing device 100 may acquire the model M1 from a model providing server or the like that provides a learning model, or may learn the model M1 on its own device. For example, when learning the model M1, the information processing device 100 learns the model M1 using the learning data LDT1 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT1 includes data that associates information about a store (also referred to as "store information") with a label (also referred to as "correct answer information") that indicates whether the store has closed or not.

[0032] The store information may include various information such as information on the business of the store's operator (business information), information on products traded (sold) at the store (product information), information on the categories of products traded (sold) at the store (category information), information on the sales of the store (sales information), and information on the evaluation of evaluation targets related to the store (evaluation information), which will be described in detail later. For example, the correct answer information for each store is assigned "1" if the store has closed, and "0" if the store has not closed. For example, the correct answer information for each store may be assigned "1" to the store information of a store up to a certain point in time (point in time X) if the store has closed within one year from point in time X, and "0" if the store has not closed within one year from point in time X. In this case, the information processing device 100 can generate a model that estimates (predicts) the probability (possibility) of a store closing within a desired period (for example, one month, six months, five years, etc.), not limited to one year.

[0033] For example, the information processing device 100 performs a learning process using a method such as backpropagation so that the score output by the model M1 approaches the correct answer information (label) associated with the store information of the store input to the model M1. For example, the information processing device 100 performs a learning process so that the score output by the model M1 to which store information including at least one of the business information, product information, category information, sales information, and evaluation information of the store is input approaches the correct answer information associated with the store. For example, when the correct answer information is "1", the information processing device 100 performs a learning process so that the score output by the model M1 approaches "1" when store information of the store to which the correct answer information is assigned is input. Also, for example, when the correct answer information is "0", the information processing device 100 performs a learning process so that the score output by the model M1 approaches "0" when store information of the store to which the correct answer information is assigned is input.

[0034] For example, the information processing device 100 adjusts the value of the weight (i.e., the connection coefficient) that is taken into consideration when a value is transmitted between nodes by the learning process. In this way, the information processing device 100 learns the model M1 by a process such as backpropagation that corrects the parameters (connection coefficients) so as to reduce the error between the output in the model M1 and the correct answer information corresponding to the input. For example, the information processing device 100 generates the model M1 by performing a process such as backpropagation to minimize a predetermined loss function. This allows the information processing device 100 to perform a learning process that learns the parameters of the model M1.

[0035] The learning method of the model is not limited to the above-mentioned method, and any known technology can be applied. The generation of each model may be performed by appropriately using various conventional technologies related to machine learning. For example, the generation of the model may be performed by using a technology related to machine learning of supervised learning, such as SVM (Support Vector Machine). Also, for example, the generation of the model may be performed by using a technology related to machine learning of unsupervised learning. For example, the generation of the model may be performed by using a deep learning technology. For example, the generation of the model may be performed by appropriately using various deep learning technologies such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). Note that the description regarding the generation of the above model is an example, and the generation of the model may be performed by a learning method appropriately selected according to the obtainable information, etc. That is, the information processing device 100 may generate the model M1 by any method as long as the model M1 can be learned so as to output a score corresponding to the correct answer information when the store information included in the learning data is input.

[0036] From here, the information processing shown in FIG. 2 will be described in detail on the premise of the above contents. First, in FIG. 2, the information processing device 100 calculates a store exit score for each of a plurality of stores that open in a commercial transaction site. The information processing device 100 inputs store information SINF1 of the store SP1 to the model M1 (step S11-1). For example, the information processing device 100 inputs store information SINF1 including at least one of business information, product information, category information, sales information, and evaluation information of the store SP1 to the model M1. The model M1 to which the store information SINF1 is input outputs a score (step S11-2). In the example of FIG. 2, the model M1 to which the store information SINF1 is input outputs a score "0.9" as shown in the score SC1. In this way, since the store exit score of the store SP1 is "0.9" and is close to "1", the information processing device 100 can estimate that there is a high possibility that the store SP1 will exit the commercial transaction site.

[0037] The information processing device 100 also inputs store information SINF2 of store SP2 to the model M1 (step S11-3). For example, the information processing device 100 inputs store information SINF2 including at least one of business information, product information, category information, sales information, and evaluation information of store SP2 to the model M1. The model M1 to which the store information SINF2 has been input outputs a score (step S11-4). In the example of FIG. 2, the model M1 to which the store information SINF2 has been input outputs a score "0.05" as shown in the score SC2. In this way, since the exit score of store SP2 is "0.05" and is close to "0", the information processing device 100 can estimate that there is a low possibility that store SP2 will exit the trading site.

[0038] Similarly, the information processing device 100 inputs the store information SINF12 of the store SP12 to the model M1 (step S11-5), and the model M1 to which the store information SINF12 has been input outputs a score (step S11-6). In the example of FIG. 2, the model M1 to which the store information SINF12 has been input outputs a score of "0.07" as shown in the score SC12. In addition, the information processing device 100 inputs the store information SINF15 of the store SP15 to the model M1 (step S11-7), and the model M1 to which the store information SINF15 has been input outputs a score (step S11-8). In the example of FIG. 2, the model M1 to which the store information SINF15 has been input outputs a score of "0.15" as shown in the score SC15. By the same process, the information processing device 100 calculates the store exit scores for stores other than the stores SP1, SP2, SP12, and SP15 in the same manner, but detailed explanations will be omitted.

[0039] Then, the information processing device 100 classifies the stores into a plurality of groups based on the store exit score of each store (step S12). The information processing device 100 groups each store into a plurality of groups using the store exit score of each store and a plurality of thresholds. For example, the information processing device 100 groups each store into a plurality of groups using a threshold related to grouping stored in the threshold information storage unit 123 (see FIG. 11). For ease of explanation, FIG. 2 illustrates an example in which nine thresholds increasing at intervals of "0.1" are used. Specifically, a first threshold TH1 of value "0.1", a second threshold TH2 of value "0.2", a third threshold TH3 of value "0.3", a fourth threshold TH4 of value "0.4", a fifth threshold TH5 of value "0.5", a sixth threshold TH6 of value "0.6", a seventh threshold TH7 of value "0.7", an eighth threshold TH8 of value "0.8", and a ninth threshold TH9 of value "0.9" are used.

[0040] The information processing device 100 groups each store into a plurality of groups according to a comparison result of comparing the store exit score of each store with nine thresholds (first threshold TH1 to ninth threshold TH9). As shown in grouping information GLT1 in FIG. 2, the information processing device 100 groups each store into ten groups according to the store exit score of each store. Specifically, the information processing device 100 classifies each store into any one of a first group, a second group, a third group, a fourth group, a fifth group, a sixth group, a seventh group, an eighth group, a ninth group, and a tenth group. Note that the number of groups is not limited to ten, and may be any number, for example, five, fifteen, or the like.

[0041] Here, as shown in the grouping information GLT1 in FIG. 2, each group is associated with a number of months for which future receivables are to be purchased (also referred to as "number of months to be purchased"). This allows the information processing device 100 to determine conditions for purchasing receivables for each group. For example, the information processing device 100 determines that a longer number of months to be purchased is to be assigned to a group to which a store estimated to have a lower probability of closing is included. In this way, the information processing device 100 determines conditions that are more favorable to stores belonging to a group that is less likely to close. In other words, the information processing device 100 determines conditions that are more favorable to stores belonging to a group that is lower risk.

[0042] In the example of Fig. 2, the first group, which includes stores estimated to have the lowest probability of closing, is associated with the longest number of months for purchase, "3." In this case, the information processing device 100 indicates that stores belonging to the first group are eligible for purchase of future claims up to three months in advance.

[0043] Furthermore, the shortest number of months for purchase, "0", is associated with the 10th group, which includes stores estimated to have the highest probability of closing. In this case, the information processing device 100 indicates that it will not purchase future claims for stores that belong to the 10th group. For example, when the information processing device 100 purchases items other than future claims, it only purchases items other than future claims for stores that belong to the 10th group.

[0044] For example, the information processing device 100 classifies stores whose exit score is less than the first threshold TH1 into a first group. In Fig. 2, the information processing device 100 classifies store SP2 whose exit score is "0.05" and is less than the first threshold TH1 of "0.1" into the first group. The information processing device 100 also classifies store SP12 whose exit score is "0.07" and is less than the first threshold TH1 of "0.1" into the first group.

[0045] In addition, the information processing device 100 classifies stores whose exit score is equal to or greater than the first threshold TH1 and less than the second threshold TH2 into a second group. In Fig. 2, the information processing device 100 classifies store SP15 whose exit score is "0.15", which is equal to or greater than the first threshold TH1 of "0.1" and less than the second threshold TH2 of "0.2", into the second group.

[0046] Furthermore, the information processing device 100 classifies stores whose exit score is equal to or greater than the second threshold TH2 and less than the third threshold TH3 into a third group. In Fig. 2, the information processing device 100 classifies store SP3 whose exit score (e.g., "0.23") is equal to or greater than the second threshold TH2 of "0.2" and less than the third threshold TH3 of "0.3" into the third group. Similarly, the information processing device 100 classifies stores that satisfy the conditions into a fourth group to a ninth group using the third threshold TH3 to the ninth threshold TH9.

[0047] Furthermore, the information processing device 100 classifies stores whose exit scores are equal to or greater than the ninth threshold TH9 into a tenth group. In Fig. 2, the information processing device 100 classifies store SP1 whose exit score is "0.9" and is equal to or greater than the ninth threshold TH9 of "0.9" into the tenth group.

[0048] The above-mentioned process is merely an example, and the information processing device 100 may group each store into a plurality of groups using various information as appropriate. For example, the information processing device 100 may group each store using a value (also called a "damage score") obtained by multiplying the store's exit score by the sales of each store. In this case, the information processing device 100 may classify a store into a group with better conditions for buying back receivables, as the damage score becomes lower.

[0049] Furthermore, the information processing device 100 may group each store into a plurality of groups without using a threshold value. For example, the information processing device 100 may group based on information related to ratios or logarithms. For example, the information processing device 100 may group the stores so that the scores belonging to each group have as equal a ratio as possible. For example, the information processing device 100 may sort the stores in ascending order of store exit scores, and divide the stores into 10 groups from the first group to the tenth group so that the groups are evenly classified into each group.

[0050] Then, the information processing device 100 determines the upper limit of the purchase price of the future receivables of each store according to the classification result (step S13). For example, the information processing device 100 determines the upper limit of the purchase price of the future receivables of each store using the formula "Upper limit of purchase price = Sales x Number of months to be purchased" as shown in the calculation function FC1 in FIG. 2. Specifically, the information processing device 100 determines the upper limit of the purchase price of the future receivables of the store by multiplying the sales of the store by the number of months to be purchased assigned to the group to which the store belongs. The sales value of the store in the previous month may be used as the sales value of the store, or the average value of the sales value of the past months may be used as the sales value of the store. Note that the sales value of the previous month and the average value of the sales value of the past months are merely examples, and any value that can be used as the sales value of the store in one month may be used as the sales value of the store, and for example, a forecast value (estimated value) of the sales value for the future month may be used.

[0051] For example, when the sales of store SP1 is a value SL1, the information processing device 100 determines the upper buyback price to be "0 (=SL1 x 0)" for store SP1 belonging to the 10th group whose buyback month count is "0". The value SL1 is assumed to be a specific numerical value such as "30,000 yen" or "150,000 yen".

[0052] Furthermore, when the sales of store SP2 is value SL2, the information processing device 100 determines the upper buy-back limit for store SP2 belonging to the first group in which the number of buy-back months is "3" as "PL2 (=SL2 x 3)". Note that the value SL2 is assumed to be a specific numerical value such as "50,000 yen" or "120,000 yen". In other words, the upper buy-back limit PL2 is three times the sales value SL2. Similarly, the information processing device 100 determines the upper buy-back limits for other stores.

[0053] The information processing device 100 may adjust the upper buyback amount using other information. For example, the information processing device 100 may increase the upper buyback amount for a store that has used factoring in the past and has completed collection without delay. For example, the information processing device 100 may increase the upper buyback amount for a store that is highly rated by users or has high future potential. For example, the information processing device 100 may increase the upper buyback amount when the score output by a future potential model described later is equal to or higher than a predetermined threshold.

[0054] Then, the information processing device 100 provides information using the determined information (step S14). For example, the information processing device 100 may provide information indicating the upper buy-back limit to a store whose upper buy-back limit is equal to or greater than a predetermined value. In this case, the information processing device 100 may transmit information indicating the upper buy-back limit to the store device 20 of the store whose upper buy-back limit is equal to or greater than a predetermined value (e.g., 100,000 yen). The information processing device 100 may also provide information indicating the upper buy-back limit or the number of buy-back target months to a store whose number of buy-back target months is equal to or greater than a predetermined value. In this case, the information processing device 100 may transmit information indicating the upper buy-back limit or the number of buy-back target months to the store device 20 of the store whose number of buy-back target months is equal to or greater than a predetermined value (e.g., 2 months).

[0055] In this way, the information processing device 100 classifies a plurality of stores that are open on the commercial transaction site into a plurality of groups, and determines the conditions for buying receivables for each group. This allows the information processing device 100 to purchase receivables according to the determined conditions, and thus makes it possible to provide appropriate services for buying receivables. For example, when factoring future receivables, future receivables are purchased, so if a store closes in the near future, it may be difficult to collect funds. Therefore, the information processing device 100 groups stores according to the risk of store closure, etc., and determines index values ​​such as the number of months for purchase for each group, thereby reducing the possibility that it will be difficult to collect funds.

[0056] In the above example, the model M1, which is a learning model, is used to calculate the store exit score. However, the information processing device 100 may calculate the store exit score of each store without using the learning model. In this case, the information processing device 100 may calculate the store exit score of each store based on a rule, for example. The information processing device 100 may calculate the store exit score of each store using rule information that associates conditions with store exit scores, for example. The information processing device 100 may compare the store information with each rule (condition), and when the store information of a store satisfies a rule, the store exit score of the rule may be the store exit score. The information processing device 100 may also compare the store information with the rules (conditions) belonging to each group, and classify the store into a group in which the store information of the store satisfies the rule.

[0057] [1-3-2. Processing based on a model corresponding to the period] The above-mentioned grouping-based processing is merely an example, and the information processing device 100 may determine the conditions for purchasing receivables without performing grouping. In this case, the information processing device 100 generates a learning model that uses store data (store information) to estimate the probability (likelihood) of occurrence of negative events such as store closure or violation of rules within a certain period, and determines factoring conditions such as the maximum number of months for purchasing future receivables based on the estimated information.

[0058] 3, the withdrawal of a store from a trading site is described as an example of a negative event, but as described above, negative events are not limited to the withdrawal of a store, and may include violation of regulations, inability to contact, sale of illegal items, malicious advertising, sale of counterfeit goods, non-payment of store opening fees, sudden drop in store evaluation, frequent cancellations, delivery delays, etc. For example, the information processing device 100 estimates a period during which the possibility of a store withdrawing satisfies a predetermined criterion using a plurality of models that output scores indicating the probability (likelihood) of a store withdrawing for each period, and determines factoring conditions based on that period.

[0059] This point will be explained using FIG. 3. FIG. 3 is a diagram showing an example of information processing executed by an information processing device. FIG. 3 explains processing based on a model corresponding to a period as an example. In the example of FIG. 3, an example is explained in which store SP12 is the store for which factoring conditions are determined (also referred to as the "target store"), but the target store is not limited to store SP12 and may be any store that opens on a trading site. Note that explanations of points similar to those described above will be omitted as appropriate.

[0060] 3 shows an example in which the information processing device 100 performs a decision process using a plurality of models M11, M12, M13, M14, etc., which are learning models (models) that output a score (store exit score) indicating the probability (likelihood) that a store will exit a commerce site within a predetermined period. The models M11, M12, M13, M14, etc. are store exit models that each correspond to a different period, and are models that are learned by machine learning.

[0061] Here, model M11 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the trading site within one month from that point. Model M12 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the trading site within two months from that point. Model M13 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the trading site within three months from that point. Model M14 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the trading site within four months from that point. Note that, although only models M11, M12, M13, and M14 are illustrated in FIG. 3, a model corresponding to each period, such as model M15 that outputs a score indicating the probability (possibility) that the target store will withdraw from the trading site within five months and model M16 that outputs a score indicating the probability (possibility) that the target store will withdraw from the trading site within six months, may be used. In addition, the period is not limited to one month, and may be any interval such as one week.

[0062] Furthermore, the information processing device 100 may acquire a plurality of models M11, M12, M13, M14, etc. from a model providing server or the like that provides a learning model, or may learn a plurality of models M11, M12, M13, M14, etc. in the information processing device 100 itself. For example, when learning the model M11, the information processing device 100 learns the model M11 using the learning data LDT11 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT11 includes data that associates information about the store (store information) with a label (correct answer information) that indicates whether the store has closed within one month from the time when the latest information in the store information was acquired (also referred to as the "starting time").

[0063] For example, as the correct answer information of each store, if the store has closed within one month from the start time, "1" is assigned, and if the store has not closed within one month from the start time, "0" is assigned. The information processing device 100 performs a learning process so that the score output by the model M11 to which the store information of the store is input approaches the correct answer information associated with the store. For example, when the correct answer information is "1", the information processing device 100 performs a learning process so that the score output by the model M11 approaches "1" when the store information of the store to which the correct answer information is assigned is input. Also, for example, when the correct answer information is "0", the information processing device 100 performs a learning process so that the score output by the model M11 approaches "0" when the store information of the store to which the correct answer information is assigned is input. Note that the learning process of the model M11 is similar to the learning process of the model M1, and therefore a detailed description will be omitted.

[0064] Furthermore, when training the model M12, the information processing device 100 trains the model M12 using the training data LDT12 stored in the model information storage unit 122. For example, the training data LDT12 includes data in which information about a store (store information) is associated with a label (correct answer information) indicating whether or not the store closed within two months from the time when the latest information in the store information was acquired (starting time).

[0065] For example, as the correct answer information of each store, if the store has closed within two months from the start time, "1" is assigned, and if the store has not closed within two months from the start time, "0" is assigned. The information processing device 100 performs a learning process so that the score output by the model M12 to which the store information of the store is input approaches the correct answer information associated with the store. For example, when the correct answer information is "1", the information processing device 100 performs a learning process so that the score output by the model M12 approaches "1" when the store information of the store to which the correct answer information is assigned is input. Also, for example, when the correct answer information is "0", the information processing device 100 performs a learning process so that the score output by the model M12 approaches "0" when the store information of the store to which the correct answer information is assigned is input. Note that the learning process of the model M12 is similar to the learning process of the models M1 and M11, and therefore a detailed description will be omitted.

[0066] Similarly, when learning a model M13, the information processing device 100 uses the learning data LDT13 stored in the model information storage unit 122 to learn the model M13, and when learning a model M14, the information processing device 100 uses the learning data LDT14 stored in the model information storage unit 122 to learn the model M14. For example, the learning data LDT13 includes data in which information about a store (store information) is associated with a label (correct answer information) indicating whether or not the store has closed within three months from the time when the latest information in the store information was acquired (starting time). For example, the learning data LDT14 includes data in which information about a store (store information) is associated with a label (correct answer information) indicating whether or not the store has closed within four months from the time when the latest information in the store information was acquired (starting time). Note that the learning process of the models M13 and M14 is similar to the learning process of the models M1, M11, and M12, and therefore detailed description thereof will be omitted. In addition, the information processing device 100 may generate the models M11, M12, M13, and M14 by any method as long as the information processing device 100 can train the models M11, M12, M13, and M14 so as to output a score corresponding to correct answer information when store information included in the training data is input.

[0067] From here, the information processing shown in FIG. 3 will be described in detail on the premise of the above contents. First, in FIG. 3, the information processing device 100 calculates a store exit score for each period for the store SP12, which is a target store. The information processing device 100 inputs store information SINF12-1 of the store SP12 to the model M11 that predicts the probability (likelihood) of store exit within one month (step S21-1). For example, the information processing device 100 inputs store information SINF12-1 including at least one of business information, product information, category information, sales information, and evaluation information of the store SP12 to the model M11. The model M11 to which the store information SINF12-1 is input outputs a store exit score (step S21-2). In the example of FIG. 3, the model M11 to which the store information SINF12-1 is input outputs a store exit score "0.02" indicating the probability (possibility) of store exit within one month as shown in the score SC12-1. Thus, since the store exit score indicating the probability (likelihood) of store SP12 exiting within one month is "0.02", which is close to "0", the information processing device 100 can estimate that there is a low possibility that store SP12 will exit the trading site within one month from that point in time.

[0068] The information processing device 100 also inputs the store information SINF12-2 of the store SP12 to the model M12 that predicts the probability (likelihood) of closing the store within two months (step S21-3). For example, the store information SINF12-2 is the same store information as the store information SINF12-1. Note that, when the model input differs for each period, the store information SINF12-2 may be different from the store information SINF12-1, and may be store information collected for a different period, for example. The model M12 to which the store information SINF12-2 is input outputs a store closing score (step S21-4). In the example of FIG. 3, the model M12 to which the store information SINF12-2 is input outputs a store closing score of "0.2" that indicates the probability (likelihood) of closing the store within two months, as shown in the score SC12-2.

[0069] Similarly, the information processing device 100 inputs the store information SINF12-3 of the store SP12 to the model M13 that predicts the probability (likelihood) of closing the store within three months (step S21-5), and the model M13 to which the store information SINF12-3 has been input outputs a store closing score (step S21-6). For example, the store information SINF12-3 is the same store information as the store information SINF12-1. Note that, when the model input differs for each period, the store information SINF12-3 may be different from the store information SINF12-1 and the store information SINF12-2. In the example of FIG. 3, the model M13 to which the store information SINF12-3 has been input outputs a store closing score of "0.52" indicating the probability (likelihood) of closing the store within three months, as shown in the score SC12-3.

[0070] Furthermore, the information processing device 100 inputs the store information SINF12-4 of the store SP12 into the model M14 that predicts the probability (likelihood) of closing the store within four months (step S21-7), and the model M14 to which the store information SINF12-4 has been input outputs a store closing score (step S21-8). In the example of FIG. 3, the model M14 to which the store information SINF12-4 has been input outputs a store closing score of "0.65" indicating the probability (likelihood) of closing the store within four months as shown in the score SC12-4. In this way, the information processing device 100 calculates a store closing score whose value increases as the period becomes longer. Note that the information processing device 100 may calculate a store closing score indicating the probability (likelihood) of closing the store within five months or a store closing score indicating the probability (likelihood) of closing the store within six months.

[0071] Then, the information processing device 100 determines the number of months for which the future receivables of the store SP12 are to be purchased based on the store SP12's store closing score for each period (step S22). For example, the information processing device 100 estimates the time when the store SP12 is likely to close, using a threshold value related to store closing time estimation stored in the threshold information storage unit 123 (see FIG. 11). In FIG. 3, a case where the threshold value TH11 related to store closing time estimation is 0.5 is described as an example.

[0072] The information processing device 100 compares the store exit score output by each model with a threshold value TH11, and determines the number of months for which future receivables of the target store will be purchased based on the comparison result. For example, the information processing device 100 determines the period corresponding to the learning model with the shortest period among the learning models whose store exit scores are equal to or greater than the threshold value TH11 as the number of months for which future receivables of the target store will be purchased. In FIG. 3, the information processing device 100 determines the number of months for which future receivables of the store SP12 will be purchased by comparing the store exit scores output by the models M11, M12, M13, M14, etc. with the value of the threshold value TH11, "0.5". Since the store exit score "0.52" output by the model M13 that predicts the probability (possibility) of store exit within three months is equal to or greater than the threshold value TH11, the information processing device 100 determines the number of months for which future receivables of the store SP12 will be purchased to "3", as shown in the target months information TM1 in FIG. 3.

[0073] The above-mentioned process is merely an example, and the information processing device 100 may determine the number of months for which future receivables of the target store are to be purchased by appropriately using various information. For example, the information processing device 100 may determine the number of months for which future receivables of the target store are to be purchased by a period shorter than the period corresponding to the shortest learning model among the learning models whose store exit scores are equal to or greater than the threshold value TH11. In this case, the information processing device 100 may determine the number of months for which future receivables of the store SP12 are to be purchased by a period shorter than the period (three months) corresponding to the model M13 whose store exit scores are equal to or greater than the threshold value TH11 (for example, two months, etc.). In addition, for example, the information processing device 100 may determine the number of months for which future receivables are to be purchased by using a value obtained by accumulating the store exit scores of each period. For example, the information processing device 100 may calculate the cumulative score by accumulating the store exit scores in ascending order of months, compare the cumulative score with the threshold value, and determine the number of months when the cumulative score exceeds the threshold value as the number of months for which the store exit scores are to be purchased. In this case, for example, if the exit score one month later is "0.02" and the exit score two months later is "0.2", the information processing device 100 calculates the cumulative score as "0.22 (=0.02+0.2)". If the threshold is "0.2", the information processing device 100 determines the number of months for which the cumulative score "0.22" exceeds the threshold "0.2" to be the number of months eligible for purchase.

[0074] Then, the information processing device 100 determines the upper limit of repurchase price of future receivables of store SP12 based on the determined number of months to be repurchased and the sales information of store SP12, but detailed description will be omitted since this is the same as the process described in Fig. 2. For example, the information processing device 100 uses the calculation function FC1 (see Fig. 2) to determine the upper limit of repurchase price of store SP12 as "PL2 (=SL2 x 3)" when the sales of store SP2 are value SL2.

[0075] Then, the information processing device 100 provides information using the determined information (step S23). Note that the information provision is similar to the process described in FIG. 2, so detailed description will be omitted. For example, the information processing device 100 may provide information indicating the number of months for which the store SP12 is eligible for resale or the upper limit of the resale price to the operator of the store SP12. In this case, the information processing device 100 may transmit information indicating the number of months for which the store SP12 is eligible for resale or the upper limit of the resale price to the store device 20 used by the operator of the store SP12.

[0076] In this way, the information processing device 100 predicts the store exit score for each period for the target store, and determines the conditions for purchasing receivables using the predicted store exit score for each period. As a result, the information processing device 100 can purchase receivables according to the determined conditions, making it possible to provide appropriate services for purchasing receivables. For example, when factoring future receivables, future receivables are purchased, so if the store closes in the near future, it may be difficult to collect funds. Therefore, the information processing device 100 predicts a period in which the target store is likely to close, and determines an index value such as the number of months to be purchased according to that period, thereby reducing the possibility that it will be difficult to collect funds.

[0077] As described above, for example, the information processing device 100 can increase the amount of receivables to be purchased by estimating the period until the store closes and setting the sales during that period as the purchase target period. Note that the above-mentioned process is merely an example, and the information processing device 100 determines the factoring conditions using various information. For example, the information processing device 100 may use multiple models that estimate the occurrence probability of each negative event. In this case, the information processing device 100 may estimate the store's closure probability using multiple scores output by multiple models corresponding to the negative events. The information processing device 100 may calculate the occurrence probability of each negative event, estimate the store's closure probability based on the calculated occurrence probability, and determine the factoring conditions based on the estimated store closure probability.

[0078] [1-3-3. Processing based on social conditions] The information processing device 100 may use various information, not limited to store information. For example, the information processing device 100 may use social conditions such as the economic situation of society. In this case, the information processing device 100 may estimate the total number of closing stores (hereinafter also simply referred to as the "number of closing stores" or "number of store closures") based on social conditions such as stock prices, and set purchase conditions based on the estimated number of closing stores. For example, the information processing device 100 reflects the estimated number of closing stores in the grouping of stores.

[0079] In FIG. 4, the number of stores that close from a trading site (number of closed stores) is described as an example of the number of occurrences of negative events, but as described above, the negative events to be estimated for the number of occurrences are not limited to store closures, but may be violations of regulations, inability to contact, sales of illegal items, malicious advertising, sales of counterfeit goods, non-payment of store opening fees, sudden drop in store evaluation, frequent cancellations, delivery delays, etc. In this way, the number of occurrences of negative events to be targeted is not limited to the number of store closures, but may be the number of occurrences of various negative events. For example, the information processing device 100 estimates the number of closed stores using social situation information indicating the economic situation of society, and determines the factoring conditions based on the estimated number of closed stores.

[0080] This point will be explained with reference to FIG. 4. FIG. 4 is a diagram showing an example of information processing executed by an information processing device. FIG. 4 shows an example of processing based on social conditions. FIG. 4 explains an example of processing for changing the threshold value used for grouping based on the number of store closures estimated based on social conditions. Specifically, FIG. 4 explains an example of processing for changing the threshold value used in FIG. 2 based on the number of store closures estimated based on social conditions. Note that explanations of points similar to those described above will be omitted as appropriate.

[0081] 4 shows an example in which the information processing device 100 changes the threshold value using model M31, which is a learning model (model) that outputs a score indicating the number of closed stores corresponding to the social situation. Model M31 is a model used to estimate the number of closed stores, and is a model that is learned by machine learning. In FIG. 4, an example is described in which model M31 outputs the number of closed stores as a score indicating the number of closed stores, but the score output by model M31 is not limited to the number of closed stores itself, and may be a value used to calculate the number of closed stores (for example, a ratio to the number of closed stores at that time, etc.).

[0082] Furthermore, the information processing device 100 may acquire the model M31 from a model providing server or the like that provides a learning model, or may learn the model M31 on its own device. For example, when learning the model M31, the information processing device 100 learns the model M31 using the learning data LDT31 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT31 includes data that associates information on a social situation (also referred to as "social situation information") with a label indicating the number of store closures corresponding to the social situation (also referred to as "correct answer information").

[0083] The social situation information includes information indicating various social situations, such as information on the economy (economic situation). For example, the social situation information includes various information indicating economic situations, such as stock prices, unemployment rates, and interest rates. For example, the number of stores closing at a time point corresponding to the social situation is associated with the correct answer information of the social situation. In FIG. 4, as the correct answer information of each social situation, a case where the number of stores closing three months after a certain time point (time point X) is assigned to the social situation information is shown as an example. The information processing device 100 generates a model M31 that estimates the number of stores closing six months after a time point corresponding to the social situation. The information processing device 100 can generate a model that estimates (predicts) the number of stores closing in a desired future (for example, one month later, six months later, one year later, five years later, etc.) corresponding to the time point of the social situation, not limited to three months later.

[0084] For example, the information processing device 100 performs a learning process so that the score output by the model M31 approaches the correct answer information (label) associated with the social situation information of the store input to the model M31. For example, when the correct answer information is "100", the information processing device 100 performs a learning process so that the score output by the model M31 approaches "100" when the social situation information of the store to which the correct answer information is assigned is input. Also, for example, when the correct answer information is "5", the information processing device 100 performs a learning process so that the score output by the model M31 approaches "5" when the social situation information of the store to which the correct answer information is assigned is input. When a store is closed from a commercial transaction site, it becomes impossible to collect receivables from the store. Therefore, in FIG. 4, the information processing device 100 learns the model M31 used to estimate the number of stores closed from the commercial transaction site as the number of uncollectible receivables. Note that the learning process of the model M31 is similar to the learning process of the model M1, etc., and therefore a detailed description will be omitted. Note that the information processing device 100 may generate the model M31 by any method as long as the information processing device 100 can train the model M31 so as to output a score corresponding to correct answer information when social situation information included in the training data is input.

[0085] From here, the information processing shown in FIG. 4 will be described in detail on the premise of the above contents. First, the information processing device 100 inputs the social situation information SDT11 indicating the social situation at the time of processing (present) to the model M31 (step S31-1). For example, the information processing device 100 inputs the social situation information SDT11 including at least one of the current stock price, unemployment rate, interest rate, etc. to the model M31. The model M31 to which the social situation information SDT11 has been input outputs a score (step S31-2). In the example of FIG. 4, the model M31 to which the social situation information SDT11 has been input outputs the number of store closures "NW1" as shown in the score SC31. Note that the number of store closures NW1 is a specific value (for example, 200, etc.) indicating the estimated number of store closures. Thus, in FIG. 4, the information processing device 100 estimates the number of store closures from the commercial transaction site as the number of uncollectible receivables.

[0086] Then, the information processing device 100 determines the threshold value based on the estimated number of store closures (step S32). In FIG. 4, the information processing device 100 changes the threshold value information TL1 used up to that point to the threshold value information TL2. For example, the information processing device 100 lowers the threshold value when the estimated number of store closures NW1 satisfies a predetermined condition. For example, the information processing device 100 lowers the threshold value when the number of store closures NW1 is greater than the number of store closures at that point (present) (also referred to as the "current actual value"). In FIG. 4, for simplicity of explanation, a case in which the information processing device 100 lowers each threshold value by 0.5 is described as an example, but the information processing device 100 may change the threshold value by increasing or decreasing the threshold value according to a comparison between the number of store closures at that point (present) (current actual value) and the number of store closures NW1. In this case, the information processing device 100 may determine the threshold value under a predetermined condition that the number of store closures NW1 is different from the current actual value.

[0087] For example, the information processing device 100 may determine the threshold value according to the comparison result between the current actual measurement value and the number of store closures NW1. For example, the information processing device 100 may lower each threshold value according to the difference or ratio between the current actual measurement value and the number of store closures NW1. For example, when the number of store closures NW1 relative to the current actual measurement value is "0.9", the information processing device 100 may update each threshold value by multiplying each threshold value by "0.9". For example, when the number of store closures NW1 relative to the current actual measurement value is "1.05", the information processing device 100 may update each threshold value by multiplying each threshold value by "1.05". In addition, the information processing device 100 may change each threshold value individually. For example, the information processing device 100 may lower only the first threshold value TH1 according to the difference or ratio between the number of store closures at that time (present) and the number of store closures NW1. Note that the above is only an example, and the information processing device 100 may change the threshold value by processing using various information appropriately.

[0088] Then, the information processing device 100 classifies the stores into groups using the changed threshold information TL2 (step S33). Note that the process from step S33 onward is similar to the process from step S12 onward in FIG. 1 except for the values ​​of each threshold, and therefore detailed description thereof will be omitted.

[0089] In this way, the information processing device 100 changes the threshold based on the number of store closures estimated based on the economic situation, classifies the multiple stores into multiple groups using the changed threshold, and determines the conditions for purchasing receivables for each group. As a result, the information processing device 100 can perform processing using a threshold appropriately adjusted according to the economic situation and purchase receivables, making it possible to provide appropriate services related to the purchase of receivables. For example, when factoring future receivables, future receivables are purchased, so if a store closes in the near future, it may be difficult to collect funds. Therefore, the information processing device 100 performs grouping taking into account the economic situation and determines an index value such as the number of months for purchase for each group, thereby reducing the possibility that it will be difficult to collect funds.

[0090] In the above example, the model M31, which is a learning model, is used to calculate the number of store closures. However, the information processing device 100 may calculate the number of store closures without using a learning model. In this case, the information processing device 100 may calculate the number of store closures based on rules, for example. The information processing device 100 may calculate the number of store closures using rule information that associates conditions with the number of store closures, for example. The information processing device 100 may compare the social situation information with each rule (condition), and if the social situation information satisfies the rule, use the number of store closures of the rule. The information processing device 100 may also determine conditions for buying receivables without grouping. In this case, the information processing device 100 may determine the number of months for which future receivables are to be purchased according to the estimated number of store closures (number of occurrences). For example, the information processing device 100 may determine the number of months for which future receivables are to be purchased using a function in which the estimated number of store closures (number of occurrences) is a variable (explanatory variable) and the number of months for which purchase is to be made is an output value (objective variable).

[0091] As described above, the information processing device 100 estimates the number of store closures based on the social situation (economic situation) and changes the threshold value used for grouping based on the estimated number of store closures. The information processing device 100 estimates the number of stores to close in the future based on the economic situation, performs grouping using the threshold value changed based on the estimated number of store closures, and determines the factoring conditions. In this way, the information processing device 100 can determine the factoring conditions of stores based on the estimated number of store closures by grouping stores into groups associated with the factoring conditions.

[0092] The information processing device 100 may estimate the number of store closures based on prediction information indicating future social conditions (economic conditions), and may change the threshold value used for grouping based on the estimated number of store closures. In this case, the information processing device 100 may acquire prediction information indicating future social conditions (economic conditions) provided by a predetermined external device, and estimate the number of store closures using the acquired prediction information. The information processing device 100 may also estimate the number of store closures based on social conditions (economic conditions), and may change the factoring conditions of each group based on the estimated number of store closures. For example, when the estimated number of store closures is equal to or greater than a predetermined number, the information processing device 100 may reduce the number of months for which each group is to be bought. Also, for example, when the estimated number of store closures is less than a predetermined number, the information processing device 100 may increase the number of months for which each group is to be bought.

[0093] The above-mentioned process is merely an example, and the information processing device 100 may perform the process using various information. For example, the information processing device 100 may determine the conditions for buying receivables based on the number of stores closing at that time (current) and the estimated number of stores closing. For example, the information processing device 100 may determine the factoring conditions based on the relative value of the number of stores closing. For example, the information processing device 100 may lower the factoring conditions by 20% when the number of stores closing at that time (current) and the current number are "1" and the estimated number of stores closing is 1.2 times that number, or "1.2". In this case, when the number of months for which a store is currently eligible for purchase is "2", the information processing device 100 may lower the number of months for which a store is eligible for purchase to "1.6".

[0094] Also, for example, when the current total number of closed stores is 100 and the economic situation is on the decline and the number of closed stores next year is estimated to be 200, the information processing device 100 may change the threshold value used for grouping. In this case, for example, the information processing device 100 may change a certain threshold value from "0.6" to "0.5". As a result, the information processing device 100 may change the store closing score belonging to a certain group from 0.6-0.8 to 0.5-0.8. The information processing device 100 may reduce the number of months eligible for purchase.

[0095] Furthermore, the information processing device 100 may predict the store closure score for each of various factors. For example, the information processing device 100 may predict the number of stores that will close for each product handled on the commercial transaction site. In this case, the information processing device 100 may predict the number of stores that will close for each product based on the economic situation for each product. For example, if a product is popular at the time (trend product), the information processing device 100 may predict a low store closure score for that product. For example, if at-home goods are popular at the time when an infectious disease such as the coronavirus is spreading, the information processing device 100 may predict a low store closure score for products related to at-home goods.

[0096] [1-3-4. Category-based processing] The information processing device 100 may determine the factoring conditions of a store according to the category of products handled by the store. In this case, the information processing device 100 may determine the factoring conditions of the receivables of the target store based on the past sales trends of the target store and the past sales trends of each category of products handled on the commerce site.

[0097] FIG. 5 shows an example of processing according to a category (also called a "main category") corresponding to products (main products) that the store mainly handles, and a category (also called a "subcategory") corresponding to products (sub-products) other than the main products that the store handles. This point will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of information processing executed by an information processing device. FIG. 5 explains processing based on categories as an example. The information processing device 100 may determine the factoring conditions for receivables of the target store according to the category of products handled by the target store, without distinguishing between category types such as main category and subcategory.

[0098] 5, the case where store SP15 is the store (target store) for which factoring conditions are determined is described as an example, but the target store is not limited to store SP15 and may be any store that opens on a trading site. Note that explanations of points similar to those described above will be omitted as appropriate.

[0099] 5 shows an example in which the information processing device 100 performs a decision process using model M41, which is a learning model that outputs a score that estimates the sales trend for each category. Model M41 is a category sales model that estimates the sales trend of a store corresponding to a category, and is a model that is learned by machine learning. Note that while FIG. 5 shows a case in which model M41 common to the main category and subcategories is used, separate models may be used for the main category and the subcategories.

[0100] Furthermore, the information processing device 100 may acquire the model M41 or the like from a model providing server or the like that provides a learning model, or may learn the model M41 or the like in the information processing device 100. For example, when learning the model M41, the information processing device 100 learns the model M41 using the learning data LDT41 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT41 includes data that associates information on one category of products handled by one store (store-specific category information) and information on the one category on a commerce site (site category information) with a label (correct answer information) that indicates the sales trend of the one category in the one store.

[0101] For example, the learning data LDT41 includes store-specific category information including information indicating sales of products belonging to one category in one store at a certain time point (time point X), and intra-site category information including information indicating sales of products belonging to the one category across the entire trading site at a certain time point (time point X), and data in which labels (correct answer information) indicating changes in sales of the one category in the one store after time point X are associated with each other. The store-specific category information may include information indicating changes in sales of products belonging to one category in the store up to a certain time point (time point X). For example, the store-specific category information may include information on multiple sales of products belonging to one category in the store corresponding to multiple time points up to a certain time point (time point X).

[0102] The site category information may include information indicating the trend of sales of products belonging to one category across the entire trading site up to a certain point in time (point in time X). For example, the site category information may include information on multiple sales of products belonging to one category across the entire trading site corresponding to multiple points in time up to a certain point in time (point in time X). The store-specific category information and the site category information may be collectively referred to as model input information. For example, a value indicating the relationship between sales of one category in one store at point in time X and a point in time (point in time Y) after a predetermined period has elapsed since point in time X is associated as the correct answer information.

[0103] For example, if the sales of a category in a store at time Y are 1.5 times the sales of the category in the store at time X (i.e., sales increase), the value "1.5" is associated as the correct answer information. In this way, if the sales of the category in the store have increased since time X, a value greater than 1 is associated as the correct answer information. If the sales of the category in the store at time Y are 0.6 times the sales of the category in the store at time X (i.e., sales decrease), the value "0.6" is associated as the correct answer information. For example, if the sales of the category in the store have decreased since time X, a value less than 1 is associated as the correct answer information. That is, the learning data LDT41 includes information indicating whether the category is in an upward trend or a downward trend from a certain time point (time point X) as the correct answer information. Note that the above is merely an example, and various information may be used as the correct answer information. For example, the sales value at time Y itself may be used as the correct answer information. In this case, model M41 outputs a score that indicates an estimate of the category's sales in the target store.

[0104] The information processing device 100 performs a learning process so that the score output by the model M41 to which model input information corresponding to one category of the target store is input approaches the correct answer information associated with the model input information. For example, when the correct answer information is "1.2", the information processing device 100 performs a learning process so that the score output by the model M41 approaches "1.2" when the model input information to which the correct answer information is assigned is input. Also, for example, when the correct answer information is "0.8", the information processing device 100 performs a learning process so that the score output by the model M41 approaches "0.8" when the model input information to which the correct answer information is assigned is input. Note that the learning process of the model M41 is similar to the learning process of the model M1 and the like, and therefore a detailed description thereof will be omitted. Also, the information processing device 100 may generate the model M41 by any method as long as the model M41 can be trained to output a score corresponding to the correct answer information when the model input information included in the learning data is input.

[0105] From here, the information processing shown in FIG. 5 will be described in detail on the premise of the above content. First, the information processing device 100 determines the main category and subcategory of the store SP15. For example, the information processing device 100 determines the main category and subcategory of the store SP15 by referring to the store information of the store SP15. For example, the information processing device 100 may determine the category with the largest sales as the main category among the categories handled by the store SP15. For example, the information processing device 100 may determine the category with the largest number of products as the main category among the categories handled by the store SP15. Furthermore, the information processing device 100 may determine the categories other than the main category as the subcategories among the categories handled by the store SP15.

[0106] The above-mentioned determination of the main category and subcategory is merely an example, and the information processing device 100 may determine the main category and subcategory by appropriately using various information. The information processing device 100 may determine the category with the second largest sales after the main category as the subcategory among the categories handled by the store SP15. The information processing device 100 may also determine the category with the second largest number of products after the main category as the subcategory among the categories handled by the store SP15.

[0107] The information processing device 100 may determine the main category and subcategory of the store SP15 by using category information stored in the store owner information storage unit 121 (see FIG. 9). When the main category and subcategory of the store SP15 are designated by the operator of the store SP15, the information processing device 100 determines the main category and subcategory of the store SP15 according to the designation by the operator of the store SP15. In the following, a case where the main category of the store SP15 is determined to be category #1 and the subcategory is determined to be category #2 will be described as an example. The categories #1 and #2 are assumed to be specific categories such as food, beverages, alcoholic beverages, clothing, and cosmetics.

[0108] The information processing device 100 inputs model input information MINF15-1 corresponding to category #1, which is the main category of the store SP15 at the time of processing (current), to the model M41 (step S41-1). For example, the information processing device 100 inputs model input information MINF15-1 including store-specific category information including information indicating the sales of products belonging to category #1 of the current store SP15, and site category information including information indicating the sales of products belonging to the category #1 in the entire current trading site, to the model M41. The model M41 to which the model input information MINF15-1 is input outputs a score (step S41-2). In the example of FIG. 5, the model M41 to which the model input information MINF15-1 is input outputs a score "VL41" as shown in the score SC31. The main score VL41 is a value (for example, 0.4, 2.5, etc.) indicating the tendency of a trend estimated for the main category (category #1) of the store SP15.

[0109] The information processing device 100 also inputs model input information MINF15-2 corresponding to category #2, which is a subcategory of the store SP15 at the time of processing (current), to the model M41 (step S41-3). For example, the information processing device 100 inputs model input information MINF15-2 including store-specific category information including information indicating the sales of products belonging to category #2 of the current store SP15, and site category information including information indicating the sales of products belonging to the category #2 in the entire current trading site, to the model M41. The model M41 to which the model input information MINF15-2 has been input outputs a score (step S41-4). In the example of FIG. 5, the model M41 to which the model input information MINF15-2 has been input outputs a score "VL42" as shown in the score SC31. The subscore VL42 is a value (for example, 0.6, 1.8, etc.) indicating the tendency of a trend estimated for the subcategory (category #2) of the store SP15.

[0110] Then, the information processing device 100 determines the upper limit of purchase price of future receivables of store SP15 based on the trend of the category of products handled by store SP15 (step S42). In Fig. 5, the information processing device 100 determines the number of months for which store SP15's future receivables will be purchased based on the trend of the category of products handled by store SP15. For example, the information processing device 100 determines the number of months for which store SP15's future receivables will be purchased using a function (also called "months calculation function FC2") that uses the score of the main category (main score) and the score of the subcategory (subscore) as variables (explanatory variables) and the number of months for which purchase is the output value (objective variable).

[0111] For example, the number of months calculation function FC2 is a function that calculates the number of months eligible for repurchase using a first value obtained by multiplying the main score by a first coefficient (first weighting) and a second value obtained by multiplying the sub-score by a second coefficient (second weighting). For example, the number of months calculation function FC2 outputs the sum of the first value and the second value as the number of months eligible for repurchase. For example, the information processing device 100 may determine the value of each weighting so that the first weighting corresponding to the score of the main category (main score) is greater than the second weighting corresponding to the score of the sub-category (sub-score). In addition, the information processing device 100 may multiply the sub-score by a value obtained by multiplying the second weighting by a predetermined attenuation value (for example, 0.8, etc.) to calculate the second value.

[0112] 5, the information processing device 100 calculates a value VL43 indicating the number of months eligible for repurchase of the store SP15 by using a first value obtained by multiplying the main score VL41 of the store SP15 by a first weighting and a second value obtained by multiplying the sub-score VL42 of the store SP15 by a second weighting. The value VL43 is assumed to be a specific value (e.g., 1.5, 3, etc.) indicating the number of months eligible for repurchase.

[0113] Here, the information processing device 100 may determine the weighting of the categories using various information. The information processing device 100 may determine the first weight value and the second weight value using various information. For example, the information processing device 100 may weight the categories by the number of items in the category, or may weight the categories by sales. For example, the information processing device 100 may increase the weight value as the number of items in the category increases, or may increase the weight value as the sales in the category increases. For example, the information processing device 100 may increase the first weight value as the sales of the main category increase. For example, the information processing device 100 may increase the second weight value as the number of items in the subcategory increases.

[0114] Then, the information processing device 100 determines the upper limit of repurchase price of future receivables of store SP15 based on the determined number of months for repurchase and information on sales of store SP15, but detailed description will be omitted since this is the same as the process described in Fig. 2. The information processing device 100 determines the upper limit of repurchase price of store SP15 to be "PL41", as shown in the upper limit of repurchase information PL1 in Fig. 5. For example, using the calculation function FC1 (see Fig. 2), when the sales of store SP15 are value SL15, the information processing device 100 determines the upper limit of repurchase price of store SP15 to be "PL41 (=SL15 x VL43)".

[0115] Then, the information processing device 100 provides information using the determined information (step S43). Note that the information provision is similar to the process described in FIG. 2, so detailed description will be omitted. For example, the information processing device 100 may provide information indicating the number of months for which the store SP15 is eligible for resale or the upper limit of the resale price to the operator of the store SP15. In this case, the information processing device 100 may transmit information indicating the number of months for which the store SP15 is eligible for resale or the upper limit of the resale price to the store device 20 used by the operator of the store SP15.

[0116] In this way, the information processing device 100 uses category information for the target store to determine conditions for buying receivables. This allows the information processing device 100 to purchase receivables according to the category of products handled by the target store, making it possible to provide appropriate services for buying receivables. For example, when factoring future receivables, future receivables are purchased, so if a store closes in the near future, it may be difficult to collect funds. Therefore, the information processing device 100 can reduce the possibility of difficulty in collecting funds by determining index values ​​such as the number of months for purchase according to trends in the category of products handled by the target store.

[0117] In the above example, the information processing device 100 calculates scores indicating upward and downward trends for each category of products handled by the store, and determines the factoring conditions. Note that the above process is merely an example, and the information processing device 100 may determine the factoring conditions using various information. For example, if the score of the main category is high, the information processing device 100 may increase the upper limit of the purchase price. Furthermore, the information processing device 100 may weight a category with a larger number of products more. Furthermore, the information processing device 100 may weight a category with a larger sales volume more. As described above, the main category and the like may be registered in advance for each store. Furthermore, if the target store handles a category that is popular overall, the information processing device 100 may determine the factoring conditions of the target store based on the share (occupancy rate) of that category.

[0118] The information processing device 100 may also change the weighting depending on whether the category with the largest number of products handled in the target store is the main category. For example, the information processing device 100 may determine the factoring conditions of the target store depending on whether a predetermined condition is met, such as a trend of a specific category increasing or decreasing more significantly than usual. Also, for example, even if the sales of a store are on a downward trend, the information processing device 100 may improve the factoring conditions of the store if the store handles a category (e.g., corona-related goods) that is popular at that time.

[0119] [1-3-5. Processing based on models from multiple viewpoints] The information processing device 100 may perform processing based on models from multiple perspectives, not limited to a model from one perspective. In this case, the information processing device 100 determines factoring conditions such as the upper limit number of months for purchasing future receivables using two models: a store exit model (store exit prediction model) that predicts a store's exit from a commercial transaction site, and a future potential model (future potential prediction model) that predicts the future potential of the store.

[0120] 6 illustrates a store's withdrawal from a commerce site as an example of a negative event, but as described above, negative events are not limited to store withdrawal, and may include violation of regulations, inability to contact, sale of illegal items, malicious advertising, sale of counterfeit items, non-payment of store opening fees, sudden drop in store evaluation, frequent cancellations, delivery delays, etc. For example, the information processing device 100 uses models from two different perspectives, model M1 which is a store withdrawal model and model M2 which is a future potential model, to output a score indicating the probability (likelihood) of a store's withdrawal for each period, and uses multiple models to determine conditions for buying back a store's receivables.

[0121] This point will be explained with reference to FIG. 6. FIG. 6 is a diagram showing an example of information processing executed by an information processing device. FIG. 6 explains an example of processing based on a model of multiple viewpoints. In the example of FIG. 5, the case where store SP12 is the store (target store) for which factoring conditions are determined is explained as an example, but the target store is not limited to store SP12 and may be any store that opens on a trading site. Note that explanations of points similar to those described above will be omitted as appropriate. For example, model M1 used in FIG. 6 is similar to model M1 in FIG. 2, and therefore explanations of its learning process, etc. will be omitted.

[0122] 6 shows an example in which the information processing device 100 performs a decision process using model M2, which is a learning model (model) that outputs a score (also called a "future potential score") indicating the future possibility of sales of a store opening on a commerce site. Model M2 is a future potential model, and is a model that is learned by machine learning.

[0123] Furthermore, the information processing device 100 may acquire the model M2 from a model providing server or the like that provides a learning model, or may learn the model M2 on its own device. For example, when learning the model M2, the information processing device 100 learns the model M2 using the learning data LDT2 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT2 includes data that associates information about a store (store information) with a label (correct answer information) that indicates how the sales of the store have changed since the time when the latest information in the store information was acquired (acquisition time).

[0124] For example, as the correct answer information of a store, if the sales of the store have increased by 1.5 times (i.e., sales have increased) after a predetermined period of time has elapsed (e.g., one month) since the time of acquisition, "1.5" is assigned, and if the sales of the store have increased by 0.8 times (i.e., sales have decreased) after a predetermined period of time has elapsed since the time of acquisition of the store, "0.8" is assigned. The information processing device 100 performs a learning process so that the score output by the model M2 to which the store information of a store has been input approaches the correct answer information associated with the store. For example, when the correct answer information is "1.8", the information processing device 100 performs a learning process so that the score output by the model M2 approaches "1.8" when the store information of the store to which the correct answer information is assigned is input. Also, for example, when the correct answer information is "0.2", the information processing device 100 performs a learning process so that the score output by the model M2 approaches "0.2" when the store information of the store to which the correct answer information is assigned is input. In this case, a model M2 is generated that outputs a score greater than 1 if the store has high future sales potential, and outputs a score less than 1 if the store has poor future sales potential. Note that the learning process of model M2 is similar to that of model M1, and therefore a detailed description thereof will be omitted.

[0125] From here, the information processing shown in FIG. 6 will be described in detail, assuming the above content. First, in FIG. 6, the information processing device 100 calculates a store exit score and a future potential score for store SP12, which is a target store. The information processing device 100 inputs store information SINF12 of store SP12 at the time of processing (current) to model M1 (step S51-1). The model M1 to which the store information SINF12 is input outputs a score (step S51-2). In the example of FIG. 6, the model M1 to which the store information SINF12 is input outputs a score "VL51" as shown in the score SC51. Note that the store exit score VL51 is a value (for example, 0.1, 0.75, etc.) indicating the probability (possibility) that store SP12 will exit the trading site.

[0126] Furthermore, the information processing device 100 inputs store information SINF12 of the store SP12 at the time of processing (current) to the model M2 (step S51-3). The model M2 to which the store information SINF12 has been input outputs a score (step S51-4). In the example of FIG. 6, the model M2 to which the store information SINF12 has been input outputs a score "VL52" as shown in the score SC52. Note that the future potential score VL52 is a value (e.g., 0.6, 1.5, etc.) indicating the future potential of the sales of the store SP12. Note that, for the sake of simplicity, FIG. 6 shows a case in which the input information of the models M1 and M2 is the same, but the input information of the models M1 and M2 may be different.

[0127] Then, the information processing device 100 determines the upper limit of the purchase price of the future claims of store SP12 based on the store exit score VL51 and the future potential score VL52 of store SP12 (step S52). In Fig. 6, the information processing device 100 determines the number of months for which the future claims of store SP12 will be purchased based on the store exit score VL51 and the future potential score VL52 of store SP12. For example, the information processing device 100 determines the number of months for which the future claims of store SP12 will be purchased using a function (also called "months calculation function FC3") that uses the store exit score and the future potential score as variables (explanatory variables) and the number of months for which the claims are purchased as an output value (objective variable).

[0128] For example, the number of months calculation function FC3 is a function that calculates the number of months eligible for repurchase using a first value obtained by multiplying the inverse of the store closing score by a first coefficient (first weighting) and a second value obtained by multiplying the future potential score by a second coefficient (second weighting). For example, the number of months calculation function FC3 outputs the sum of the first value and the second value as the number of months eligible for repurchase.

[0129] 6, the information processing device 100 calculates a value VL53 indicating the number of months eligible for purchase of the store SP12 by using a first value obtained by multiplying the inverse of the store exit score VL51 of the store SP12 by a first weighting and a second value obtained by multiplying the future potential score VL52 of the store SP12 by a second weighting. The value VL53 is assumed to be a specific value (e.g., 1.5, 3, etc.) indicating the number of months eligible for purchase.

[0130] The first weighting value and the second weighting value may be set appropriately. For example, if the risk of a store closing is important, the first weighting value may be set to a large value. Also, for example, if the future potential of a store is important, the second weighting value may be set to a large value.

[0131] Then, the information processing device 100 determines the upper limit of repurchase price of future receivables of store SP12 based on the determined number of months for repurchase and information on sales of store SP12, but detailed description will be omitted since this is the same as the process described in Fig. 2. The information processing device 100 determines the upper limit of repurchase price of store SP12 to be "PL51", as shown in the upper limit of repurchase information PL2 in Fig. 6. For example, using the calculation function FC1 (see Fig. 2), when the sales of store SP12 are value SL12, the information processing device 100 determines the upper limit of repurchase price of store SP12 to be "PL51 (=SL12 x VL53)".

[0132] Then, the information processing device 100 provides information using the determined information (step S53). The information provision is similar to the process described in FIG. 2, so detailed description is omitted. For example, the information processing device 100 may provide information indicating the number of months for which the store SP12 is eligible for resale or the upper limit of the resale price to the operator of the store SP12. In this case, the information processing device 100 may transmit information indicating the number of months for which the store SP12 is eligible for resale or the upper limit of the resale price to the store device 20 used by the operator of the store SP12.

[0133] In this way, the information processing device 100 determines the conditions for purchasing the receivables of the target store based on multiple perspectives. As a result, the information processing device 100 can purchase the receivables of the target store by comprehensively considering multiple perspectives, and therefore can provide appropriate services for purchasing the receivables. For example, when factoring future receivables, future receivables are purchased, so if the store closes in the near future, it may be difficult to collect funds. Therefore, the information processing device 100 can reduce the possibility of difficulty in collecting funds by determining an index value such as the number of months to be purchased that comprehensively takes into account the risk of the target store closing and future prospects.

[0134] As described above, the information processing device 100 can improve the accuracy of processing while preventing the learning data from becoming huge by dividing the store closure model and the future potential model. The above-mentioned processing is merely an example, and the information processing device 100 may perform processing using various information. For example, the store closure model may be a model that is trained to input past store data and output whether or not the store has been closed within a predetermined period. In addition, the future potential model may be a model that predicts the number of visitors, the number of products, the number of evaluations of the store, and the like, not limited to whether sales will increase in the future. For example, the information processing device 100 may determine the factoring conditions of the store depending on whether or not the handling ratio of popular (buzzworthy) products is high.

[0135] [1-3-6. Determining the collection method] Next, an example of determining the mode of collection of money when factoring is performed will be described. For example, when factoring is performed on future receivables to a store, the information processing device 100 determines the mode of collection of accounts receivable corresponding to the future receivables. The information processing device 100 determines the lower limit of the collection rate based on the store's closure probability. For example, the information processing device 100 determines the lower limit of the monthly redemption rate according to the store's closure probability after a predetermined period of time. For example, the information processing device 100 predicts the store closure probability for each month, and determines the lower limit of the collection rate so that collection is completed by the month in which the store closure probability exceeds a predetermined threshold.

[0136] For example, the information processing device 100 calculates the store exit score for each period, determines the period in which the store exit score exceeds a threshold as the collection period, and determines the lower limit so that the full amount can be collected within the determined collection period. In this case, the information processing device 100 determines the collection period using multiple models each corresponding to a different period as shown in FIG. 3. This point will be described with reference to FIG. 3. In the following, the case where the store SP12 is the target store and the store SP12 performs factoring on future receivables will be described as an example. Also, the same points as those in the above-mentioned process will be omitted as appropriate.

[0137] For example, the information processing device 100 determines the collection mode of the accounts receivable corresponding to the future credit of the store SP12 based on the store closure score indicating the store closure probability of the store SP12 for each period. For example, the information processing device 100 determines the collection period of the accounts receivable corresponding to the future credit of the store SP12 using a threshold value related to the store closure timing estimation stored in the threshold value information storage unit 123 (see FIG. 11).

[0138] The information processing device 100 compares the store exit score output by each model with a threshold value TH11, and determines the collection period of the accounts receivable corresponding to the future credit of the target store based on the comparison result. For example, the information processing device 100 determines the period corresponding to the learning model with the shortest period among the learning models whose store exit scores are equal to or greater than the threshold value TH11 as the collection period of the accounts receivable corresponding to the future credit of the target store. The information processing device 100 determines the collection period of the accounts receivable corresponding to the future credit of the store SP12 by comparing the store exit scores output by the models M11, M12, M13, M14, etc. with the value of the threshold value TH11, "0.5". The information processing device 100 determines the collection period of the accounts receivable corresponding to the future credit of the store SP12 to be "three months" because the store exit score "0.52" output by the model M13 that predicts the probability (possibility) of store exit within three months is equal to or greater than the threshold value TH11.

[0139] The above-mentioned process is merely an example, and the information processing device 100 may determine the collection period of the accounts receivable corresponding to the future credit by appropriately using various information. For example, the information processing device 100 may determine the collection period of the accounts receivable corresponding to the future credit to be a period shorter than the period corresponding to the shortest learning model among the learning models whose store closure scores are equal to or greater than the threshold value TH11. In this case, the information processing device 100 may determine the collection period of the accounts receivable corresponding to the future credit of the store SP12 to be a period (e.g., two months) shorter than the period (three months) corresponding to the model M13 whose store closure score is equal to or greater than the threshold value TH11.

[0140] Then, the information processing device 100 determines the collection rate of the accounts receivable corresponding to the future receivable of store SP12 according to the determined collection period. For example, the information processing device 100 determines the collection rate so that the full amount can be collected within the determined collection period. For example, if the information processing device 100 determines the collection period of the accounts receivable corresponding to the future receivable of store SP12 to be three months, it determines the monthly payment rate (collection rate) of store SP12 to be "33.4%" so that the full amount can be collected within three months.

[0141] Then, the information processing device 100 notifies the target store of the determined information. For example, the information processing device 100 transmits information indicating that the collection period is "three months" and the monthly payment rate (collection rate) is "33.4%" to the store device 20 used by the operator of the store SP12.

[0142] In this way, the information processing device 100 predicts the store closure score for each period for the target store, and determines the collection mode of the accounts receivable corresponding to the future receivable of the target store according to the predicted period. This allows the information processing device 100 to determine the collection mode taking into account the risk of the target store closing, making it possible to provide appropriate services related to the purchase of receivables. For example, when factoring future receivables, future receivables are purchased, so if the store closes in the near future, it may be difficult to collect funds. Therefore, the information processing device 100 predicts a period in which the target store is likely to close, and determines the collection period and collection rate according to that period, thereby reducing the possibility that collection of funds will be difficult.

[0143] By the above-mentioned process, the information processing device 100 can determine the lower limit of the collection rate so that the repayment period is not extended, even if the collection rate can be set by the store side. As described above, the information processing device 100 determines the lower limit of the collection rate of the receivable. For example, if the probability of closing the store is at its highest after ten months, the information processing device 100 may determine the collection mode so that 10% of the factored amount is collected every month. For example, if the probability of closing the store is at its highest after nine months, the information processing device 100 may determine the collection rate so that the full amount can be collected in nine months.

[0144] In addition, the information processing device 100 may update the collection mode of the accounts receivable corresponding to the future receivable of the target store when the collection of the accounts receivable corresponding to the future receivable of the target store satisfies a predetermined condition. For example, when the collection of the accounts receivable corresponding to the future receivable of the target store is delayed, the information processing device 100 updates the store closure probability of the target store, and updates the collection mode of the accounts receivable corresponding to the future receivable of the target store based on the updated store closure probability of the target store. For example, when the period exceeding the threshold becomes four months from five months, the information processing device 100 may shorten the collection period by one month and determine the collection rate for that period.

[0145] In this way, when the store delays payment, the information processing device 100 may extend the collection period or recalculate the collection rate. Furthermore, when refactoring, the information processing device 100 may recalculate the collection rate.

[0146] [1-3-7. Provision of services to stores] Now, an example of service provision to a store will be described. The information processing device 100 provides a service to a store in step S5 shown in FIG. 2. The information processing device 100 determines a store to which factoring will be proposed (also referred to as a "proposed store"). For example, the information processing device 100 determines a proposed store from among a plurality of stores to which a proposal for purchasing receivables will be made based on store information relating to each of a plurality of stores that open on a commercial transaction site.

[0147] Then, the information processing device 100 provides information proposing the purchase of the receivables to the determined proposal destination store. For example, the information processing device 100 determines the number of months for which purchases are eligible and the upper limit of purchase amount for the determined proposal destination store by a determination process such as shown in Figs. 2 to 5, and provides information indicating the determined number of months for which purchases are eligible and the upper limit of purchase amount to the proposal destination store. For example, the information processing device 100 transmits information indicating the number of months for which purchases are eligible or the upper limit of purchase amount for the proposal destination store determined by the determination process such as shown in Figs. 2 to 5 to the store device 20 used by the operator of the proposal destination store.

[0148] Here, the information processing device 100 may determine the proposed store using various information. For example, the information processing device 100 may determine the proposed store using store information including information indicating whether the store advertises. For example, the information processing device 100 may determine the proposed store depending on whether the store advertises. For example, the information processing device 100 determines a store that does not advertise as the proposed store. This allows the information processing device 100 to propose factoring to a store that is not currently advertising and is expected to increase sales if it advertises.

[0149] Also, for example, the information processing device 100 may determine a proposed store using store information including information indicating products handled by the store. For example, the information processing device 100 may determine a proposed store according to the products handled by the store. For example, the information processing device 100 determines a store that handles products less than a predetermined threshold as a proposed store. This allows the information processing device 100 to propose factoring to a store that has a small number of product items and is expected to increase sales if the number of product items is increased.

[0150] Furthermore, the information processing device 100 may determine the proposed store using a learning model (also referred to as a "measure effect prediction model") that has learned the characteristics of the association between a store opening on a commercial transaction site and a change in sales when the store implements a measure to increase sales (also referred to as an "executed measure"). In this case, the information processing device 100 determines the proposed store as a store whose score output by the proposal determination model is equal to or greater than a predetermined threshold. In this case, the information processing device 100 proposes the executed measure to the proposed store together with the factoring conditions. Furthermore, the information processing device 100 may propose the factoring conditions to the proposed store on the condition that the executed measure is implemented.

[0151] For example, the policy effect prediction model is a model that receives store information of a store and policy information indicating the executed policy implemented by the store as input, and outputs a value indicating an increase or decrease in sales when the store implements the policy. For example, the information processing device 100 learns the policy effect prediction model using learning data in which model input information including store information of a store and policy information indicating the executed policy implemented by the store is associated with a value (correct answer information) indicating an increase or decrease in sales corresponding to the model input information. Note that the information processing device 100 may acquire the policy effect prediction model from a model providing server or the like that provides learning models.

[0152] For example, the information processing device 100 may determine a factoring proposal destination using a model (policy effect prediction model) that has learned changes (increases or decreases) in sales when a policy such as advertising is implemented. When the policy effect prediction model outputs a score indicating that sales will increase when a policy such as advertising is implemented for a certain store, the information processing device 100 may determine the store as a proposal destination store.

[0153] As described above, the information processing device 100 determines a store to which factoring is proposed. Note that the above-mentioned process is merely an example, and the information processing device 100 may perform the process using various information as appropriate. For example, when there is a store that would grow if the place where advertisements are placed is changed, the information processing device 100 may propose factoring to the store. Also, for example, when there is a store that handles products in a promising category and would grow if the place where advertisements are placed is changed, the information processing device 100 may propose factoring to the store. Also, the information processing device 100 may propose information indicating a user (target user) to whom advertisements are to be provided, and factoring conditions when advertising to the target user.

[0154] 2. Configuration of Information Processing Device Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 8, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing device 100 may have an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0155] (Communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information between the user terminal 10, the store device 20, and the web server 30.

[0156] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in Fig. 8, the storage unit 120 according to the embodiment has a shop owner information storage unit 121, a model information storage unit 122, a threshold information storage unit 123, a group information storage unit 124, a social situation information storage unit 125, a commercial transaction site information storage unit 126, and a factoring information storage unit 127. The storage unit 120 may store various information, not limited to the above.

[0157] (Shop owner information storage unit 121) The store owner information storage unit 121 according to the embodiment stores information about a business operator who opens a store on the commerce site. For example, the store owner information storage unit 121 stores various information about a store (shop) opened by a business operator (store owner) on the commerce site. For example, the information stored in the store owner information storage unit 121 is acquired from the web server 30 via a communication network. FIG. 9 is a diagram showing an example of the store owner information storage unit according to the embodiment. The store owner information storage unit 121 shown in FIG. 9 has items such as "store owner", "store", "store opening date", "store closing date", "store closing reason", "store information", and "score information". In addition, the "store information" includes items such as "business information", "product information", "category information", "sales information", and "evaluation information". In addition, the "score information" includes items such as "store closing" and "future potential".

[0158] "Shop owner" refers to information (such as a business owner ID or name) that identifies a business that has a shop on a commerce site. For example, "shop owner" refers to information that identifies a business that has had a shop on a commerce site in the past or that currently has a shop on the commerce site. "Store" refers to a store that a business has opened on a commerce site.

[0159] In addition, in the store owner information storage unit 121 shown in FIG. 9, an example is shown in which each business opens one store on the commercial transaction site, but each business may open multiple stores on the commercial transaction site. In this case, the business can use different stores depending on the category of products handled and the business form. For example, a process may be performed in which the other stores of a business that has a store that has been closed due to forced closure or the like are also closed (lost the right to open a store).

[0160] "Opening date" indicates the date a store opened on the trading site. "Closing date" indicates the date a store closed on the trading site. For businesses (or stores) that have not yet closed their stores, the closing date field will be left blank ("-" (hyphen)).

[0161] "Store information" includes various information related to the store. "Store information" includes information registered by the store operator (registered data) and history (performance data) accumulated by the operation of the store. For example, "store information" includes information used by the information processing device 100 to learn a model.

[0162] "Business information" refers to information related to a business. "Business information" includes various information related to a business, such as information indicating the business form (corporation or sole proprietorship), information on business funds such as capital, information indicating the store's industry, and the number of years the store has been in operation. "Business information" may also include information related to a business operator. For example, "business information" may include attribute information of a business operator. "Business information" may also include financial information indicating the financial status of a business operator. Note that the above is merely an example, and "business information" may include various information related to a business. In the example of FIG. 9, business information corresponding to a store is stored, as indicated by an abstract code such as "business information #1."

[0163] "Product information" refers to information about products traded in a store. "Product information" includes various information about a product, such as information to identify the product (JAN code or product ID, etc.), product name, product image, product description, product price, product stock quantity, product category, etc. Note that the above is merely an example, and "product information" may include various information about a product. In the example of FIG. 9, product information corresponding to a store is stored, which is indicated by an abstract code such as "product information #1."

[0164] "Category information" refers to information about the category of merchandise traded at a store. "Category information" includes information indicating the category of merchandise traded at a store. "Category information" includes information indicating the main category, which is the category of merchandise that the store primarily trades, and the subcategory, which is the category of merchandise that the store trades other than the main category.

[0165] For example, the main category and subcategory may be specified by the store operator, or may be determined based on the store's sales, etc. Also, there may be multiple main categories, and there may be no subcategories. Note that the above is merely an example, and "category information" may include various information related to the category. In the example of FIG. 9, category information corresponding to a store is stored, as indicated by an abstract code such as "category information #1."

[0166] "Sales information" refers to information relating to sales at a store. "Sales information" includes information indicating sales at a store. "Sales information" includes information indicating the number of sales of products at a store and information indicating the sales amount of products at a store. For example, "sales information" includes information indicating sales for each period, such as one day, one week, or one month. "Sales information" may include various information relating to sales, such as information indicating sales for each product traded at a store and information indicating sales for each category.

[0167] The "sales information" may include information such as the number of sales and sales amount for each product. The "sales information" may include various information related to the number of sales and sales amount, such as the number of sales and sales amount of a product, the ratio of the number of sales to the number of products handled, and the collection period for the number of sales and amount. The above is merely an example, and the "sales information" may include various information related to sales. In the example of FIG. 9, sales information corresponding to a store is stored, as indicated by an abstract code such as "sales information #1."

[0168] "Evaluation information" refers to information regarding evaluations of businesses, stores opened by businesses, and products traded at stores. "Evaluation information" includes information indicating evaluations from users. For example, "evaluation information" includes information such as the number of accesses (page views) per day to a page corresponding to a store on a trading site, the number of store reviews indicating the number of reviews posted by users for the store, and store ratings given to stores in reviews posted by users. The number of page views is not limited to one day and may include the number of page views over a specified period (such as one week). For example, the number of store reviews may be the average number of store reviews per day for a store.

[0169] For example, the store rating may be on a 5-point scale, with a minimum of "1" and a maximum of "5." The store rating may be the average rating of reviews submitted by users up until the store is closed. The number of store reviews and the store rating may be stored as the number or average rating tallied over a predetermined period (e.g., one week), or the cumulative number up to the present time may be stored, or information tallied in various ways, such as the cumulative number up to the present time divided by the number of years the store has been in operation, may be stored. For example, the "rating information" may include information indicating the ratio of the number of reviews submitted to the page views.

[0170] For example, the "rating information" includes information such as the number of product reviews indicating the number of reviews posted for the product, and the product rating indicating the rating in the reviews posted by users for the product. For example, the product rating may be on a five-point scale ranging from a minimum of "1" to a maximum of "5". Note that, for example, the product rating may be the average rating in the reviews posted by users until the store stops handling the product. Note that the above is merely an example, and the "rating information" may include various information related to the rating. In the example of FIG. 9, the rating information corresponding to the store is stored, which is indicated by an abstract code such as "rating information #1".

[0171] "Score information" indicates score information for a store. "Score information" includes various information estimated by the information processing device 100. For example, "score information" stores the score output by the model. As shown in FIG. 9, for stores that are not subject to score calculation, such as stores that have already been closed, the score information item is left blank ("-" (hyphen)).

[0172] "Store closure" indicates the probability (likelihood) that a store will close from a trading site. In "Store closure", a store closure score indicating the probability (likelihood) that a store will close is stored. For example, in "Store closure", a score (store closure score) output by a store closure model (e.g., model M1) is stored. In the example of FIG. 9, this is shown as an abstract code such as "Store closure score #1", but a concrete value (numerical value) such as "0.7" is stored.

[0173] "Future potential" indicates the future potential of the store. In "Future potential", a future potential score indicating the future potential of the store is stored. For example, in "Future potential", a score (future potential score) output by a future potential model (e.g. model M2) is stored. In the example of FIG. 9, it is shown as an abstract code such as "future potential score #1", but a concrete value (numerical value) such as "0.5" or "10" is stored.

[0174] The store owner information storage unit 121 may store various information according to the purpose, without being limited to the above. For example, the store owner information storage unit 121 may store information indicating the reason for the store closure of a store that has closed. For example, the reason for the store closure is used to distinguish correct answer information in the model generation process described later. For example, the store owner information storage unit 121 may store information indicating the reason for the store closure, such as "forced closure," which indicates that the store was forced to close by the commercial transaction site, or "closed," which indicates that the store was voluntarily closed by the business operator.

[0175] (Model information storage unit 122) The model information storage unit 122 according to the embodiment stores information about the model. For example, the model information storage unit 122 stores information (model data) of a trained model (model) trained (generated) by a learning process. The model information storage unit 122 stores data used in learning (trained data) in association with the trained model (model). FIG. 10 is a diagram illustrating an example of a model information storage unit according to the embodiment. In the example illustrated in FIG. 10, the model information storage unit 122 includes items such as "model ID", "purpose", "model data", and "trained data". In the example of FIG. 10, the model information storage unit 122 stores data used in learning (trained data) in association with the trained model (model).

[0176] "Model ID" indicates identification information for identifying a model. "Use" indicates the use of the corresponding model. "Model data" indicates the data of the model. FIG. 10 etc. shows an example in which conceptual information such as "MDT1" is stored in "model data", but in reality, various information constituting the model is included, such as information on the model configuration (network configuration) and information on parameters. For example, "model data" includes information including the nodes in each layer of the network, the functions employed by each node, the connection relationships of the nodes, and the connection coefficients set for the connections between the nodes.

[0177] "Learning data" refers to data used to train a trained model (model). In the "learning data", information indicating a data set used to train the corresponding model is stored. For example, the "learning data" stores data (input information) and answer information (output information) corresponding to the data as learning data (also called "data for learning"). FIG. 10 shows an example in which conceptual information such as "LDT1" is stored in the "learning data", but in reality, various information related to the data used to train the corresponding model, such as data (input information) and answer information (output information) corresponding to the data, is included.

[0178] In FIG. 10, the model (model M1) identified by the model ID "M1" indicates that the application is "store withdrawal." In other words, model M1 indicates that it is a model that outputs information (score) indicating the probability (likelihood) that a store corresponding to input data will withdraw from a trading site. Also, it indicates that the model data of model M1 is model data MDT1. Also, it indicates that the learning data used to train model M1 is learning data LDT1.

[0179] Also, the model (model M2) identified by the model ID "M2" indicates that its use is "future potential." In other words, model M2 indicates that it is a model that outputs information (score) indicating the future potential of a store corresponding to input data. For example, model M2 outputs information (score) for estimating changes in sales of a store corresponding to input data. It indicates that the model data of model M2 is model data MDT2. It also indicates that the learning data used to learn model M2 is learning data LDT2.

[0180] The model (model M11) identified by the model ID "M11" indicates that the application is "closing in one month." In other words, model M11 indicates that it is a model that outputs information (score) indicating the probability (likelihood) that a store corresponding to input data will close from a trading site within one month. Also, it indicates that the model data of model M11 is model data MDT11. Also, it indicates that the learning data used to train model M11 is learning data LDT11.

[0181] The model (model M12) identified by the model ID "M12" indicates that the application is "closing in February." In other words, model M12 indicates that it is a model that outputs information (score) indicating the probability (likelihood) that a store corresponding to input data will close within two months from a trading site. Also, it indicates that the model data of model M12 is model data MDT12. Also, it indicates that the learning data used to train model M12 is learning data LDT12.

[0182] The model (model M13) identified by the model ID "M13" indicates that the application is "closing in March." In other words, model M13 indicates that it is a model that outputs information (score) indicating the probability (likelihood) that a store corresponding to input data will close from a trading site within three months. Also, it indicates that the model data of model M13 is model data MDT13. Also, it indicates that the learning data used to train model M13 is learning data LDT13.

[0183] Although FIG. 10 illustrates models up to M13, the model information storage unit 122 may store models that estimate (predict) the probability of store closures corresponding to various time periods, such as model M14 that predicts store closures in April.

[0184] The model (model M31) identified by the model ID "M31" indicates that its application is "number of store closures." In other words, the model M31 indicates that it is a model that outputs information (score) indicating the number of stores that will close from a trading site (number of store closures). The model data of the model M31 is also indicated to be model data MDT31. The learning data used to train the model M31 is also indicated to be learning data LDT31.

[0185] Note that model M31 is merely an example, and the model information storage unit 122 may store therein models that estimate (predict) the number of occurrences of various negative behaviors, not limited to model M31 used to estimate the number of store closures.

[0186] The model (model M41) identified by the model ID "M41" indicates that its use is "category sales." In other words, the model M41 indicates that it is a model that outputs information (score) indicating sales at a trading site for products in a category corresponding to input data. Also, it indicates that the model data of the model M41 is model data MDT41. Also, it indicates that the learning data used to train the model M41 is learning data LDT41. When a model is trained for each category, the model information storage unit 122 may store a model for each category in association with the category.

[0187] The model information storage unit 122 is not limited to the above, and may store various types of information depending on the purpose.

[0188] (Threshold information storage unit 123) The threshold information storage unit 123 according to the embodiment stores various information related to thresholds. Fig. 11 is a diagram illustrating an example of the threshold information storage unit according to the embodiment. The threshold information storage unit 123 illustrated in Fig. 11 includes items such as "threshold", "value", and "use".

[0189] "Threshold" indicates information for identifying a threshold. "Value" indicates a specific numerical value (value) of the corresponding threshold. "Use" indicates the use for which the corresponding threshold is used.

[0190] In the example of FIG. 11, the value of the threshold (threshold TH1) identified by threshold "TH1" is "0.9". The purpose of threshold TH1 is grouping (classification). In other words, threshold TH1 is the first threshold used for grouping (classification) of stores. For example, threshold TH1 is the first threshold used to classify a first group of stores.

[0191] The threshold value (threshold value TH2) identified by threshold value "TH2" indicates that the value is "0.8". The purpose of threshold value TH2 is grouping (classification). In other words, threshold value TH2 indicates that it is a second threshold value used for grouping (classification) of stores. For example, threshold value TH2 is a second threshold value used to classify stores into a second group.

[0192] The value of the threshold (threshold TH11) identified by threshold "TH11" is "VL11." The purpose of threshold TH11 is to estimate the time of store closure. In other words, threshold TH11 is a threshold used to estimate when a store will close from a trading site. Note that while the example in FIG. 11 is shown with an abstract symbol such as "VL11," the value of each threshold is a specific numerical value according to the purpose.

[0193] The value of the threshold (threshold TH21) identified by the threshold "TH21" is "VL21". The purpose of the threshold TH21 is to determine the proposal destination. In other words, the threshold TH21 is a threshold used to determine the store to which the proposal will be made.

[0194] The threshold information storage unit 123 is not limited to the above, and may store various types of information depending on the purpose.

[0195] (Group information storage unit 124) The group information storage unit 124 according to the embodiment stores various information related to groups. The group information storage unit 124 stores various information related to a plurality of groups corresponding to each of the plurality of groups. FIG. 12 is a diagram illustrating an example of the group information storage unit according to the embodiment. The group information storage unit 124 illustrated in FIG. 12 includes items such as "group ID," "group information," and "members."

[0196] "Group ID" indicates identification information for identifying a group. "Group information" indicates group information for the corresponding group. For example, "group information" indicates group information including information such as the index value (number of months) set for the group. FIG. 12 shows an example in which conceptual information such as "SM1" is stored in "group information," but in reality, specific information such as the index value (number of months) set for the group is stored.

[0197] "Member" refers to a member of a group. For example, information (such as a store ID) that identifies a member (store) belonging to a group is stored in "member."

[0198] In FIG. 12, the group information of the group (first group) identified by the group ID "GP1" is group information SM1. In FIG. 12, it is shown that "3" is set as the index value for group GP1, which is the first group. For example, the number of months "3" is set as the index value for group GP1, which is the first group. It is shown that stores SP2, SP12, etc. belong to group GP1 as members.

[0199] The group information storage unit 124 is not limited to the above, and may store various kinds of information according to the purpose.

[0200] (Social situation information storage unit 125) The social situation information storage unit 125 according to the embodiment stores various information related to social situations. In the example of Fig. 13, social situation information related to the economy is stored. Fig. 13 is a diagram showing an example of the social situation information storage unit according to the embodiment. The social situation information storage unit 125 shown in Fig. 13 includes items such as "social situation ID", "time point", and "social situation information".

[0201] "Social situation ID" indicates identification information for identifying a social situation (object). Character information or the like for identifying the social situation corresponding to each social situation ID may be stored in association with the social situation ID. "Time" indicates the time (time point) when the corresponding social situation occurred. For example, "time" indicates the time (time point) when the corresponding social situation information was acquired. In the example of FIG. 8, the time point is indicated by an abstract code such as "Time #1", but information indicating the corresponding period may also be included, such as "19XY year Z month..." in parentheses.

[0202] "Social situation information" indicates information related to a social situation identified by a social situation ID. In the example of Fig. 13, the social situation information is indicated by an abstract code such as "SDT1", but each piece of social situation information includes information indicating various social situations, such as information related to the economy (economic situation) at the time corresponding to the social situation identified by the social situation ID. For example, the social situation information includes various information indicating the economic situation, such as stock prices, unemployment rates, and interest rates.

[0203] 13, the social situation identified by the social situation ID "SC1" is a social situation corresponding to time point #1. The social situation information of the social situation identified by the social situation ID "SC1" is social situation information SDT1.

[0204] The social situation information storage unit 125 is not limited to the above, and may store various kinds of information according to the purpose.

[0205] (Commerce site information storage unit 126) The commercial transaction site information storage unit 126 according to the embodiment stores various information related to the commercial transaction site. For example, the commercial transaction site information storage unit 126 stores statistical information related to the commercial transaction site, such as overall sales at the commercial transaction site. FIG. 14 is a diagram showing an example of the commercial transaction site information storage unit according to the embodiment. The commercial transaction site information storage unit 126 shown in FIG. 14 includes items such as "category" and "sales information by category." Note that the example of FIG. 14 shows a case where sales information for each category is stored as an example, but the commercial transaction site information storage unit 126 may store various information, not limited to sales information for each category.

[0206] "Category" indicates identification information for identifying a category. In Fig. 14, an example is shown in which conceptual information such as "Category #1" is stored in "Category", but in reality, information for identifying a category, such as the name of the category or an identifier (category ID) of the category, is stored.

[0207] "Sales information by category" indicates sales at the trading site of products belonging to the corresponding category. Although FIG. 14 shows an example in which conceptual information such as "Category sales #1" is stored in "Sales information by category", in reality, information indicating sales of the corresponding category is stored. Note that sales information by category is not limited to sales of the category, and may include various information related to sales in the category, such as the number of sales in the category.

[0208] In Fig. 14, sales in category #1 are shown as category sales #1. For example, sales at a trading site for products belonging to category #1 are the value shown as category sales #1. Sales in category #2 are shown as category sales #2, and sales in category #3 are shown as category sales #3.

[0209] The commercial transaction site information storage unit 126 is not limited to the above, and may store various types of information according to the purpose.

[0210] (Factoring information storage unit 127) The factoring information storage unit 127 according to the embodiment stores various information related to factoring. Fig. 15 is a diagram showing an example of the factoring information storage unit according to the embodiment. The factoring information storage unit 127 shown in Fig. 15 includes items such as "store" and "factoring information."

[0211] "Store" indicates identification information for identifying a store. "Factoring information" indicates information regarding factoring of the corresponding store (factoring information). For example, "Factoring information" indicates whether or not factoring of the corresponding store is being used. For example, a store whose "Factoring information" is "-" (hyphen) indicates that the store does not use factoring.

[0212] A store whose "Factoring Information" is Factoring Information #* (* is an arbitrary number) indicates that the store is using factoring. Figure 15 shows an example in which conceptual information such as "Factoring Information #12" is stored in "Factoring Information", but in reality, specific information regarding factoring, such as the amount of factoring and its collection mode (collection period, collection interval, etc.), is stored.

[0213] 15, it is shown that store SP1 is not using factoring, and store SP12 is using factoring, and its factoring information is factoring information #12.

[0214] The factoring information storage unit 127 is not limited to the above, and may store various types of information depending on the purpose.

[0215] (Control unit 130) Returning to the explanation of Fig. 8, the control unit 130 is a controller, and is realized, for example, by a CPU (Central Processing Unit), MPU (Micro Processing Unit), or the like, executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 100 using a RAM as a working area. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0216] 8, the control unit 130 has an acquisition unit 131, a learning unit 132, an estimation unit 133, a classification unit 134, a determination unit 135, a decision unit 136, and a provision unit 137, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 8, and may be other configurations as long as they perform the information processing described below.

[0217] (Acquisition part 131) The acquisition unit 131 acquires various information. The acquisition unit 131 acquires various information from an external device such as the user terminal 10. The acquisition unit 131 also acquires various information from the storage unit 120. The acquisition unit 131 also acquires various information from the shop owner information storage unit 121, the model information storage unit 122, the threshold information storage unit 123, the group information storage unit 124, the social situation information storage unit 125, the commercial transaction site information storage unit 126, the factoring information storage unit 127, etc.

[0218] The acquisition unit 131 receives various information from an external information processing device via the communication unit 110. The acquisition unit 131 stores the received information in the storage unit 120. The acquisition unit 131 receives various information from the user terminal 10, the store device 20, or the web server 30. The acquisition unit 131 acquires information from the user terminal 10 used by the user. The acquisition unit 131 acquires various information from the store device 20. For example, the acquisition unit 131 acquires information about a store that a shopkeeper has opened on a commercial transaction site from the store device 20 used by the shopkeeper. For example, the acquisition unit 131 acquires various information from the web server 30. For example, the acquisition unit 131 acquires information about the commercial transaction site from the web server 30. For example, the acquisition unit 131 acquires information about the store on the commercial transaction site from the web server 30.

[0219] The acquisition unit 131 acquires store information regarding each of a plurality of stores that open on a commercial transaction site on the network. The acquisition unit 131 acquires a learning model (model). The acquisition unit 131 acquires store sales information indicating past sales of a target store that is a store that opens on a commercial transaction site on the network. The acquisition unit 131 acquires category sales information indicating past sales for each category of products handled on the commercial transaction site. The acquisition unit 131 acquires store sales information indicating changes in past sales of a target store that is a store that opens on a commercial transaction site on the network. The acquisition unit 131 acquires category sales information indicating changes in past sales for each category of products handled on the commercial transaction site.

[0220] The acquisition unit 131 acquires a first learning model that predicts the occurrence probability of a negative event, which is an event caused by a store opening at a commercial transaction site on a network and is a negative event for the commercial transaction site. The acquisition unit 131 acquires a second learning model that predicts future possibilities regarding sales of a store opening at the commercial transaction site. The acquisition unit 131 acquires the first learning model that receives store information of a store as an input and outputs a score indicating the occurrence probability of a negative event caused by the store.

[0221] The acquisition unit 131 acquires a second learning model that receives store information of a store and outputs a score indicating future sales potential of the store. The acquisition unit 131 acquires a first learning model that predicts the occurrence probability of a store's receivable becoming uncollectible. The acquisition unit 131 acquires a first learning model that predicts the occurrence probability of a store withdrawing from a trading site.

[0222] The acquisition unit 131 acquires store information on each of a plurality of stores that are located on a commerce site on a network. The acquisition unit 131 acquires store information including information indicating whether each of the plurality of stores is advertising. The acquisition unit 131 acquires store information including information indicating products that are handled by each of the plurality of stores.

[0223] (Learning Section 132) The learning unit 132 executes a learning process to learn a learning model (model). For example, the learning unit 132 executes the learning process based on various information acquired by the acquisition unit 131. The learning unit 132 executes the learning process based on information from an external information processing device and information stored in the storage unit 120. The learning unit 132 executes the learning process based on information stored in the model information storage unit 122. The learning unit 132 stores the model generated by learning in the model information storage unit 122.

[0224] The learning unit 132 learns a learning model that predicts the occurrence probability of a negative event, which is an event that occurs within a predetermined period of time by a store that opens a shop on a commercial transaction site on the network and is an event that is negative for the commercial transaction site. The learning unit 132 learns a learning model that receives store information of a store as an input and outputs a score indicating the occurrence probability of a negative event occurring by the store.

[0225] The learning unit 132 learns a learning model that predicts the occurrence probability of a store's receivable becoming uncollectible. The learning unit 132 learns a learning model that predicts the occurrence probability of a store withdrawing from a commercial transaction site.

[0226] The learning unit 132 learns a plurality of learning models, each of which corresponds to a different time period and each of which predicts the occurrence probability of a negative event caused by a store within a corresponding time period. The learning unit 132 learns a plurality of learning models, each of which outputs a score indicating the occurrence probability of a negative event caused by a store within a corresponding time period.

[0227] The learning unit 132 performs a learning process. The learning unit 132 performs various learning. The learning unit 132 learns various pieces of information based on the information acquired by the acquisition unit 131. The learning unit 132 learns (generates) a model. The learning unit 132 learns various pieces of information such as a model. The learning unit 132 generates a model by learning. The learning unit 132 learns the model using various machine learning techniques. For example, the learning unit 132 learns parameters of the model (network). The learning unit 132 learns the model using various machine learning techniques.

[0228] The learning unit 132 generates various learning models such as models M1, M2, M11, M12, M13, M21, M22, M31, and M41. The learning unit 132 learns network parameters. For example, the learning unit 132 learns network parameters of various learning models such as models M1, M2, M11, M12, M13, M21, M22, M31, and M41. The learning unit 132 performs a learning process using the learning data stored in the model information storage unit 122, thereby generating various learning models such as models M1, M2, M11, M12, M13, M21, M22, M31, and M41. For example, the learning unit 132 generates a model used for voice recognition. The learning unit 132 generates various learning models such as models M1, M2, M11, M12, M13, M21, M22, M31, M41, etc., by learning network parameters of various learning models such as models M1, M2, M11, M12, M13, M21, M22, M31, M41, etc.

[0229] The learning unit 132 performs a learning process based on the learning data (teacher data) stored in the model information storage unit 122. The learning unit 132 performs a learning process using the learning data stored in the model information storage unit 122, thereby generating various learning models such as models M1, M2, M11, M12, M13, M21, M22, M31, and M41.

[0230] For example, the learning unit 132 generates a model used to estimate the probability (likelihood) of a store closing. For example, when store information of a store is input, the learning unit 132 generates a model that outputs a score indicating the probability (likelihood) that a store corresponding to the store information will close from a trading site. The learning unit 132 generates the model M1 by learning parameters of the network of the model M1.

[0231] The learning method by the learning unit 132 is not particularly limited, but for example, learning data in which data (input information) and its correct answer information (output information) are linked may be prepared, and the learning data may be input to a computation model based on a multi-layer neural network for learning. In addition, a method based on a DNN (Deep Neural Network), such as a CNN (Convolutional Neural Network) or a 3D-CNN, may be used. When targeting time-series data such as voice, the learning unit 132 may use a method based on a recurrent neural network (RNN) or LSTM (Long Short-Term Memory units), which is an extension of an RNN.

[0232] (Estimation part 133) The estimation unit 133 executes an estimation process to estimate various pieces of information. The estimation unit 133 stores the information estimated by the estimation process in the storage unit 120. For example, the estimation unit 133 executes the estimation process based on various pieces of information acquired by the acquisition unit 131. The estimation unit 133 executes the estimation process based on various pieces of information stored in the storage unit 120. The estimation unit 133 executes the estimation process based on various pieces of information received from an external information processing device.

[0233] The estimation unit 133 executes the estimation process using the model learned by the learning unit 132. For example, the estimation unit 133 executes the estimation process based on information classified by the classification unit 134. For example, the estimation unit 133 executes the estimation process based on information determined by the determination unit 135. For example, the estimation unit 133 executes the estimation process based on information determined by the determination unit 136.

[0234] The estimation unit 133 estimates the number of occurrences of negative events, which are events caused by stores opening on a commercial transaction site on a network and are negative events for the commercial transaction site, using social situation information indicating the economic situation of society. The estimation unit 133 estimates the number of uncollectible receivables of a store as the occurrence number. The estimation unit 133 estimates the number of stores that will close from the commercial transaction site as the occurrence number. The estimation unit 133 estimates the number of stores that will close from the commercial transaction site using a learning model that has learned the characteristics of the association between the economic situation of society and the number of stores that will close from the commercial transaction site.

[0235] The estimation unit 133 estimates a store exit probability, which is the probability that a target store, which is a store opening on a commercial transaction site on a network, will exit the commercial transaction site after a predetermined period of time. The estimation unit 133 estimates the store exit probability of the target store using a learning model that has learned characteristics of the association between stores opening on a commercial transaction site and stores exiting the commercial transaction site.

[0236] The estimation unit 133 estimates the store closure probability of the target store using a plurality of learning models, each of which corresponds to a different time period and each of which estimates the probability of the store closing within the corresponding time period. The estimation unit 133 estimates the store closure probability of the target store using a plurality of learning models, each of which outputs a score indicating the probability of the store closing within the corresponding time period. The estimation unit 133 updates the store closure probability of the target store when the collection of accounts receivable corresponding to the future receivable of the target store satisfies a condition regarding delay.

[0237] (Classification section 134) The classification unit 134 executes a classification process to classify various pieces of information. The classification unit 134 stores the information classified by the classification process in the storage unit 120. For example, the classification unit 134 executes the classification process based on various pieces of information acquired by the acquisition unit 131. The classification unit 134 executes the classification process based on various pieces of information stored in the storage unit 120. The classification unit 134 executes the classification process based on various pieces of information received from an external information processing device.

[0238] The classification unit 134 performs the classification process using the model learned by the learning unit 132. For example, the classification unit 134 performs the classification process based on information determined by the determination unit 136. For example, the classification unit 134 performs the classification process based on information determined by the determination unit 135. For example, the classification unit 134 performs the classification process based on information estimated by the estimation unit 133.

[0239] The classification unit 134 classifies the multiple stores into multiple groups based on store information on each of the multiple stores that open on a commercial transaction site on the network. The classification unit 134 classifies the multiple stores into multiple groups according to the risk of non-collection of receivables of each of the multiple stores based on the store information. The classification unit 134 classifies the multiple stores into multiple groups according to the possibility of the store closing from the commercial transaction site.

[0240] The classification unit 134 classifies the multiple stores into multiple groups using a learning model that has learned characteristics of the association between stores opening on a commercial transaction site and stores closing on the commercial transaction site. The classification unit 134 classifies the multiple stores into multiple groups based on store information including information on products sold by each of the multiple stores. The classification unit 134 classifies the multiple stores into multiple groups based on store information including sales information of each of the multiple stores. The classification unit 134 classifies the multiple stores opening on the commercial transaction site into multiple groups using a threshold based on the number of occurrences estimated by the estimation unit 133.

[0241] (Judgment unit 135) The determination unit 135 executes a determination process for determining various pieces of information. For example, the determination unit 135 executes the determination process based on various pieces of information acquired by the acquisition unit 131. For example, the determination unit 135 executes the determination process based on information stored in the storage unit 120.

[0242] The determination unit 135 executes the determination process using the model learned by the learning unit 132. For example, the determination unit 135 executes the determination process based on information estimated by the estimation unit 133. For example, the determination unit 135 executes the determination process based on information classified by the classification unit 134. For example, the determination unit 135 executes the determination process based on information determined by the determination unit 136.

[0243] The determination unit 135 determines the sales trend for each category based on the past sales for each category. The determination unit 135 determines the sales trend for each category based on the transition of the past sales for each category. For example, the determination unit 135 determines the sales trend for each category using the score output by the model M41. For example, when the score output by the model M41 is equal to or greater than a predetermined threshold (e.g., 1.2), the determination unit 135 determines that the sales trend for the category corresponding to the model input information input to the model M41 is an upward trend. For example, when the score output by the model M41 is less than a predetermined threshold (e.g., 0.8), the determination unit 135 determines that the sales trend for the category corresponding to the model input information input to the model M41 is a downward trend.

[0244] The determination unit 135 may execute a generation process to generate various information. The determination unit 135 stores the generated information in the storage unit 120. For example, the determination unit 135 executes the generation process based on various information acquired by the acquisition unit 131. The determination unit 135 executes the generation process based on various information stored in the storage unit 120. The determination unit 135 executes the generation process based on various information received from an external information processing device.

[0245] For example, the determination unit 135 executes the generation process based on information determined by the determination unit 136. For example, the determination unit 135 executes the generation process based on information determined by the determination unit 135. For example, the determination unit 135 executes the generation process based on information classified by the classification unit 134. For example, the determination unit 135 executes the generation process based on information estimated by the estimation unit 133.

[0246] The determination unit 135 generates content. For example, the determination unit 135 generates a screen (content) to be provided to the user terminal 10 by appropriately using various technologies such as Java (registered trademark). Note that the determination unit 135 may generate the screen (content) to be provided to the user terminal 10 based on the format of CSS, JavaScript (registered trademark), or HTML. Also, for example, the determination unit 135 may generate the screen (content) in various formats such as JPEG (Joint Photographic Experts Group), GIF (Graphics Interchange Format), and PNG (Portable Network Graphics).

[0247] (Decision unit 136) The determination unit 136 executes a determination process for determining various pieces of information. The determination unit 136 stores the determined information in the storage unit 120. For example, the determination unit 136 executes the determination process based on various pieces of information acquired by the acquisition unit 131. The determination unit 136 executes the determination process based on various pieces of information stored in the storage unit 120. For example, the determination unit 136 executes the determination process based on various pieces of information received from an external information processing device.

[0248] The determination unit 136 executes the determination process using the model learned by the learning unit 132. For example, the determination unit 136 executes the determination process based on information estimated by the estimation unit 133. For example, the determination unit 136 executes the determination process based on information classified by the classification unit 134. For example, the determination unit 136 executes the determination process based on information determined by the determination unit 135.

[0249] For example, the determination unit 136 calculates various information based on the information estimated by the estimation unit 133. For example, the determination unit 136 calculates various information based on the information determined by the determination unit 135. For example, the determination unit 136 calculates various information based on the information generated by the determination unit 135. For example, the determination unit 136 calculates various information based on the information classified by the classification unit 134. The determination unit 136 calculates various scores using a model. For example, the determination unit 136 calculates various scores.

[0250] The determination unit 136 determines conditions for buying bonds for each group classified by the classification unit 134. The determination unit 136 determines conditions that are more advantageous to stores belonging to a group that has a lower risk. The determination unit 136 determines conditions that are more advantageous to stores belonging to a group that has a lower probability of closing.

[0251] The determination unit 136 determines conditions for the purchase of future receivables for each group. The determination unit 136 determines an index value for the purchase of future receivables for each group. The determination unit 136 determines an upper limit for the purchase price of future receivables for one store based on the index value of the group to which the one store belongs and the sales of the one store. The determination unit 136 determines an upper limit for the purchase price of one store based on the value obtained by multiplying the index value of the group to which the one store belongs and the sales of the one store. The determination unit 136 determines the number of months for which future receivables will be purchased for each group as an index value.

[0252] The determination unit 136 determines conditions for purchasing the receivables of the target store based on the probability of occurrence of a negative event by the target store predicted using the learning model learned by the learning unit 132. The determination unit 136 determines conditions that are more advantageous to the target store as the probability of occurrence of the receivables of the target store becoming uncollectible is lower. The determination unit 136 determines conditions that are more advantageous to the target store as the probability of occurrence of the target store closing is lower.

[0253] The determination unit 136 determines conditions for purchasing future receivables of the target store based on the probability of occurrence of a negative event by the target store. The determination unit 136 determines an index value for purchasing future receivables of the target store. The determination unit 136 determines an upper limit for purchasing future receivables of the target store based on the index value of the target store and the sales of the target store. The determination unit 136 determines an upper limit for purchasing future receivables of the target store based on the multiplication of the index value of the target store and the sales of the target store. The determination unit 136 determines the number of months for which future receivables of the target store are to be purchased as the index value.

[0254] The determination unit 136 uses a plurality of learning models to determine the number of months for which the future receivables of the target store are to be purchased as an index value. The determination unit 136 determines the number of months for which the future receivables of the target store are to be purchased based on the period corresponding to the learning model with the shortest period among the learning models whose scores are equal to or greater than the threshold.

[0255] The determination unit 136 determines the conditions for purchasing the claims based on the number of occurrences estimated by the estimation unit 133.

[0256] The determination unit 136 determines the upper limit of receivables for the target store based on the sales trend of the target store indicated by the store sales information and the sales trend of the category corresponding to the handled products that are products handled by the target store indicated by the category sales information. The determination unit 136 determines the upper limit of receivables for the target store based on the sales trend of the target store indicated by the store sales information and the sales trend of the category corresponding to the handled products that are products handled by the target store indicated by the category sales information. The determination unit 136 determines a target category corresponding to the target store based on the handled products of the target store, and determines the upper limit of receivables for the target store based on the sales trend of the determined target category.

[0257] The determination unit 136 determines a plurality of target categories corresponding to the target store based on the products handled by the target store, and determines the upper limit of the receivable amount of the target store based on the sales trend of each of the determined plurality of target categories. The determination unit 136 determines the upper limit of the receivable amount of the target store based on weighting according to the number of products in the plurality of target categories on the commercial transaction site. The determination unit 136 determines the upper limit of the receivable amount of the target store by increasing the weighting for a category with a larger number of products handled on the commercial transaction site.

[0258] The determination unit 136 determines a main category from among the multiple target categories, and determines the upper limit of the receivable amount of the target store based on the sales trend of the determined main category. The determination unit 136 determines the upper limit of the receivable amount of the target store by weighting the main category more heavily than categories other than the main category from among the multiple target categories.

[0259] The determination unit 136 determines the maximum purchase price of the receivables of the target store using a learning model that has learned the characteristics of the relationship between the trends in sales trends of the store up to a specified point in time and the trends in sales trends of the category corresponding to the products handled by the store, and the sales of the store after the specified point in time.

[0260] The determination unit 136 determines the upper limit of the purchase price of the future receivables of the target store. The determination unit 136 determines an index value for the purchase of the future receivables of the target store based on the sales trend of the target store and the sales trend of the category corresponding to the products handled by the target store, and determines the upper limit of the purchase price of the future receivables of the target store using the determined index value. The determination unit 136 determines the upper limit of the purchase price of the receivables of the target store according to the determination result by the determination unit 135.

[0261] For example, when the determination unit 135 determines that sales in the category of the target store are on an upward trend, the determination unit 136 may increase the upper limit of the receivables of the target store. In this case, when the determination unit 135 determines that sales in the main category of the target store are on an upward trend, the determination unit 136 may increase the upper limit of the receivables of the target store. Also, for example, when the determination unit 135 determines that sales in the category of the target store are on a downward trend, the determination unit 136 may decrease the upper limit of the receivables of the target store. In this case, when the determination unit 135 determines that sales in the main category of the target store are on a downward trend, the determination unit 136 may decrease the upper limit of the receivables of the target store.

[0262] The determination unit 136 determines conditions for purchasing the receivables of the target store based on the probability of occurrence of a negative event by the target store predicted using the first learning model and the future sales potential of the target store predicted using the second learning model. The determination unit 136 determines conditions that are more favorable to the target store as the probability of occurrence of the receivables of the target store becoming uncollectible is lower. The determination unit 136 determines conditions that are more favorable to the target store as the probability of occurrence of the target store closing is lower.

[0263] The determination unit 136 determines conditions for buying the receivables of the target store using a first learning model that has learned characteristics of the association between stores opening on a commerce site and stores closing on the commerce site. The determination unit 136 determines conditions for buying the future receivables of the target store based on the probability of a negative event occurring at the target store and the future sales potential of the target store.

[0264] The determination unit 136 determines a collection mode of accounts receivable corresponding to future receivables of the target store, based on the store closure probability of the target store estimated by the estimation unit 133. The determination unit 136 determines a collection rate of accounts receivable corresponding to future receivables of the target store, based on the store closure probability of the target store. The determination unit 136 determines a collection mode of accounts receivable corresponding to future receivables of the target store, based on the store closure probability of the target store for each period.

[0265] The determination unit 136 determines the collection mode of the accounts receivable corresponding to the future receivable of the target store based on the period corresponding to the shortest learning model among the learning models whose scores are equal to or greater than the threshold. The determination unit 136 determines the period corresponding to the shortest learning model among the learning models whose scores are equal to or greater than the threshold as the collection period of the accounts receivable corresponding to the future receivable of the target store, and determines the collection rate of the accounts receivable corresponding to the future receivable of the target store according to the collection period.

[0266] The determination unit 136 updates the collection mode of the accounts receivable corresponding to the future receivable of the target store when the collection of the accounts receivable corresponding to the future receivable of the target store satisfies a predetermined condition. The determination unit 136 updates the collection mode of the accounts receivable corresponding to the future receivable of the target store when the collection of the accounts receivable corresponding to the future receivable of the target store satisfies a condition related to delay. The determination unit 136 updates the collection mode of the accounts receivable corresponding to the future receivable of the target store based on the updated store closure probability of the target store.

[0267] The determination unit 136 determines, from among the plurality of stores, a proposed store to which a proposal for buying a bond is to be made based on store information on each of the plurality of stores. The determination unit 136 determines the proposed store depending on whether the store advertises. The determination unit 136 determines a store that does not advertise as the proposed store.

[0268] The determination unit 136 determines a suggestion destination store according to the products handled. The determination unit 136 determines a store that handles less than a predetermined threshold as a suggestion destination store.

[0269] The determination unit 136 determines the suggested store using a learning model that has learned the characteristics of the association between a store opening on the commerce site and a change in sales when the store implements measures to increase sales. The determination unit 136 determines the suggested store using a learning model that receives store information of a store as input and outputs a score indicating a change in sales when the measure is implemented. The determination unit 136 determines the suggested store as a store whose score output by the learning model is equal to or greater than a predetermined threshold.

[0270] (Providing Department 137) The providing unit 137 provides various information. The providing unit 137 transmits various information to an external information processing device via the communication unit 110. The providing unit 137 transmits various information to the user terminal 10, the store device 20, and the web server 30. The providing unit 137 transmits content to the user terminal 10.

[0271] The providing unit 137 provides the information determined by the determining unit 136. The providing unit 137 provides the information determined by the determining unit 135. The providing unit 137 provides the information generated by the determining unit 135. The providing unit 137 provides the information classified by the classifying unit 134. The providing unit 137 provides the information estimated by the estimating unit 133.

[0272] The providing unit 137 transmits the information determined by the determining unit 136 to the store device 20 used by the target store. The providing unit 137 provides information indicating the conditions determined by the determining unit 136. The providing unit 137 provides information indicating the upper buyback amount determined by the determining unit 136. The providing unit 137 provides information indicating the collection mode of accounts receivable corresponding to the future receivable of the target store determined by the determining unit 136. The providing unit 137 provides information proposing the purchase of the receivable to the proposed store determined by the determining unit 136.

[0273] 3. Processing Procedure Next, the procedure of information processing executed by the information processing device 100 according to the embodiment will be described with reference to Fig. 16 to Fig. 22. Fig. 16 to Fig. 22 are flowcharts showing an example of the flow of information processing executed by the information processing device.

[0274] First, Fig. 16 will be described. For example, Fig. 16 shows an example of the determination of conditions for buying bonds for each group performed by the information processing device 100. In Fig. 16, the information processing device 100 classifies a plurality of stores that open on a commercial transaction site on a network into a plurality of groups based on store information for each of the stores (step S101). Then, the information processing device 100 determines conditions for buying bonds for each group (step S102).

[0275] Next, FIG. 17 will be described. For example, FIG. 17 shows an example of model learning performed by the information processing device 100 and processing using the learned model. In FIG. 17, the information processing device 100 learns a learning model that predicts the occurrence probability of a negative event, which is an event that occurs within a predetermined period of time by a store that opens a shop on a commercial transaction site on a network and is a negative event for the commercial transaction site (step S201). Then, the information processing device 100 determines the conditions for purchasing the receivables of the target store based on the occurrence probability of the negative event by the target store predicted using the learning model (step S202).

[0276] Next, Fig. 18 will be described. For example, Fig. 18 shows an example of the determination of conditions for buying bonds according to the economic situation of society, performed by the information processing device 100. In Fig. 18, the information processing device 100 estimates the number of occurrences of negative events, which are events that occur at a store opening at a commercial transaction site on a network and are negative events for the commercial transaction site, using social situation information that indicates the economic situation of society (step S301). Then, the information processing device 100 determines the conditions for buying bonds based on the estimated number of occurrences (step S302).

[0277] Next, FIG. 19 will be described. For example, FIG. 19 shows an example of determining the upper limit of receivables purchase price performed by the information processing device 100. In FIG. 19, the information processing device 100 acquires store sales information indicating past sales of a target store, which is a store that opens a shop on a commerce site on a network (step S401). The information processing device 100 also acquires category sales information indicating past sales of each category of products handled on the commerce site (step S402). Then, the information processing device 100 determines the upper limit of receivables purchase price of the target store based on the sales trend of the target store indicated by the store sales information and the sales trend of the category corresponding to the products handled by the target store indicated by the category sales information (step S403).

[0278] Next, FIG. 20 will be described. For example, FIG. 20 shows an example of processing using a plurality of models performed by the information processing device 100. In FIG. 20, the information processing device 100 acquires a first learning model that predicts the occurrence probability of a negative event that is an event caused by a store opening on a commercial transaction site on a network and is a negative event for the commercial transaction site (step S501). The information processing device 100 also acquires a second learning model that predicts the future possibility of sales of a store opening on the commercial transaction site (step S502). Then, the information processing device 100 determines the conditions for buying the receivables of the target store based on the occurrence probability of a negative event caused by the target store predicted using the first learning model and the future possibility of sales of the target store predicted using the second learning model (step S503).

[0279] Next, Fig. 21 will be described. For example, Fig. 21 shows an example of the determination of the collection mode of the accounts receivable corresponding to the future credit performed by the information processing device 100. In Fig. 21, the information processing device 100 estimates a store closure probability, which is the probability that a target store, which is a store that opens on a commercial transaction site on a network, will close from the commercial transaction site after a predetermined period of time (step S601). Then, the information processing device 100 determines the collection mode of the accounts receivable corresponding to the future credit of the target store based on the store closure probability of the target store (step S602).

[0280] Next, Fig. 22 will be described. For example, Fig. 22 shows an example of the determination of a proposed store for buying a bond performed by the information processing device 100. In Fig. 22, the information processing device 100 acquires store information on each of a plurality of stores that open on a commercial transaction site on a network (step S701). Then, based on the store information on each of the plurality of stores, the information processing device 100 determines, from among the plurality of stores, a proposed store to which the proposed store for buying a bond will be proposed (step S702).

[0281] 4. Effects As described above, the information processing device 100 according to the embodiment includes the estimation unit 133 and the determination unit 136. The estimation unit 133 estimates a store exit probability, which is the probability that a target store, which is a store opening on a commercial transaction site on a network, will exit the commercial transaction site after a predetermined period of time. The determination unit 136 determines a collection mode of accounts receivable corresponding to future receivables of the target store, based on the store exit probability of the target store estimated by the estimation unit 133.

[0282] In this way, the information processing device 100 according to the embodiment determines the collection mode of the accounts receivable corresponding to the future receivables of the target store based on the estimated probability of the target store closing, and is able to purchase the future receivables in the determined collection mode, thereby making it possible to provide appropriate services related to the purchase of receivables.

[0283] Moreover, in the information processing device 100 according to the embodiment, the determination unit 136 determines the collection rate of the accounts receivable corresponding to the future receivable of the target store, based on the store closure probability of the target store.

[0284] In this way, the information processing device 100 according to the embodiment can provide appropriate services related to the purchase of receivables by determining the collection rate of accounts receivable corresponding to the target store's future receivables based on the target store's probability of closing.

[0285] In addition, in the information processing device 100 according to the embodiment, the estimation unit 133 estimates the closure probability of a target store using a learning model that has learned the characteristics of the association between stores opening on a commercial transaction site and stores closing down from the commercial transaction site.

[0286] In this way, the information processing device 100 according to the embodiment can provide appropriate services for purchasing receivables by determining the collection mode of accounts receivable corresponding to the target store's future receivables based on the store closure probability estimated using the learning model.

[0287] In the information processing device 100 according to the embodiment, the estimation unit 133 estimates the store closure probability of the target store using a plurality of learning models, each of which corresponds to a different time period and estimates the probability of the store closing during the corresponding time period. The determination unit 136 determines the collection mode of the accounts receivable corresponding to the future receivable of the target store based on the store closure probability of the target store for each time period.

[0288] In this way, the information processing device 100 according to the embodiment can provide appropriate services related to the purchase of receivables by determining the collection mode of accounts receivable corresponding to the target store's future receivables based on the store closure probability estimated using multiple learning models, each of which corresponds to a different period.

[0289] In the information processing device 100 according to the embodiment, the estimation unit 133 estimates the store closure probability of the target store using a plurality of learning models each outputting a score indicating the probability that the store will close within a corresponding period. The determination unit 136 determines the collection mode of the accounts receivable corresponding to the future credit of the target store based on the period corresponding to the learning model with the shortest period among the learning models whose scores are equal to or greater than a threshold.

[0290] In this way, the information processing device 100 of the embodiment uses multiple learning models, each corresponding to a different period, and determines the collection mode of accounts receivable corresponding to the target store's future receivables based on the period corresponding to the learning model with the shortest period among the learning models whose scores are above the threshold, thereby making it possible to provide appropriate services related to the purchase of receivables.

[0291] In addition, in the information processing device 100 according to the embodiment, the determination unit 136 determines the period corresponding to the learning model with the shortest period among the learning models whose score is equal to or above the threshold as the collection period of the accounts receivable corresponding to the future receivable of the target store, and determines the collection rate of the accounts receivable corresponding to the future receivable of the target store according to the collection period.

[0292] In this way, the information processing device 100 according to the embodiment can provide appropriate services related to the purchase of receivables by determining the collection rate of the accounts receivable corresponding to the future receivables of the target store in accordance with the determined collection period.

[0293] Furthermore, in the information processing device 100 according to the embodiment, when the collection of the accounts receivable corresponding to the future receivable of the target store satisfies a predetermined condition, the decision unit 136 updates the collection mode of the accounts receivable corresponding to the future receivable of the target store.

[0294] In this way, the information processing device 100 of the embodiment can provide appropriate services related to the purchase of receivables by updating the collection mode of the accounts receivable corresponding to the future receivables of the target store when the collection of the accounts receivable corresponding to the future receivables of the target store satisfies specified conditions.

[0295] Furthermore, in the information processing device 100 according to the embodiment, when the collection of the accounts receivable corresponding to the future receivable of the target store satisfies the condition related to delay, the decision unit 136 updates the collection mode of the accounts receivable corresponding to the future receivable of the target store.

[0296] In this way, the information processing device 100 of the embodiment can provide appropriate services related to the purchase of receivables by updating the collection mode of the accounts receivable corresponding to the future receivables of the target store when the collection of the accounts receivable corresponding to the future receivables of the target store satisfies the conditions regarding delay.

[0297] In addition, in the information processing device 100 according to the embodiment, when the collection of the accounts receivable corresponding to the future receivable of the target store satisfies the condition related to delay, the estimation unit 133 updates the store closure probability of the target store. The determination unit 136 updates the collection mode of the accounts receivable corresponding to the future receivable of the target store based on the updated store closure probability of the target store.

[0298] In this way, the information processing device 100 of the embodiment can provide appropriate services related to the purchase of receivables by updating the collection mode of the accounts receivable corresponding to the target store's future receivables based on the updated probability of the target store closing when the collection of the accounts receivable corresponding to the target store's future receivables satisfies the conditions regarding delay.

[0299] Moreover, the information processing device 100 according to the embodiment includes a providing unit 137. The providing unit 137 provides information indicating the collection mode of the accounts receivable corresponding to the future credit of the target store determined by the determining unit 136.

[0300] In this manner, the information processing device 100 according to the embodiment can provide appropriate information by providing information indicating the collection status of accounts receivable corresponding to the future receivable of the target store.

[0301] [5. Hardware Configuration] The information processing device 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 23. Fig. 23 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0302] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0303] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0304] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0305] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0306] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0307] Although some of the embodiments and variants of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the lines of the disclosure of the invention.

[0308] [6. Other] Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0309] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0310] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0311] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0312] 1. Information Processing Systems 100 Information processing device 121 Exhibitor information storage unit 122 Model information storage unit 123 Threshold information storage unit 124 Group information storage unit 125 Social Situation Information Storage Unit 126 Commercial transaction site information storage unit 127 Factoring information storage unit 130 Control section 131 Acquisition Department 132 Learning Department 133 Estimation Department 134 Classification Department 135 Judgment section 136 Decision Section 137 Provision Department 10 User terminal 20 Store Equipment 30 Web Server N Network

Claims

1. An estimation unit that estimates a store exit probability, which is a score indicating the probability that a target store, which is a store that opens a store on a commerce site on a network, will exit the commerce site within a plurality of periods; a determination unit that determines a period during which the store closure probability exceeds a threshold as a collection period based on the store closure probability of the target store, which is a score corresponding to each of the multiple periods estimated by the estimation unit, and determines a lower limit of the collection rate of the accounts receivable corresponding to the future receivable of the target store so that the full amount can be collected within the determined collection period, thereby determining a collection mode of the accounts receivable corresponding to the future receivable of the target store, the collection mode including the lower limit; An information processing device comprising:

2. The estimation unit is The store closure probability of the target store is estimated using a learning model that has learned characteristics of the association between stores that open on the commerce site and stores that close from the commerce site.

2. The information processing apparatus according to claim 1,

3. The estimation unit is estimating the store closure probability of the target store using a plurality of learning models, each of which corresponds to a different time period, each of which estimates the probability of a store closure during a corresponding time period; The determination unit is A collection mode of accounts receivable corresponding to future receivables of the target store is determined based on the store closure probability of the target store for each period.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The estimation unit is estimating the store closure probability of the target store using the plurality of learning models, each of which outputs a score indicative of the probability of a store closing within a corresponding time period; The determination unit is Among the learning models whose scores are equal to or greater than the threshold, a collection mode of accounts receivable corresponding to the future credit of the target store is determined based on a period corresponding to the learning model with the shortest period.

4. The information processing apparatus according to claim 3.

5. The determination unit is Among the learning models whose scores are equal to or greater than the threshold, the period corresponding to the learning model with the shortest period is determined as the collection period of the accounts receivable corresponding to the future receivable of the target store, and the collection rate of the accounts receivable corresponding to the future receivable of the target store is determined according to the collection period.

5. The information processing apparatus according to claim 4.

6. The determination unit is If the collection of the accounts receivable corresponding to the future receivable of the target store satisfies a predetermined condition, the collection manner of the accounts receivable corresponding to the future receivable of the target store is updated.

6. The information processing device according to claim 1,

7. The determination unit is If the collection of the accounts receivable corresponding to the future receivable of the target store satisfies a condition regarding delay, the collection manner of the accounts receivable corresponding to the future receivable of the target store is updated.

7. The information processing apparatus according to claim 6,

8. The estimation unit is If the collection of accounts receivable corresponding to the future receivables of the target store satisfies a condition regarding delay, the store closure probability of the target store is updated; The determination unit is Based on the updated store closure probability of the target store, the collection status of the accounts receivable corresponding to the future receivable of the target store is updated.

8. The information processing apparatus according to claim 7,

9. A provision unit that provides information indicating a collection state of accounts receivable corresponding to the future receivable of the target store determined by the determination unit; 9. The information processing device according to claim 1, further comprising:

10. 1. A computer-implemented information processing method, comprising: an estimation step of estimating a store withdrawal probability, which is a score indicating the probability that a target store, which is a store that opens a store on a commerce site on a network, will withdraw from the commerce site within a plurality of time periods; a determination step of determining a period during which the store closure probability exceeds a threshold as a collection period based on the store closure probability of the target store, which is a score corresponding to each of the multiple periods estimated by the estimation step, and determining a lower limit of the collection rate of the accounts receivable corresponding to the future receivable of the target store so that the full amount can be collected within the determined collection period, thereby determining a collection mode of the accounts receivable corresponding to the future receivable of the target store, the collection mode including the lower limit; 13. An information processing method comprising:

11. An estimation step of estimating a store exit probability, which is a score indicating the probability that a target store, which is a store that opens a store on a commerce site on a network, will exit the commerce site within a plurality of periods; a determination step of determining a collection period for which the store closure probability exceeds a threshold based on the store closure probability of the target store, which is a score corresponding to each of the multiple periods estimated by the estimation step, and determining a lower limit of the collection rate of the accounts receivable corresponding to the future receivable of the target store so that the full amount can be collected within the determined collection period, thereby determining a collection mode of the accounts receivable corresponding to the future receivable of the target store, the collection mode including the lower limit; An information processing program characterized by causing a computer to execute the above.

Images