JP7130104B1 - Information processing device, information processing method, and information processing program - Google Patents

Abstract

An object of the present invention is to make it possible to provide appropriate services regarding the purchase of bonds. An information processing apparatus according to the present application has a classification section and a determination section. The classification unit classifies the plurality of stores into a plurality of groups based on the store information regarding each of the plurality of stores that open on the commercial transaction site on the network. The determination unit determines the conditions for purchasing bonds for each group classified by the classification unit. For example, the classification unit classifies a plurality of stores into a plurality of groups using a learning model that has learned characteristics of relationships between stores that open on the commercial transaction site and stores that leave the commercial transaction site. [Selection drawing] Fig. 8

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Conventionally, various techniques have been provided regarding the purchase of receivables (hereinafter also referred to as "factoring"). For example, technology is provided for predicting the amount of future claims and providing funds according to the predicted future amount of claims.

Japanese Patent No. 6836255 Japanese Patent Application Laid-Open No. 2021-033762

However, the above conventional techniques have room for improvement. For example, in the above-described conventional technology, the amount of future receivables is predicted, and funds are provided according to the amount, and it is difficult to flexibly purchase receivables. Therefore, it is desired to be able to provide appropriate services regarding the purchase of bonds.

The present application has been made in view of the above, and an object thereof is to provide an information processing device, an information processing method, and an information processing program capable of providing appropriate services regarding the purchase of claims.

An information processing apparatus according to the present application includes a classification unit that classifies the plurality of stores into a plurality of groups based on store information about each of the plurality of stores that open on a commercial transaction site on a network; and a decision unit that decides the conditions regarding the purchase of bonds for each group.

According to one aspect of the embodiment, there is an effect that it is possible to provide an appropriate service regarding the purchase of a bond.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 3 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 4 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 5 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 6 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 7 is a diagram illustrating a configuration example of an information processing system according to the embodiment; FIG. 8 is a diagram illustrating a configuration example of an information processing apparatus according to the embodiment; 9 is a diagram illustrating an example of a store owner information storage unit according to the embodiment; FIG. 10 is a diagram illustrating an example of a model information storage unit according to the embodiment; FIG. 11 is a diagram illustrating an example of a threshold information storage unit according to the embodiment; FIG. 12 is a diagram illustrating an example of a group information storage unit according to the embodiment; FIG. 13 is a diagram illustrating an example of a social situation information storage unit according to the embodiment; FIG. 14 is a diagram illustrating an example of a commercial transaction site information storage unit according to the embodiment; FIG. 15 is a diagram illustrating an example of a factoring information storage unit according to the embodiment; FIG. FIG. 16 is a flowchart illustrating an example of the flow of information processing executed by the information processing device. FIG. 17 is a flowchart illustrating an example of the flow of information processing executed by the information processing device. FIG. 18 is a flowchart illustrating an example of the flow of information processing executed by the information processing device. FIG. 19 is a flowchart showing an example of the flow of information processing executed by the information processing device. FIG. 20 is a flowchart showing an example of the flow of information processing executed by the information processing device. FIG. 21 is a flowchart illustrating an example of the flow of information processing executed by the information processing device. FIG. 22 is a flowchart illustrating an example of the flow of information processing executed by the information processing device. FIG. 23 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus.

Hereinafter, modes for implementing an information processing apparatus, an information processing method, and an information processing program (hereinafter referred to as "embodiments") according to the present application will be described in detail with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

(embodiment)
[1. information processing]
An example of information processing executed by the information processing system 1 will be described below with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. The information processing system 1 executes information processing related to electronic commerce (EC) services. For example, the information processing device 100 of the information processing system 1 executes information processing regarding the purchase of credits of businesses that open stores on commercial transaction sites 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 as long as the following information processing can be applied. . Further, hereinafter, a business operator who opens a store on a commercial transaction site may be referred to as a store owner, and a business operator who has left the commercial transaction site after opening a store may be referred to as a store closing person.

In the information processing described below, a case of processing future claims as an example of claims will be shown. The future receivables referred to here are, for example, future sales that have not yet occurred for a store opened on a commercial transaction site. The future receivables may be sales expected to be generated in the future on the commercial transaction site by a store opened on the commercial transaction site. It should be noted that the following processing for future claims is merely an example, and the claims are not limited to future claims, and may be any claims as long as the following information processing can be applied. For example, the receivables may be any receivables as long as they are legally permitted to be factored.

[1-1. Configuration of information processing system]
Prior to explaining the processing shown in FIGS. 1 to 6, the configuration of the information processing system 1 will be explained using FIGS. 1 and 7. FIG. FIG. 7 is a diagram illustrating a configuration example of an 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 communicatively connected via a predetermined network N 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. good.

A 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 a user who accesses content such as web pages displayed on a browser and content for applications. For example, the user terminal 10 is used by the user to view contents (web pages, etc.) of a commercial transaction site, purchase products on the commercial transaction site, and post product information evaluations (so-called reviews). be.

The user terminal 10 is realized by, for example, a smart phone, 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 smart phone. In addition, below, the user terminal 10 may be described as a user. That is, hereinafter, the user can also be read as the user terminal 10 .

The store device 20 is a computer used by a business operator who conducts business related to stores. For example, the store device 20 is used by an operator (operator) of a store (store) that opens a store on a commercial transaction site. Store device 20 transmits and receives information to and from web server 30 . The business uses the store device 20 to open a store on the commercial transaction site provided by the web server 30 . The store device 20 transmits to the web server 30 various kinds of information about the store opened by the business operator on the commercial transaction site. For example, the store device 20 transmits various information regarding 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 .

The store device 20 is realized by, for example, a smart phone, a tablet terminal, a notebook PC (laptop 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. Note that the store device 20 may be hereinafter referred to as a store or a business operator (operator) who has opened a store. That is, hereinafter, the store or business operator (store owner) can also be read as the store device 20 .

The web server 30 is a server device that provides electronic commerce services to users. The web server 30 provides a commercial transaction site such as an electronic shopping mall on the network. The web server 30 provides users with online shopping services at commercial transaction sites. For example, the web server 30 provides various types of information regarding commercial transaction sites in response to requests from the user terminal 10 used by the user, and executes purchase processing for products that the user wishes to purchase.

In the commercial transaction site provided by the web server 30, each business operator opens a store (store) that handles products of various categories. The web server 30 accepts a request to open a store on the commercial transaction site from the store device 20 used by the business. The web server 30 receives, from the store device 20, various kinds of information about the store opened by the business operator on the commercial transaction site. The web server 30 adds the store opened by the requesting business to the commercial transaction site. Information communication and the like between the web server 30, the store device 20, and the user terminal 10 described above are the same as in the case of online shopping in a general electronic commerce service, so detailed descriptions thereof will be omitted.

The web server 30 provides information to the information processing device 100 . The web server 30 transmits to the information processing apparatus 100 various information necessary for processing by the information processing apparatus 100 . The web server 30 provides the information processing device 100 with information regarding commercial transaction sites. For example, the web server 30 provides the information processing apparatus 100 with various types of information collected at a commercial transaction site. For example, the web server 30 provides the information processing apparatus 100 with various information such as a history of sales at each store on the commercial transaction site and a history of purchases by each user. The web server 30 provides information collected from the store device 20 and the user terminal 10 to the information processing device 100 .

The information processing device 100 is a computer that executes information processing related to the purchase of credits of businesses that open stores on commercial transaction sites. For example, the information processing device 100 is a determination device that determines conditions (also referred to as “factoring conditions”) regarding the purchase of bonds using various types of information. Further, the information processing apparatus 100 determines the maximum purchase amount of the credits of the store using various types of information. In addition, the information processing apparatus 100 determines the mode of collection of accounts receivable corresponding to the future credit of the store based on the estimated (predicted) store closing probability. Further, the information processing apparatus 100 determines the proposed store to which the purchase of the bond is proposed from among the plurality of stores opened on the commercial transaction site.

[1-2. Overall overview of processing in information processing system]
An example of information processing performed by the information processing system 1 will now be described with reference to FIGS. 1 to 6. FIG. First, using FIG. 1, an outline of processing in the information processing system 1 including transmission and reception of information between each device of the information processing system 1 will be described. Then, details of each information processing will be described using FIGS. explain. The electronic commerce service provided by the information processing system 1 is the same as general electronic commerce services except for the purchase of claims. omitted.

First, the store device 20 used by the business performs processing for opening the store of the business (step S1). For example, the store device 20 requests the web server 30 to open a store in response to the operator's operation, and the web server 30 adds the business operator's store to the commercial transaction site in response to the request from the store device 20 .

Also, the user using the user terminal 10 uses the commercial transaction site provided by the web server 30 (step S2). For example, the web server 30 provides users with online shopping services on commercial transaction sites in response to requests from the user terminals 10 used by the users. For example, the web server 30 provides the user terminal 10 with various information related to commercial transaction sites, and executes purchase processing for products that the user wishes to purchase.

Then, the information processing apparatus 100 acquires information used for processing from the web server 30 (step S3). The information processing device 100 receives information on commercial transaction sites from the web server 30 . For example, the information processing apparatus 100 acquires from the web server 30 various types of information that the web server 30 has collected through the services of the commercial transaction site. For example, the information processing apparatus 100 acquires various information from the web server 30, such as a history of sales at each store on the commercial transaction site and a history of purchases by each user. Note that the information processing device 100 may acquire information from the store device 20 or the user terminal 10 .

Then, the information processing apparatus 100 executes various information processing using the acquired information (step S4). The information processing apparatus 100 executes the determination process using the acquired information. For example, the information processing apparatus 100 uses the acquired information to execute determination processing for determining the conditions for purchasing the bond, details of which will be described later.

Then, the information processing apparatus 100 uses the information determined by the determination process to provide the service to the business operator (step S5). For example, the information processing apparatus 100 uses the information determined by the determination process to provide the information providing service to the business operator. The information processing device 100 transmits the information determined by the determination process to the store device 20 used by the business. For example, the information processing device 100 transmits, to the store device 20 used by the business operator, information indicating the maximum purchase amount of credits of the store based on the information determined by the determination process. In this way, the information processing apparatus 100 can provide appropriate services related to the purchase of claims by providing information to the business operator using the information determined by the determination process. The details of the services provided to the store by the information processing apparatus 100 will be described later.

[1-3. Information processing details]
Assuming the information processing performed by the information processing system 1 described above, details of various information processing performed by the information processing apparatus 100 will be described. It should be noted that descriptions of the same points as those described above will be omitted as appropriate. Also, various types of processing described below may be combined as appropriate.

[1-3-1. Processing based on classification]
For example, the information processing apparatus 100 may perform determination processing using grouping results obtained by grouping (classifying) a plurality of stores into a plurality of groups. In this case, the information processing apparatus 100 groups the stores based on information indicating the probability of non-collection calculated based on the store data (store information), and sets the purchase limit month, which is an example of an index value, for each group. Determine factoring conditions such as numbers. Then, the information processing apparatus 100 multiplies the upper limit number of months for purchase by a value based on the store's sales performance (last month or the like) to determine the upper limit purchase price. An example of processing based on such classification will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of information processing executed by an information processing apparatus; In the example of FIG. 2, only some stores such as stores SP1, SP2, SP12, and SP15 are shown as examples of stores opened on the commercial transaction site, but there are many stores on the commercial transaction site. shall be

In FIG. 2, a model M1, which is a learning model (hereinafter simply referred to as "model") that outputs a score (also referred to as "store exit score") indicating the probability (possibility) that a store will withdraw from a commercial transaction site, is used. , a case where the information processing apparatus 100 performs grouping. The model M1 is a store closing model, and is a model learned by machine learning. Note that the grouping using the information on closing the store is only an example, and the information processing apparatus 100 may group the stores using information on the risk of not being able to collect the credit, not limited to the closing of the store.

For example, the risk of uncollectible receivables includes negative events (also referred to as “negative events”) for the commercial transaction site. Negative events include various actions (also referred to as "negative actions") by the store that can cause negative events. For example, negative events include violation of terms, inability to contact, sales of illegal products, malicious advertisements, sales of counterfeit goods, delinquency in payment of store opening fees, sudden drop in store evaluation, frequent cancellations, delivery delays, and the like. For example, the information processing apparatus 100 may group stores using information on various risks including negative events as described above. In addition, the information processing apparatus 100 may group the stores using information regarding the future potential of the store, in addition to the information regarding the risk of closing the store.

Further, the information processing apparatus 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 by itself. For example, when learning the model M1, the information processing apparatus 100 learns the model M1 using learning data LDT1 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT1 includes data in which information about a store (also referred to as "store information") is associated with a label indicating whether or not the store has closed (also referred to as "correct information"). .

In addition, store information includes information on the business of the store operator (business information), information on products traded (sold) at the store (product information), information on the category of products traded (sold) at the store ( category information), information on sales of the store (sales information), information on evaluation of an evaluation target related to the store (evaluation information), and the like, the details of which will be described later. Further, for example, as the correct information for each store, "1" is assigned when the store is closed, and "0" is assigned when the store is not closed. For example, as the correct information for each store, "1" is assigned to store information of a store up to a certain point in time (point in time X) if the store closed within one year from point in time X, and the store is "0" may be assigned if the store has not exited within one year from X. In this case, the information processing apparatus 100 creates a model for estimating (predicting) the probability (possibility) that the store will close within a desired period (for example, one month, six months, five years, etc.), not limited to one year. can be generated.

For example, the information processing apparatus 100 performs back propagation (error backpropagation) or the like so that the score output by the model M1 approaches the correct information (label) associated with the store information of the store input to the model M1. The learning process is performed by the method of For example, the information processing apparatus 100 determines that the score output by the model M1 to which store information including at least one of store business information, product information, category information, sales information, evaluation information, etc. is input corresponds to the store. Learning processing is performed so as to approach the attached correct information. For example, when the correct answer information is "1" and the store information of the store to which the correct answer information is assigned is input, the information processing apparatus 100 makes the score output by the model M1 approach "1". , the learning process is performed. Further, for example, when the correct information is "0" and the store information of the store to which the correct information is assigned is input, the information processing apparatus 100 makes the score output by the model M1 approach "0". , the learning process is performed.

For example, the information processing apparatus 100 adjusts the values of weights (that is, connection coefficients) that are considered when values are transmitted between nodes by learning processing. In this way, the information processing apparatus 100 learns the model M1 by processing such as back propagation that corrects the parameters (connection coefficients) so that the error between the output of the model M1 and the correct information corresponding to the input is reduced. . For example, the information processing apparatus 100 generates the model M1 by performing processing such as back propagation so as to minimize a predetermined loss function. Thereby, the information processing apparatus 100 can perform learning processing for learning the parameters of the model M1.

Note that the model learning method is not limited to the method described above, and any known technique can be applied. Note that each model may be generated using various conventional techniques related to machine learning as appropriate. For example, a model may be generated using a technology related to supervised learning machine learning such as SVM (Support Vector Machine). Also, for example, model generation may be performed using techniques related to unsupervised machine learning. For example, model generation may be performed using deep learning techniques. For example, the model may be generated using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). Note that the above description of model generation is an example, and model generation may be performed by a learning method appropriately selected according to obtainable information and the like. That is, if the information processing apparatus 100 can learn the model M1 so as to output a score corresponding to the correct answer information when the store information included in the learning data is input, what kind of method can be used to train the model M1? You can generate.

From here, the information processing shown in FIG. 2 will be described in detail on the premise of the above-described contents. First, in FIG. 2, the information processing apparatus 100 calculates a closing score for each of a plurality of stores that open on the commercial transaction site. The information processing apparatus 100 inputs the 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, merchandise information, category information, sales information, evaluation information, etc. 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, model M1 to which store information SINF1 is input outputs a score of "0.9" as indicated by score SC1. In this way, since the closing score of the store SP1 is "0.9", which is close to "1", the information processing apparatus 100 can estimate that the store SP1 is likely to exit the commercial transaction site. .

The information processing apparatus 100 also inputs the store information SINF2 of the 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, evaluation information, etc. of the store SP2 to the model M1. The model M1 to which the store information SINF2 is input outputs a score (step S11-4). In the example of FIG. 2, the model M1 to which the store information SINF2 is input outputs a score of "0.05" as indicated by the score SC2. In this way, since the exit score of the store SP2 is "0.05" and close to "0", the information processing device 100 can estimate that the possibility of the store SP2 exiting the commercial transaction site is low. .

Similarly, the information processing apparatus 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 is input outputs a score (step S11-6). In the example of FIG. 2, the model M1 to which the store information SINF12 is input outputs a score of "0.07" as indicated by the score SC12. The information processing apparatus 100 also 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 is input outputs a score (step S11-8). In the example of FIG. 2, the model M1 to which the store information SINF15 is input outputs a score of "0.15" as indicated by the score SC15. Through similar processing, the information processing apparatus 100 similarly calculates closing scores for stores other than the stores SP1, SP2, SP12, and SP15, but detailed description thereof will be omitted.

Then, the information processing device 100 classifies the plurality of stores into a plurality of groups based on the closing score of each store (step S12). The information processing apparatus 100 groups each store into a plurality of groups using the closing score of each store and a plurality of thresholds. For example, the information processing apparatus 100 groups each store into a plurality of groups using the thresholds for grouping stored in the threshold information storage unit 123 (see FIG. 11). In FIG. 2, in order to simplify the explanation, the case of using nine thresholds that increase at intervals of "0.1" will be explained as an example. 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", and a fourth threshold TH3 of value "0.4" Threshold TH4, fifth threshold TH5 with value "0.5", sixth threshold TH6 with value "0.6", seventh threshold TH7 with value "0.7", eighth threshold TH8 with value "0.8" , a ninth threshold TH9 of value "0.9" is used.

The information processing apparatus 100 groups each store into a plurality of groups according to the comparison result of comparing the closing score of each store with nine thresholds (first threshold TH1 to ninth threshold TH9). The information processing apparatus 100 groups each store into 10 groups according to the closing score of each store, as shown in the grouping information GLT1 of FIG. Specifically, the information processing apparatus 100 includes the first group, the second group, the third group, the fourth group, the fifth group, the sixth group, the seventh group, the eighth group, the ninth group, and the tenth group. Sort each store into one of the groups. Note that the number of groups is not limited to 10, and may be any number such as 5 or 15, for example.

Here, as shown in the grouping information GLT1 in FIG. 2, each group is associated with the number of months to be purchased for future bonds (also referred to as "number of months to be purchased"). Thereby, the information processing apparatus 100 determines the conditions for purchasing the bond for each group. For example, the information processing apparatus 100 determines to allocate a longer number of purchase target months to a group to which a store that is estimated to have a lower store closing probability belongs. In this way, the information processing apparatus 100 determines conditions that are advantageous to the stores belonging to a group with a lower possibility of closing. That is, the information processing apparatus 100 determines conditions that are advantageous to stores belonging to a group with a lower risk.

In the example of FIG. 2, the first group to which the store estimated to have the lowest closing probability belongs is associated with "3", which is the longest purchase target month number. In this case, the information processing device 100 indicates that the stores belonging to the first group are subject to purchase of future claims up to three months ahead.

In addition, the tenth group to which the store estimated to have the highest closing probability belongs is associated with "0", which is the shortest number of months to be purchased. In this case, the information processing apparatus 100 indicates that future claims will not be purchased from stores belonging to the tenth group. For example, when the information processing apparatus 100 also purchases items other than future claims, the information processing apparatus 100 only purchases items other than future claims for stores belonging to the tenth group.

For example, the information processing apparatus 100 classifies stores whose closing score is less than the first threshold TH1 into the first group. In FIG. 2, the information processing apparatus 100 classifies the store SP2 whose exit score is "0.05" and is less than the first threshold TH1 of "0.1" into the first group. Further, the information processing apparatus 100 classifies the store SP12 whose closing score is "0.07" and which is less than the first threshold TH1 of "0.1" into the first group.

In addition, the information processing apparatus 100 classifies stores whose closing scores are equal to or greater than the first threshold TH1 and less than the second threshold TH2 into the second group. In FIG. 2, the information processing apparatus 100 determines that the closing score of the store SP15 is "0.15", is equal to or greater than the first threshold TH1 of "0.1", and is less than the second threshold TH2 of "0.2". are classified into the second group.

In addition, the information processing apparatus 100 classifies stores whose closing scores are equal to or greater than the second threshold TH2 and less than the third threshold TH3 into the third group. In FIG. 2, the information processing apparatus 100 determines that the exit score (for example, "0.23") of the store SP3 is equal to or greater than "0.2" of the second threshold TH2 and less than "0.3" of the third threshold TH3. are classified into the third group. Similarly, the information processing apparatus 100 classifies the stores satisfying the conditions into the fourth to ninth groups using the third threshold TH3 to ninth threshold TH9.

In addition, the information processing apparatus 100 classifies stores whose exit score is equal to or higher than the ninth threshold TH9 into the tenth group. In FIG. 2, the information processing apparatus 100 classifies the store SP1 whose exit score is "0.9" and whose closing score is equal to or greater than the ninth threshold TH9 of "0.9" into the tenth group.

Note that the above-described processing is merely an example, and the information processing apparatus 100 may group each store into a plurality of groups using various information as appropriate. For example, the information processing apparatus 100 may perform grouping using a value obtained by multiplying the closing score of each store by the sales of each store (also referred to as a "damage score"). In this case, the information processing apparatus 100 may classify the lower the damage score into a group with better conditions regarding the purchase of the bond.

Further, the information processing apparatus 100 may group each store into a plurality of groups without using thresholds. For example, the information processing apparatus 100 may perform grouping based on information regarding ratios and logarithms. For example, the information processing apparatus 100 may perform grouping so that scores belonging to each group have the same ratio as much as possible. For example, the information processing apparatus 100 may sort each store in descending order of closing 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.

Then, the information processing apparatus 100 determines the maximum purchase amount of future bonds of each store according to the classification result (step S13). For example, the information processing apparatus 100 determines the upper limit purchase amount of future bonds of each store using the formula "purchase upper limit amount=sales×number of months to be purchased" as shown in the calculation function FC1 in FIG. Specifically, the information processing apparatus 100 determines the upper limit purchase amount of future bonds 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. For the sales of a store, the sales of the store in the immediately preceding month may be used, or the average sales of past months may be used. Note that the sales for the previous month and the average sales for the past month are only examples, and any value that can be used as the sales for the store for the month is used for the sales of the store. For example, a predicted value (estimated value) of sales for the next month may be used.

For example, when the sales of the store SP1 is the value SL1, the information processing apparatus 100 sets the purchase upper limit to "0 (=SL1×0 )”. Note that the value SL1 is assumed to be a specific numerical value such as "30,000 yen" or "150,000 yen".

Further, when the sales of the store SP2 is the value SL2, the information processing apparatus 100 sets the purchase upper limit to "PL2 (=SL2×3 )”. It is assumed that the value SL2 is a specific numerical value such as "50,000 yen" or "120,000 yen". That is, the purchase upper limit PL2 is three times the sales value SL2. Similarly, the information processing apparatus 100 determines the maximum purchase amount for other stores.

Note that the information processing apparatus 100 may adjust the purchase upper limit using other information. For example, the information processing apparatus 100 may increase the purchase upper limit for a store that has used factoring in the past and has completed collection without delay. For example, the information processing apparatus 100 may increase the purchase upper limit for a store highly rated by users or a store with a high future potential. For example, the information processing apparatus 100 may increase the maximum purchase amount when a score output by a future potential model, which will be described later, is equal to or greater than a predetermined threshold.

Then, the information processing apparatus 100 provides information using the determined information (step S14). For example, the information processing apparatus 100 may provide information indicating the maximum purchase amount to a store whose maximum purchase amount is equal to or greater than a predetermined value. In this case, the information processing device 100 may transmit information indicating the maximum purchase price to the store device 20 of the store whose maximum purchase price is equal to or greater than a predetermined value (for example, 100,000 yen). In addition, the information processing apparatus 100 may provide information indicating the purchase upper limit amount or the number of months to be purchased to a store whose number of months to be purchased is equal to or greater than a predetermined value. In this case, the information processing device 100 may transmit information indicating the purchase upper limit amount or the number of months to be purchased to the store device 20 of the store whose number of months to be purchased is equal to or greater than a predetermined value (for example, two months). good.

In this way, the information processing apparatus 100 classifies a plurality of stores that open on the commercial transaction site into a plurality of groups, and determines the conditions regarding the purchase of bonds for each classified group. As a result, the information processing apparatus 100 can purchase the bond according to the determined conditions, and can provide an appropriate service related to the purchase of the bond. For example, when factoring future receivables, the future receivables will be purchased, so if the store closes in the near future, it may be difficult to collect the funds. Therefore, the information processing device 100 performs grouping according to the risk of closing the store, etc., and determines an index value such as the number of months to be purchased for each group, thereby reducing the possibility of difficulty in collecting funds. can be done.

In the above example, the model M1, which is a learning model, is used to calculate the closing score, but the information processing apparatus 100 calculates the closing score of each store without using the learning model. may be calculated. In this case, the information processing apparatus 100 may calculate the closing score of each store based on rules, for example. The information processing apparatus 100 may calculate the closing score of each store, for example, using rule information that associates conditions with closing scores. The information processing apparatus 100 compares the store information with each rule (condition), and if the store information of the store satisfies the rule, the store exit score of the rule may be used as the store exit score of the store. The information processing apparatus 100 may also compare the store information with rules (conditions) belonging to each group, and classify the stores into groups in which the store information of the stores satisfies the rules.

[1-3-2. Processing based on the model corresponding to the period]
Note that the processing based on the grouping described above is merely an example, and the information processing apparatus 100 may determine the conditions regarding the purchase of bonds without grouping. In this case, the information processing apparatus 100 generates a learning model for estimating the probability (possibility) of occurrence of negative events such as store closures and rule violations within a certain period of time using store data (store information), Based on the estimated information, factoring conditions such as the maximum number of months for purchase of future receivables are determined.

In FIG. 3, the closing of the store from the commercial transaction site will be described as an example of a negative event. . For example, the information processing device 100 estimates a period in which the possibility of store closure satisfies a predetermined criterion using a plurality of models that output a score indicating the probability (possibility) of store closure for each period. , to determine the factoring terms based on that period.

This point will be described with reference to FIG. FIG. 3 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 3 illustrates an example of processing based on a model corresponding to a period. In the example of FIG. 3, the case where the store SP12 is the target store for determining the factoring conditions (also referred to as the "target store") will be described as an example, but the target store is not limited to the store SP12. store. It should be noted that descriptions of the same points as those described above will be omitted as appropriate.

In FIG. 3, models M11, M12, M13, M14, etc., which are learning models (models) that output a score (store exit score) indicating the probability (possibility) that the store will exit the commercial transaction site within a predetermined period of time. A case where the information processing apparatus 100 performs determination processing using a plurality of models is shown as an example. Models M11, M12, M13, M14, etc. are store exit models corresponding to different periods, and are learned by machine learning.

Here, the model M11 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the commercial transaction site within one month from that point. The model M12 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the commercial transaction site within two months from that time. The model M13 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the commercial transaction site within three months from that point. The model M14 is a model that outputs a score indicating the probability (possibility) that the target store will withdraw from the commercial transaction site within four months from that point. In FIG. 3, only the models M11, M12, M13, and M14 are illustrated, but the model M15, which outputs a score indicating the probability (possibility) that the target store will withdraw from the commercial transaction site within five months, A model corresponding to each period may be used, such as the model M16 that outputs a score indicating the probability (possibility) that the target store will withdraw from the commercial transaction site during the period. Also, the period is not limited to one month, and may be any interval such as one week.

Further, the information processing apparatus 100 may acquire a plurality of models M11, M12, M13, M14, etc. from a model providing server or the like that provides learning models, or may acquire a plurality of models M11, M12, M13, M14 by itself. etc. can be learned. For example, when learning the model M11, the information processing apparatus 100 learns the model M11 using learning data LDT11 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT11 includes information about the store (store information) and whether or not the store closed within one month from the time when the latest information in the store information was acquired (also referred to as "starting time"). contains data associated with a label (correct answer information) indicating

For example, as the correct information for each store, "1" is assigned if the store has closed within one month from the start of the calculation, and "1" is assigned if the store has not closed within one month from the start of the calculation. 0” is assigned. The information processing apparatus 100 performs learning processing so that the score output by the model M11 to which the store information of the store is input approaches the correct information associated with the store. For example, when the correct answer information is "1" and the store information of the store to which the correct answer information is assigned is input, the information processing apparatus 100 makes the score output by the model M11 approach "1". , the learning process is performed. Further, for example, when the correct information is "0" and the store information of the store to which the correct information is assigned is input, the information processing apparatus 100 makes the score output by the model M11 approach "0". , the learning process is performed. Note that the learning process for the model M11 is the same as the learning process for the model M1, so detailed description will be omitted.

When learning the model M12, the information processing apparatus 100 uses the learning data LDT12 stored in the model information storage unit 122 to learn the model M12. For example, the learning data LDT12 contains information about the store (store information) and a label ( Correct answer information) are associated with each other.

For example, as the correct information for each store, "1" is assigned if the store has closed within two months from the start of the calculation, and "1" is assigned if the store has not closed within two months from the start of the calculation. 0” is assigned. The information processing apparatus 100 performs learning processing so that the score output by the model M12 to which the store information of the store is input approaches the correct information associated with the store. For example, when the correct answer information is "1" and the store information of the store to which the correct answer information is assigned is input, the information processing apparatus 100 makes the score output by the model M12 approach "1". , the learning process is performed. Further, for example, when the correct answer information is "0", 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 to the information processing apparatus 100. , the learning process is performed. Note that the learning process for the model M12 is the same as the learning process for the models M1 and M11, so a detailed description thereof will be omitted.

Similarly, when learning the model M13, the information processing apparatus 100 uses the learning data LDT13 stored in the model information storage unit 122 to learn the model M13, and when learning the model M14, the model information storage unit 122 The model M14 is learned using the learning data LDT14 stored in . For example, the learning data LDT13 contains information about the store (store information) and a label ( Correct answer information) are associated with each other. For example, the learning data LDT14 contains information about the store (store information) and a label ( Correct answer information) are associated with each other. Note that the learning process for the models M13 and M14 is the same as the learning process for the models M1, M11 and M12, so a detailed description will be omitted. If the information processing apparatus 100 can learn the models M11, M12, M13, and M14 so as to output a score corresponding to the correct answer information when the store information included in the learning data is input, how can the information processing apparatus 100 The models M11, M12, M13, and M14 may be generated by any method.

From now on, the information processing shown in FIG. 3 will be described in detail on the premise of the above-described contents. First, in FIG. 3, the information processing apparatus 100 calculates the closing score for each period for the store SP12, which is the target store. The information processing apparatus 100 inputs the store information SINF12-1 of the store SP12 to the model M11 that predicts the probability (possibility) of closing the store 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, merchandise information, category information, sales information, evaluation information, etc. 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 has a closing score of 0.02 indicating the probability (possibility) of closing the store within one month, as indicated by the score SC12-1. ' is output. In this way, since the closing score indicating the probability (possibility) of closing the store SP12 in one month is "0.02", which is close to "0", the information processing apparatus 100 determines that the store SP12 It can be estimated that there is a low possibility of exiting from the commercial transaction site within one month from that point.

The information processing apparatus 100 also inputs the store information SINF12-2 of the store SP12 to the model M12 that predicts the probability (possibility) 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 if the input of the model differs for each period, the store information SINF12-2 may be different from the store information SINF12-1. For example, the store information may have different collection periods. The model M12 to which the store information SINF12-2 is input outputs a store exit score (step S21-4). In the example of FIG. 3, the model M12 to which the store information SINF12-2 is input has a store closing score of 0.2 indicating the probability (possibility) of closing the store within two months, as indicated by the score SC12-2. ' is output.

Similarly, the information processing apparatus 100 inputs the store information SINF12-3 of the store SP12 into the model M13 that predicts the probability (possibility) of closing the store within three months (step S21-5), and stores the store information SINF12. The model M13, to which -3 is input, outputs the 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 if the input of the model 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 is input has a closing score of 0.52 indicating the probability (possibility) of closing the store within three months, as indicated by the score SC12-3. ' is output.

Further, the information processing apparatus 100 inputs the store information SINF12-4 of the store SP12 into the model M14 for predicting the probability (possibility) of closing the store in four months (step S21-7), and stores the store information SINF12-4. The model M14 to which 4 is input outputs a closing score (step S21-8). In the example of FIG. 3, the model M14 to which the store information SINF12-4 is input has a store closing score of 0.65 indicating the probability (possibility) of closing the store within four months, as indicated by the score SC12-4. ' is output. In this way, the information processing apparatus 100 calculates a closing score that increases in value as the period lengthens. The information processing apparatus 100 may calculate a store closing score indicating the probability (possibility) of closing the store within five months or a closing score indicating the probability (possibility) of closing the store within six months. good.

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

The information processing apparatus 100 compares the closing score output by each model with the threshold value TH11, and determines the number of months to be purchased for the future bond of the target store based on the comparison result. For example, the information processing apparatus 100 determines the period corresponding to the learning model with the shortest period among the learning models for which the closing score is equal to or greater than the threshold TH11 as the number of months to be purchased for the future bond of the target store. In FIG. 3, the information processing apparatus 100 compares the closing score output by the models M11, M12, M13, M14, etc. with the value of the threshold TH11 of "0.5" to determine the future bond purchase target month of the store SP12. determine the number. Since the closing score "0.52" output by the model M13 for predicting the probability (possibility) of closing the store in three months is equal to or greater than the threshold TH11, the information processing apparatus 100 determines the number of target months information in FIG. As indicated by TM1, the number of months to be purchased for future bonds of the store SP12 is determined to be "3".

Note that the above-described processing is merely an example, and the information processing apparatus 100 may use various information as appropriate to determine the number of months to be purchased for the future bond of the target store. For example, the information processing device 100 sets a period shorter than the period corresponding to the learning model with the shortest period among the learning models for which the closing score is equal to or greater than the threshold TH11 as the number of months to be purchased for future bonds of the target store. may decide. In this case, the information processing apparatus 100 selects a period (for example, two months) shorter than the period (three months) corresponding to the model M13 in which the closing score is equal to or higher than the threshold TH11 as the purchase target month of future bonds of the store SP12. number can be determined. Further, for example, the information processing apparatus 100 may determine the number of months to be purchased for future bonds by using a value obtained by accumulating store closing scores for each period. For example, the information processing apparatus 100 accumulates store closing scores in ascending order of month to calculate the accumulated score, compares the accumulated score with a threshold, and purchases the number of months when the accumulated score exceeds the threshold. You can decide on the number of months. In this case, for example, if the exit score after one month is "0.02" and the exit score after two months is "0.2", the information processing apparatus 100 sets the cumulative score to "0.22". (=0.02+0.2)". Then, when the threshold is "0.2", the information processing apparatus 100 determines the number of months "2" in which the accumulated score "0.22" exceeds the threshold "0.2" as the number of months to be purchased.

Then, the information processing device 100 determines the maximum purchase amount of future bonds of the store SP12 based on the determined number of months to be purchased and the sales information of the store SP12. Detailed description is omitted. For example, the information processing apparatus 100 uses the calculation function FC1 (see FIG. 2) to determine the purchase upper limit of the store SP12 to be "PL2 (=SL2×3)" when the sales of the store SP2 is the value SL2. .

Then, the information processing apparatus 100 provides information using the determined information (step S23). Since the information provision is the same as the processing described with reference to FIG. 2, a detailed description will be omitted. may be provided. In this case, the information processing device 100 may transmit information indicating the number of months to be purchased or the maximum purchase price of the store SP 12 to the store device 20 used by the business operator of the store SP 12 .

In this way, the information processing apparatus 100 predicts the closing score of the target store for each period, and uses the predicted closing score for each period to determine the conditions for purchasing the bond. As a result, the information processing apparatus 100 can purchase the bond according to the determined conditions, and can provide an appropriate service related to the purchase of the bond. For example, when factoring future receivables, the future receivables will be purchased, so if the store closes in the near future, it may be difficult to collect the 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 the period, thereby making it difficult to collect funds. can be reduced.

As described above, for example, the information processing apparatus 100 can increase the amount of receivables to be purchased by estimating the period until closing of the store and setting the sales during that period as the period to be purchased. Note that the processing described above is merely an example, and the information processing apparatus 100 determines factoring conditions using various types of information. For example, the information processing apparatus 100 may use multiple models for estimating the probability of occurrence of each negative event. In this case, the information processing apparatus 100 may estimate the store exit probability using a plurality of scores output by a plurality of models corresponding to negative events. The information processing apparatus 100 calculates the occurrence probability of each negative event, estimates the store closing probability based on the calculated occurrence probability, and determines factoring conditions based on the estimated closing probability. good.

[1-3-3. Processing based on social conditions]
Note that the information processing apparatus 100 may use various information other than the information of the store. For example, the information processing apparatus 100 may use social conditions such as social economic conditions. In this case, the information processing apparatus 100 estimates the total number of closed stores (hereinafter simply referred to as “the number of closed stores” or “the number of closed stores”) based on social conditions such as stock prices, and determines the estimated number of closed stores. Purchasing conditions may be set based on this. For example, the information processing apparatus 100 reflects the estimated number of closed stores in the store grouping.

In FIG. 4, the number of stores exiting the commercial transaction site (the number of stores closing) will be described as an example of the number of occurrences of negative events. Not limited to exiting the store, violation of terms, inability to contact, sale of illegal goods, malicious advertisement, sale of counterfeit goods, delinquency in payment of opening fee, rapid drop in store evaluation, frequent cancellations, delay in delivery, etc. In this way, the number of occurrences of negative events to be targeted is not limited to the number of closings, and may be the number of occurrences of various negative events. For example, the information processing apparatus 100 estimates the number of closed stores using social situation information indicating the social economic situation, and determines factoring conditions based on the estimated number of closed stores.

This point will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 4 shows an example of processing based on social conditions. FIG. 4 illustrates an example of processing for changing the threshold value used for grouping based on the number of store closings estimated based on social conditions. Specifically, in FIG. 4, processing for changing the threshold used in FIG. 2 based on the number of store closings estimated based on social conditions will be described as an example. It should be noted that descriptions of the same points as those described above will be omitted as appropriate.

FIG. 4 shows an example in which the information processing apparatus 100 changes the threshold using a model M31, which is a learning model that outputs a score indicating the number of closed stores corresponding to social conditions. The model M31 is a model used for estimating the number of closed stores, and is a model learned by machine learning. In FIG. 4, a case where the model M31 outputs the number of store closures as a score indicating the number of stores that have closed will be described as an example. It may be a value used for calculation (for example, the ratio of the number of store closings at that time).

Further, the information processing apparatus 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 by itself. For example, when learning the model M31, the information processing apparatus 100 learns the model M31 using learning data LDT31 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT31 includes data in which information about social conditions (also referred to as “social condition information”) is associated with a label indicating the number of store closures corresponding to the social condition (also referred to as “correct information”). included.

The social situation information includes information indicating various social situations, such as information on business conditions (economic conditions). For example, social condition information includes various information indicating economic conditions such as stock prices, unemployment rates, and interest rates. For example, as the correct answer information of the social situation, the number of closed stores at the time corresponding to the social situation is associated. FIG. 4 shows, as an example, the case where the number of closed stores after three months from time X is assigned to social situation information at a certain time (time X) as correct information for each social situation. The information processing apparatus 100 generates a model M31 for estimating the number of store closings half a year from the point corresponding to the social situation. Note that the information processing apparatus 100 estimates the number of closing stores not only in three months but also in a desired future (for example, one month, six months, one year, five years, etc.) corresponding to the social situation. It can generate a model that (predicts).

For example, the information processing apparatus 100 performs learning processing so that the score output by the model M31 approaches the correct 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 apparatus 100 is configured 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. Then, the learning process is performed. Further, for example, when the correct information is "5", the information processing apparatus 100 changes the score output by the model M31 to "5" when the social situation information of the store to which the correct information is assigned is input. Learning processing is performed so as to approach. When a store closes from a commercial transaction site, it becomes impossible to collect the receivables from that store. Therefore, in FIG. Learn the model M31 used to Note that the learning process for the model M31 is the same as the learning process for the model M1 and the like, so detailed description thereof will be omitted. If the information processing apparatus 100 can learn the model M31 so as to output a score corresponding to the correct answer information when the social situation information included in the learning data is input, what kind of method can be used for the model M31? may be generated.

From now on, the information processing shown in FIG. 4 will be described in detail based on the above-described contents. First, the information processing apparatus 100 inputs social situation information SDT11 indicating the social situation at the time of processing (current) to the model M31 (step S31-1). For example, the information processing device 100 inputs 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 is input outputs a score (step S31-2). In the example of FIG. 4, the model M31 to which the social situation information SDT11 is input outputs the store closing number "NW1" as indicated by the score SC31. It is assumed that the closing number NW1 is a specific value (for example, 200) indicating the estimated closing number. Thus, in FIG. 4, the information processing apparatus 100 estimates the number of store closings from the commercial transaction site as the number of uncollectible claims.

Then, the information processing apparatus 100 determines a threshold value based on the estimated number of store closings (step S32). In FIG. 4, the information processing apparatus 100 changes the threshold information TL1 used up to that point to the threshold information TL2. For example, the information processing apparatus 100 lowers the threshold when the estimated store closing number NW1 satisfies a predetermined condition. For example, the information processing apparatus 100 lowers the threshold when the number of closings NW1 is greater than the number of closings NW1 at that point in time (currently) (also referred to as "actual measured value at present"). In FIG. 4, in order to simplify the explanation, a case where the information processing apparatus 100 lowers each threshold value by 0.5 will be described as an example. The threshold value may be changed by increasing or decreasing the threshold value according to the comparison between the (measured value at the present time) and the closing number NW1. In this case, the information processing apparatus 100 may determine the threshold based on a predetermined condition that the store closing number NW1 differs from the current measured value.

For example, the information processing apparatus 100 may determine the threshold value according to the result of comparison between the current actual measurement value and the closing number NW1. For example, the information processing apparatus 100 may lower each threshold according to the difference or ratio between the current actual measurement value and the closing number NW1. For example, when the store closing count NW1 for the current actual measurement value is "0.9", the information processing apparatus 100 may update each threshold by multiplying each threshold by "0.9". For example, when the number NW1 of store closings with respect to the current actual measurement value is "1.05", the information processing apparatus 100 may update each threshold by multiplying each threshold by "1.05". Further, the information processing apparatus 100 may individually change each threshold. For example, the information processing apparatus 100 may lower only the first threshold TH1 according to the difference or ratio between the number of store closings at that time (current) and the number of store closings NW1. Note that the above is merely an example, and the information processing apparatus 100 may change the threshold by performing processing using various information as appropriate.

Then, the information processing apparatus 100 classifies the multiple stores into multiple groups using the changed threshold information TL2 (step S33). Note that the processing after step S33 is the same as the processing after step S12 in FIG. 1 except for each threshold value, so detailed description thereof will be omitted.

In this way, the information processing apparatus 100 changes the threshold value based on the number of store closures estimated based on the economic situation, classifies a plurality of stores into a plurality of groups using the changed threshold value, and classifies the classified groups. determine the terms and conditions for the purchase of receivables. As a result, the information processing apparatus 100 can perform processing using threshold values that are appropriately adjusted according to the economic situation, and can purchase claims. can be done. For example, when factoring future receivables, the future receivables will be purchased, so if the store closes in the near future, it may be difficult to collect the funds. Therefore, the information processing device 100 performs grouping in consideration of the economic situation, and determines an index value such as the number of months to be purchased for each group, thereby reducing the possibility of difficulty in collecting funds. can.

In the above example, the case where the number of store closings is calculated using the model M31, which is a learning model, is shown as an example, but the information processing apparatus 100 calculates the number of store closings without using the learning model. may In this case, the information processing apparatus 100 may calculate the number of store closings on a rule basis, for example. The information processing apparatus 100 may calculate the number of store closings using, for example, rule information that associates conditions with the number of store closings. The information processing apparatus 100 may compare the social situation information with each rule (condition), and if the social situation information satisfies the rule, the number of closings of the rule may be used. Further, the information processing apparatus 100 may determine the conditions regarding the purchase of bonds without grouping. In this case, the information processing apparatus 100 may determine the number of months to be purchased for future claims according to the estimated number of closings (number of occurrences). For example, the information processing apparatus 100 uses a function with the estimated number of closings (number of occurrences) as a variable (explanatory variable) and the number of months to be purchased as an output value (objective variable) to determine the number of months to be purchased for future bonds. may be determined.

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

Note that the information processing apparatus 100 may estimate the number of closings based on prediction information indicating future social conditions (economic conditions), and change the threshold used for grouping based on the estimated number of closings. . In this case, the information processing apparatus 100 may acquire prediction information indicating future social conditions (economic conditions) provided from a predetermined external device, and estimate the number of closings using the acquired prediction information. . Further, the information processing apparatus 100 may estimate the number of store closings based on social conditions (economic conditions), and change the factoring conditions for each group based on the estimated number of store closings. For example, the information processing apparatus 100 may reduce the number of months to be purchased for each group when the estimated number of closings is equal to or greater than a predetermined number. Further, for example, when the estimated number of store closings is less than a predetermined number, the information processing apparatus 100 may increase the number of months to be purchased for each group.

Note that the above-described processing is merely an example, and the information processing apparatus 100 may perform processing using various types of information. For example, the information processing apparatus 100 may determine the conditions for purchasing bonds based on the number of closed stores at that time (current) and the estimated number of closed stores. For example, the information processing apparatus 100 may determine factoring conditions based on the relative number of closings. For example, the information processing apparatus 100 assumes that the number of closed stores at that time (current) and the current number is "1", and if the estimated number of closed stores is "1.2", which is 1.2 times that, factoring The conditions may be reduced by 20%. In this case, if the current number of months to be purchased for one store is "2", the information processing apparatus 100 may reduce the number of months to be purchased for that one store to "1.6".

Further, for example, when the current total number of closed stores is 100 and it is estimated that the number of closed stores will be 200 next year due to a downward trend in economic conditions, the information processing apparatus 100 changes the threshold for grouping. good too. In this case, for example, the information processing apparatus 100 may change the threshold value from "0.6" to "0.5". Accordingly, the information processing apparatus 100 may change the 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 to be purchased.

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

[1-3-4. Processing based on category]
The information processing apparatus 100 may determine the factoring conditions of the store according to the category of products handled by the store. In this case, the information processing device 100 determines the factoring conditions for the receivables of the target store based on the past sales trends of the target store and the past sales trends for each product category handled on the commercial transaction site. good too.

In addition, in FIG. 5, a category (also referred to as "main category") corresponding to the product (main product) mainly handled by the store and a category ("sub-category") corresponding to the product (sub-product) handled by the store other than the main product A case where processing is performed in accordance with (also referred to as) is shown as an example. This point will be described with reference to FIG. FIG. 5 is a diagram illustrating an example of information processing executed by an information processing apparatus; In FIG. 5, processing based on categories will be described as an example. If the factoring conditions for the receivables of the target store are determined according to the category of the product handled by the target store, the information processing device 100 can Factoring terms may be determined.

In the example of FIG. 5, the case where the store SP15 is the target store (target store) for determining the factoring conditions will be described as an example, but the target store is not limited to the store SP15, and can be any store that opens on a commercial transaction site. may It should be noted that descriptions of the same points as those described above will be omitted as appropriate.

FIG. 5 shows an example of the case where the information processing apparatus 100 performs determination processing using a model M41, which is a learning model (model) that outputs a score for estimating sales trends for each category. The model M41 is a category sales model for estimating sales trends of stores corresponding to categories, and is a model learned by machine learning. Although FIG. 5 shows a case where a common model M41 is used for the main category and subcategories, separate models may be used for the main category and subcategories.

Further, the information processing apparatus 100 may acquire the model M41 or the like from a model providing server or the like that provides learning models, or may learn the model M41 or the like by itself. For example, when learning the model M41, the information processing apparatus 100 learns the model M41 using learning data LDT41 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT41 includes information on one category of products handled by one store (category information by store), information on the one category on the commercial transaction site (in-site category information), and one store on the one store. This includes data associated with labels (correct information) that indicate sales trends of categories.

For example, the learning data LDT41 includes store-by-store category information including information indicating sales of products belonging to one category in one store at a certain point in time (point X), and the entire commercial transaction site at a certain point in time (point X). In-site category information including information indicating the sales of products belonging to that one category in the store, and labels (correct information) indicating changes after time point X in the sales of one category in that one store are associated. Contains data. The store-by-store category information may include information indicating changes in sales of products belonging to one category in a store up to a certain point in time (point in time X). For example, the store-by-store category information may include information on multiple sales of products belonging to one category in stores corresponding to multiple points of time up to a certain point of time (point of time X).

The intra-site category information may include information indicating changes in sales of products belonging to one category in the entire commercial transaction site up to a certain point in time (point in time X). For example, the intra-site category information may include information on multiple sales of products belonging to one category in the entire commercial transaction site corresponding to multiple time points up to a certain time point (time point X). In some cases, store-specific category information and in-site category information are collectively referred to as model input information. For example, a value indicating the relationship between sales of one category in one store at time X and time (time Y) after a predetermined period of time has elapsed from time X is associated as correct information.

For example, if the sales of one category in one store at time Y is 1.5 times the sales of one category in one store at time X (i.e., sales increase), the value "1.5" is correct. Associated as information. In this way, if the sales of one category in one store have increased after time point X, a value greater than 1 is associated as correct information. If the sales of one category in one store at time Y is 0.6 times the sales of one category in one store at time X (ie sales decrease), the value "0.6" is correct information be associated. For example, if the sales of one category in one store are decreasing after time X, a value smaller than 1 is associated as correct information. That is, the learning data LDT41 includes, as correct information, information indicating whether one category is in an upward trend or a downward trend from a certain time point (time point X). Note that the above is only an example, and various types of information may be used as the correct answer information. For example, the sales value itself at time Y may be used as the correct answer information. In this case, the model M41 outputs a score that indicates the estimated sales of the category at the target store.

The information processing apparatus 100 performs learning processing so that the score output by the model M41 to which the model input information corresponding to one category of the target store is input approaches the correct information associated with the model input information. For example, when the correct answer information is "1.2" and the model input information to which the correct answer information is assigned is input, the information processing apparatus 100 sets the score output by the model M41 to "1.2". Learning processing is performed so as to approach. Further, for example, when the correct information is "0.8" and the model input information to which the correct information is assigned is input, the information processing apparatus 100 sets the score output by the model M41 to "0.8". ”, the learning process is performed. Note that the learning process for the model M41 is the same as the learning process for the model M1 and the like, so detailed description thereof will be omitted. Further, if the information processing apparatus 100 can learn the model M41 so as to output a score corresponding to the correct answer information when the model input information included in the learning data is input, what kind of method is used for the model M41? may be generated.

Based on the above-described content, the information processing shown in FIG. 5 will be described in detail below. First, the information processing device 100 determines the main category and subcategories of the store SP15. For example, the information processing apparatus 100 refers to the store information of the store SP15 and determines the main category and subcategories of the store SP15. For example, the information processing apparatus 100 may determine the category with the highest sales among the categories handled by the store SP 15 as the main category. For example, the information processing apparatus 100 may determine the category with the largest number of products among the categories handled by the store SP 15 as the main category. Further, the information processing apparatus 100 may determine categories handled by the store SP 15 other than the main category as subcategories.

The determination of the main category and subcategories described above is merely an example, and the information processing apparatus 100 may determine the main category and subcategories using various information as appropriate. The information processing apparatus 100 may determine the category with the next largest sales after the main category among the categories handled by the store SP 15 as the subcategory. Further, the information processing apparatus 100 may determine, as a subcategory, the category with the second largest number of products after the main category among the categories handled by the store SP 15 .

The information processing device 100 may determine the main category and subcategories of the store SP15 using the category information stored in the store owner information storage unit 121 (see FIG. 9). When the main category and subcategories of the store SP15 are designated by the operator of the store SP15, the information processing device 100 determines the main category and subcategories 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 as category #1 and the subcategory is determined as category #2 will be described as an example. Category #1 and category #2 are, for example, specific categories such as foods, beverages, alcoholic beverages, clothes, and cosmetics.

The information processing apparatus 100 inputs the model input information MINF15-1 corresponding to the 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 indicates store-by-store category information including information indicating sales of products belonging to category #1 of the current store SP15, and sales of products belonging to category #1 on the current commercial transaction site as a whole. The model input information MINF15-1 including the in-site category information including the information is input 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 indicated by the score SC31. It should be noted that the main score VL41 is a value (for example, 0.4, 2.5, etc.) indicating the tendency of the trend estimated for the main category (category #1) of the store SP15.

The information processing apparatus 100 also inputs the model input information MINF15-2 corresponding to the category #2, which is the 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 indicates store-by-store category information including information indicating sales of products belonging to category #2 of the current store SP15, and sales of products belonging to category #2 on the current commercial transaction site as a whole. The model input information MINF15-2 including the in-site category information including the information is input to the model M41. The model M41 to which the model input information MINF15-2 is input outputs a score (step S41-4). In the example of FIG. 5, the model M41 to which the model input information MINF15-2 is input outputs a score "VL42" as indicated by the score SC31. The subscore VL42 is assumed to be a value (for example, 0.6, 1.8, etc.) indicating the tendency of the trend estimated for the subcategory (category #2) of the store SP15.

Then, the information processing apparatus 100 determines the maximum purchase amount of future bonds of the store SP 15 based on the trend trend of the product category handled by the store SP 15 (step S42). In FIG. 5, the information processing apparatus 100 determines the number of months to be purchased for future bonds of the store SP15 based on the trend of the category of products handled by the store SP15. For example, the information processing apparatus 100 uses a function ("number of months Calculation function FC2”) is used to determine the number of months to be purchased for the future bond of the store SP15.

For example, the number of months calculation function FC2 uses a first value obtained by multiplying the main score by a first coefficient (first weight) and a second value obtained by multiplying the subscore by a second coefficient (second weight). A function that calculates the number of months. For example, the number-of-months calculation function FC2 outputs the total value of the first value and the second value as the number of months to be purchased. For example, the information processing device 100 determines the value of each weight so that the first weight corresponding to the main category score (main score) is greater than the second weight corresponding to the subcategory score (subscore). may Further, the information processing apparatus 100 may calculate the second value by multiplying the subscore by a value obtained by multiplying the second weight by a predetermined attenuation value (for example, 0.8).

In FIG. 5, the information processing apparatus 100 determines the purchase target of the store SP15 based on the first value obtained by multiplying the main score VL41 of the store SP15 by the first weight and the second value obtained by multiplying the sub-score VL42 of the store SP15 by the second weight. A value VL43 indicating the number of months is calculated. Note that the value VL43 is a specific value (for example, 1.5, 3, etc.) indicating the number of months to be purchased.

Here, the information processing apparatus 100 may determine the weighting of categories using various information. The information processing apparatus 100 may determine the value of the first weight and the value of the second weight using various information. For example, the information processing apparatus 100 may weight by the product score of the category, or may weight by the sales of the category. For example, the information processing apparatus 100 may increase the weight value as the number of products in the category increases, or increase the weight value as the sales in the category increase. For example, the information processing apparatus 100 may increase the value of the first weight as the sales of the main category increase. For example, the information processing apparatus 100 may increase the value of the second weight as the number of products in the subcategory increases.

Then, the information processing device 100 determines the maximum purchase amount of future bonds of the store SP15 based on the determined number of months to be purchased and the sales information of the store SP15. Detailed description is omitted. The information processing device 100 determines the upper limit purchase price of the store SP15 to be "PL41", as indicated by the upper limit purchase price information PL1 in FIG. For example, the information processing apparatus 100 uses the calculation function FC1 (see FIG. 2) to determine the purchase upper limit of the store SP15 to be "PL41 (=SL15×VL43)" when the sales of the store SP15 is the value SL15. .

Then, the information processing apparatus 100 provides information using the determined information (step S43). Since the information provision is the same as the processing described with reference to FIG. 2, detailed description will be omitted. may be provided. In this case, the information processing device 100 may transmit information indicating the number of months to be purchased or the maximum purchase amount of the store SP 15 to the store device 20 used by the business operator of the store SP 15 .

In this way, the information processing apparatus 100 determines the conditions regarding the purchase of the bond using the category information for the target store. As a result, the information processing apparatus 100 can purchase claims according to the category of products handled by the target store, and can provide an appropriate service related to the purchase of claims. For example, when factoring future receivables, the future receivables will be purchased, so if the store closes in the near future, it may be difficult to collect the funds. Therefore, the information processing apparatus 100 can reduce the possibility of difficulty in collecting funds by determining an index value such as the number of months to be purchased according to the trend of the category of products handled by the target store.

In the example described above, the information processing apparatus 100 calculates scores indicating upward trends and downward trends for each category of products handled by the store, and determines factoring conditions. Note that the processing described above is merely an example, and the information processing apparatus 100 may determine factoring conditions using various types of information. For example, the information processing apparatus 100 may increase the purchase upper limit if the main category score is high. Further, the information processing apparatus 100 may give a greater weight to a category having a larger number of products. In addition, the information processing apparatus 100 may give a higher weighting to categories with higher sales. As described above, the main category and the like may be registered in advance for each store. Further, when the target store handles a category that is popular as a whole, the information processing apparatus 100 may determine the factoring condition of the target store based on the share (occupancy rate) in that category.

Further, the information processing apparatus 100 may change the weighting depending on whether the category that handles the largest number of products in the target store is the main category. For example, the information processing apparatus 100 may determine the factoring condition for the target store depending on whether a predetermined condition is satisfied, such as the tendency of a specific category to rise or fall more prominently than usual. Further, for example, even if the sales of the store are on a downward trend, the information processing apparatus 100 may detect that the store deals with popular categories (for example, corona-related goods, etc.) at that time. Factoring conditions may be improved.

[1-3-5. Processing Based on Models of Multiple Viewpoints]
Note that the information processing apparatus 100 may perform processing based on a model from a plurality of viewpoints instead of a model from one viewpoint. In this case, the information processing device 100 includes a store closure model (store closure prediction model) for predicting that the store will leave the commercial transaction site, and a future possibility model (future possibility prediction model) for predicting the future potential of the store. Using these two models, factoring conditions such as the maximum number of months for purchase of future receivables are determined.

In FIG. 6, the closing of the store from the commercial transaction site will be described as an example of a negative event. . For example, the information processing apparatus 100 calculates the probability (possibility) of closing a store for each period using models from two different viewpoints, a model M1 that is a store closing model and a model M2 that is a future model. A number of models that output indicative scores are used to determine the conditions for the purchase of the store's bonds.

This point will be described with reference to FIG. FIG. 6 is a diagram illustrating an example of information processing executed by an information processing apparatus; FIG. 6 illustrates an example of processing based on a model of multiple viewpoints. In the example of FIG. 5, the case where the store SP12 is the target store (target store) for determining the factoring conditions will be described as an example, but the target store is not limited to the store SP12, and can be any store that opens on the commercial transaction site. may It should be noted that descriptions of the same points as those described above will be omitted as appropriate. For example, the model M1 used in FIG. 6 is the same as the model M1 in FIG. 2, so the explanation of the learning process and the like is omitted.

In FIG. 6, the information processing apparatus 100 determines using a model M2, which is a learning model (model) that outputs a score (also referred to as a "future score") indicating the future possibility of sales of a store opening on a commercial transaction site. An example of processing is shown. The model M2 is a future model and is a model learned by machine learning.

Further, the information processing apparatus 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 by itself. For example, when learning the model M2, the information processing apparatus 100 learns the model M2 using learning data LDT2 stored in the model information storage unit 122 (see FIG. 10). For example, the learning data LDT2 contains information about a store (store information) and a label indicating how the sales of the store changed after the latest information in the store information was acquired (acquisition point). (Correct answer information) and data associated with each other are included.

For example, as the correct information for a store, if the store's sales increase by 1.5 times (i.e., sales increase) after a predetermined period of time (for example, one month) from the time of acquisition, "1.5" is assigned. If the sales increase by 0.8 times (that is, the sales decrease) after the elapse of a predetermined period from the store acquisition time, "0.8" is assigned. The information processing apparatus 100 performs learning processing so that the score output by the model M2 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 "1.8" and the store information of the store to which the correct answer information is assigned is input, the information processing apparatus 100 outputs a score of "1.8" from the model M2. The learning process is performed so as to approach Further, for example, when the correct information is "0.2", the information processing apparatus 100 determines that the score output by the model M2 is "0.2" when the store information of the store to which the correct information is assigned is input. 2”, the learning process is performed. In this case, a model M2 is generated that outputs a score greater than 1 if the store is highly prospective in terms of sales and outputs a score less than 1 if the store is leading in terms of sales. . Note that the learning process for the model M2 is the same as the learning process for the model M1, so detailed description will be omitted.

From now on, the information processing shown in FIG. 6 will be described in detail based on the above-described contents. First, in FIG. 6, the information processing apparatus 100 calculates a closing score and a future score for the store SP12, which is the target store. The information processing apparatus 100 inputs the store information SINF12 of the store SP12 at the time of processing (current) to the 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 the score "VL51" as indicated by the score SC51. It is assumed that the closing score VL51 is a value (for example, 0.1, 0.75, etc.) indicating the probability (possibility) that the store SP12 will withdraw from the commercial transaction site.

The information processing apparatus 100 also inputs the 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 is input outputs a score (step S51-4). In the example of FIG. 6, the model M2 to which the store information SINF12 is input outputs a score "VL52" as indicated by the score SC52. It is assumed that the future score VL52 is a value (for example, 0.6, 1.5, etc.) indicating the future regarding sales of the store SP12. In order to simplify the explanation, FIG. 6 shows the case where the input information of the model M1 and the model M2 is the same, but the input information of the model M1 and the model M2 may be different.

Then, the information processing apparatus 100 determines the maximum purchase amount of future bonds of the store SP12 based on the closing score VL51 and the future potential score VL52 of the store SP12 (step S52). In FIG. 6, the information processing apparatus 100 determines the number of months for purchase of future bonds of the store SP12 based on the closing score VL51 and the future potential score VL52 of the store SP12. For example, the information processing device 100 uses a function (also referred to as “number of months calculation function FC3”) that uses the closing score and future score as variables (explanatory variables) and the number of months to be purchased as an output value (objective variable). to determine the number of months to be purchased for the future bond of the store SP12.

For example, the number-of-months calculation function FC3 is a first value obtained by multiplying the reciprocal of the closing score by a first coefficient (first weight), and a second value obtained by multiplying the future score by a second coefficient (second weight). It is a function that calculates the number of months to be purchased based on the value. For example, the number-of-months calculation function FC3 outputs the total value of the first value and the second value as the number of months to be purchased.

In FIG. 6, the information processing apparatus 100 obtains a first value obtained by multiplying the reciprocal of the closing score VL51 of the store SP12 by a first weight, and a second value obtained by multiplying the future potential score VL52 of the store SP12 by a second weight. A value VL53 indicating the number of months for purchase of the store SP12 is calculated. It is assumed that the value VL53 is a specific value (for example, 1.5, 3, etc.) indicating the number of months to be purchased.

Note that the value of the first weight and the value of the second weight may be set as appropriate. For example, the value of the first weight may be set large if the risk of closing the store is emphasized. Also, for example, when the future potential of the store is emphasized, the value of the second weight may be set large.

Then, the information processing device 100 determines the maximum purchase amount of future bonds of the store SP12 based on the determined number of months to be purchased and the sales information of the store SP12. Detailed description is omitted. The information processing apparatus 100 determines the upper purchase limit of the store SP12 to be "PL51" as indicated by the purchase upper limit information PL2 in FIG. For example, the information processing apparatus 100 uses the calculation function FC1 (see FIG. 2) to determine the purchase upper limit of the store SP12 to be "PL51 (=SL12×VL53)" when the sales of the store SP12 is the value SL12. .

Then, the information processing apparatus 100 provides information using the determined information (step S53). Since the information provision is the same as the processing described with reference to FIG. 2, a detailed description will be omitted. may be provided. In this case, the information processing device 100 may transmit information indicating the number of months to be purchased or the maximum purchase price of the store SP 12 to the store device 20 used by the business operator of the store SP 12 .

In this way, the information processing apparatus 100 determines the conditions for purchasing the bond of the target store based on a plurality of viewpoints. As a result, the information processing apparatus 100 can comprehensively consider a plurality of points of view when purchasing the bond of the target store, so that an appropriate service regarding the purchase of the bond can be provided. For example, when factoring future receivables, the future receivables will be purchased, so if the store closes in the near future, it may be difficult to collect the funds. Therefore, the information processing apparatus 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 considers the closing risk and future potential of the target store. can.

As described above, the information processing apparatus 100 can improve the accuracy of processing while suppressing learning data from becoming enormous by dividing the closing model and the future model. Note that the above-described processing is merely an example, and the information processing apparatus 100 may perform processing using various types of information. For example, the exit model may be a model trained to input past store data and output whether or not the customer exited the store within a predetermined period of time. Further, the potential model is not limited to whether or not sales will increase in the future, and may be a model that predicts the number of visitors, the number of products, the number of store evaluations, and the like. For example, the information processing apparatus 100 may determine the factoring conditions of the store depending on whether or not the handling ratio of trendy (buzzy) products is high.

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

For example, the information processing apparatus 100 calculates a closing score for each period, determines a period in which the closing score exceeds a threshold as a collection period, and determines a lower limit so that the entire amount can be collected within the determined collection period. In this case, the information processing apparatus 100 determines the recovery period using a plurality of models each corresponding to a different period as shown in FIG. This point will be described with reference to FIG. In addition, below, store SP12 is a target store, and the case where store SP12 performs factoring regarding a future claim is demonstrated as an example. In addition, the description of the points similar to those of the above-described processing will be omitted as appropriate.

For example, the information processing apparatus 100 determines the mode of collection of the accounts receivable corresponding to the future receivables of the store SP12 based on the store closing score indicating the closing probability of the store SP12 for each period. For example, the information processing apparatus 100 determines the collection period of the accounts receivable corresponding to future claims of the store SP 12 using the threshold value related to the store closing time estimation stored in the threshold information storage unit 123 (see FIG. 11).

The information processing apparatus 100 compares the closing score output by each model with the threshold value TH11, and based on the comparison result, determines the collection period for the accounts receivable corresponding to the future receivables of the target store. For example, the information processing apparatus 100 determines the period corresponding to the learning model with the shortest period among the learning models for which the closing score is equal to or greater than the threshold TH11 as the collection period for the accounts receivable corresponding to the future receivables of the target store. . The information processing apparatus 100 compares the closing score output by the models M11, M12, M13, M14, etc. with the value of the threshold TH11 "0.5" to determine the collection period of the accounts receivable corresponding to the future receivables of the store SP12. decide. Since the store exit score "0.52" output by the model M13 that predicts the probability (possibility) of closing the store within three months is equal to or greater than the threshold TH11, the information processing apparatus 100 corresponds to the future claim of the store SP12. Set the collection period for accounts receivable to “three months”.

Note that the above-described processing is merely an example, and the information processing apparatus 100 may use various types of information as appropriate to determine the collection period for accounts receivable corresponding to future claims. For example, the information processing apparatus 100 determines a period shorter than the period corresponding to the learning model with the shortest period among the learning models for which the closing score is equal to or greater than the threshold TH11 as the collection period for the accounts receivable corresponding to future claims. You may In this case, the information processing apparatus 100 sets a period (for example, two months) shorter than the period (three months) corresponding to the model M13 in which the closing score is equal to or higher than the threshold TH11 to the accounts receivable corresponding to the future receivables of the store SP12. may be determined during the collection period.

Then, the information processing apparatus 100 determines the collection rate of the accounts receivable corresponding to the future receivables of the store SP12 according to the determined collection period. For example, the information processing apparatus 100 determines the collection rate so that the entire amount can be collected within the determined collection period. For example, when the collection period for the accounts receivable corresponding to future receivables of the store SP 12 is determined to be three months, the information processing apparatus 100 sets the monthly payment rate (collection rate) of the store SP 12 so that the entire amount can be collected within three months. is determined to be "33.4%".

Then, the information processing apparatus 100 notifies the target store of the determined information. For example, the information processing device 100 informs the store device 20 used by the operator of the store SP 12 that the collection period is "three months" and the monthly payment rate (collection rate) is "33.4%." Send information indicating

In this way, the information processing apparatus 100 predicts the closing score of the target store for each period, and determines the collection mode of the accounts receivable corresponding to the future credit of the target store according to the predicted period. As a result, the information processing apparatus 100 can determine a collection mode that takes into account the risk of closing of the target store, so that it is possible to provide an appropriate service regarding the purchase of the credit. For example, when factoring future receivables, the future receivables will be purchased, so if the store closes in the near future, it may be difficult to collect the funds. Therefore, the information processing device 100 predicts a period during which the target store is likely to close, and determines the collection period and collection rate according to that period, thereby reducing the possibility of difficulty in collecting funds. can be made

Through the above-described processing, the information processing apparatus 100 can determine the lower limit of the collection rate so that the repair period does not extend even when the store side can set the collection rate. As described above, the information processing apparatus 100 determines the lower limit of the collection rate of the claim. For example, the information processing apparatus 100 may determine the collection mode so that 10% of the factored amount is collected every month when the probability of closing the store is maximized after ten months. For example, the information processing apparatus 100 may determine the recovery rate so that the full amount can be recovered in nine months when the probability of closing the store is maximized after nine months.

Note that the information processing apparatus 100 may update the collection mode of the accounts receivable corresponding to the future claim of the target store when the collection of the accounts receivable corresponding to the future claim of the target store satisfies a predetermined condition. For example, when the collection of the accounts receivable corresponding to the future credit of the target store is delayed, the information processing device 100 updates the closing probability of the target store, and calculates the future closing probability of the target store based on the updated closing probability of the target store. Update the collection mode of accounts receivable corresponding to receivables. For example, when the period over which the threshold value is exceeded has changed from five months to four months, the information processing apparatus 100 may shorten the collection period by one month and determine the collection rate for that period.

In this way, when the store delays payment, the information processing apparatus 100 may extend the collection period or calculate the collection rate again. Further, the information processing apparatus 100 may calculate the recovery rate again when factoring is performed again.

[1-3-7. Provision of services to stores]
An example of service provision to the store will now be described. The information processing apparatus 100 provides services to the store in step S5 shown in FIG. The information processing apparatus 100 determines a store to which factoring is proposed (also referred to as a “proposal destination store”). For example, the information processing apparatus 100 determines, from among the plurality of stores, the proposed store to which the bond purchase is proposed, based on the store information regarding each of the plurality of stores that open on the commercial transaction site.

Then, the information processing apparatus 100 provides the determined proposal destination store with information proposing the purchase of the bond. For example, the information processing apparatus 100 determines the number of months to be purchased and the maximum purchase amount of the proposed store by the determination processing shown in FIGS. and information indicating the purchase limit amount to the proposed store. For example, the information processing apparatus 100 transmits information indicating the number of months to be purchased or the maximum purchase amount of the proposed store determined by the determination processing shown in FIGS. 20.

Here, the information processing apparatus 100 may determine the proposal destination store using various information. For example, the information processing apparatus 100 may determine the suggested store using store information including information indicating whether the store is advertising. For example, the information processing apparatus 100 may determine the suggested store depending on whether an advertisement is being displayed. For example, the information processing apparatus 100 determines a store that does not advertise as the proposed store. As a result, the information processing apparatus 100 can propose factoring to a store that does not currently advertise but whose sales are expected to increase if it does.

Further, for example, the information processing apparatus 100 may determine the suggested store by using store information including information indicating products handled by the store. For example, the information processing apparatus 100 may determine the suggested store according to the products handled by the store. For example, the information processing apparatus 100 determines, as the proposal destination store, a store whose number of products handled is less than a predetermined threshold. As a result, the information processing apparatus 100 can propose factoring to a store that has a small number of product items and is expected to increase sales by increasing the number of product items.

In addition, the information processing apparatus 100 learns the characteristics of the relationship between the store that opens on the commercial transaction site and the change in sales when the store takes measures to increase sales (also referred to as "execution measures"). A model (also referred to as a "policy effect prediction model") may be used to determine the proposed store. In this case, the information processing apparatus 100 determines a store whose score output by the proposal destination determination model is equal to or greater than a predetermined threshold as the proposal destination store. In this case, the information processing apparatus 100 proposes the execution measures together with the factoring conditions to the proposal destination store. Further, the information processing apparatus 100 may propose a factoring condition to the proposal destination store on the condition that the execution measure is executed.

For example, the measure effect prediction model is a model that inputs store information and measure information indicating the measures taken by the store, and outputs a value that indicates the increase or decrease in sales when the store implements the measures. is. For example, the information processing apparatus 100 stores model input information including store information of a store and measure information indicating measures taken by the store, and a value (correct answer information) indicating an increase or decrease in sales corresponding to the model input information. A policy effect prediction model is learned using the associated learning data. The information processing apparatus 100 may acquire the policy effect prediction model from a model providing server or the like that provides learning models.

For example, the information processing apparatus 100 may determine a factoring proposal destination using a model (policy effect prediction model) that has learned changes (increase or decrease) in sales when a measure such as an advertisement is implemented. The information processing apparatus 100 may determine a store as a proposal destination store when the policy effect prediction model outputs a score indicating that sales will increase when a policy such as an advertisement is implemented for a certain store.

As described above, the information processing apparatus 100 determines the store to which factoring is proposed. Note that the above-described processing is merely an example, and the information processing apparatus 100 may perform processing using various types of information as appropriate. For example, the information processing apparatus 100 may propose factoring to the store when there is a store that can be expanded by changing the place where the advertisement is displayed. In addition, for example, if a store that handles products in a category with future potential and can grow by changing the place where the advertisement is displayed, the information processing apparatus 100 may propose factoring to the store. In addition, the information processing apparatus 100 may propose information indicating a user (target user) to whom advertisements are to be provided, and factoring conditions when advertising to the target users.

[2. Configuration of Information Processing Device]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described using FIG. FIG. 8 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 8, the information processing apparatus 100 has a communication section 110, a storage section 120, and a control section . The information processing apparatus 100 includes an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from an administrator of the information processing apparatus 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network by wire or wirelessly, and transmits and receives information to and from the user terminal 10 , the store device 20 and the web server 30 .

(storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) 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 includes a store owner information storage unit 121, a model information storage unit 122, a threshold information storage unit 123, a group information storage unit 124, and a social situation information storage unit. 125 , a commercial transaction site information storage unit 126 and a factoring information storage unit 127 . In addition, the storage unit 120 may store various types of information, not limited to the above.

(Store owner information storage unit 121)
The shop owner information storage unit 121 according to the embodiment stores information about businesses that open shops on commercial transaction sites. For example, the store owner information storage unit 121 stores various types of information related to a store opened by a business operator (store owner) on a commercial transaction site. For example, the information stored in the store owner information storage unit 121 is obtained from the web server 30 via the communication network. 9 is a diagram illustrating an example of a store owner information storage unit according to the embodiment; FIG. The store owner information storage unit 121 shown in FIG. 9 stores items such as "store owner", "store", "store opening date", "store closing date", "store closing reason", "store information", and "score information". have. "Store information" includes items such as "business information", "merchandise information", "category information", "sales information", and "evaluation information". The "score information" includes items such as "store closing" and "future potential".

"Store owner" indicates information (business operator ID, name, etc.) that identifies a business operator that opens a store on the commercial transaction site. For example, "store owner" indicates information identifying a business that has opened a store in the commercial transaction site in the past or is currently opening a store. "Store" indicates a store (store) opened by the business operator on the commercial transaction site.

Note that although the store owner information storage unit 121 shown in FIG. 9 shows an example in which each business operator opens one store on the commercial transaction site, each business operator may open a plurality of stores on the commercial transaction site. In this case, the business operator can use different stores according to the category of products handled and the type of business. For example, a process of closing (losing the right to open a store) may be performed for other stores of a company having a store that has been closed due to forced closure or the like.

"Store opening date" indicates the date of opening the store on the commercial transaction site. "Date of exit" indicates the date of exit from the commercial transaction site. For business operators (or stores) that have not closed at this time, the closing date item is blank ("-" (hyphen)).

"Store information" includes various information about the store. The "store information" includes information (registration data) registered by the store operator, and history (actual data) accumulated by the operation of the store. For example, “store information” includes information used by the information processing apparatus 100 for model learning.

"Business information" indicates information about business. "Business information" includes various types of business-related information such as information indicating business forms such as corporations or sole proprietors, information about business funds such as capital, information indicating the type of store, and the number of years the store has been in business. Also, the "business information" may include information about the business. For example, the "business information" may include attribute information of the business operator. Also, the "business information" may include financial information indicating the financial status of the business. It should be noted that the above is merely an example, and the "business information" may include various information related to business. In the example of FIG. 9, business information corresponding to the store is stored, although indicated by an abstract code such as "business information #1".

"Product information" indicates information related to products traded at the store. "Product information" includes information that identifies the product (JAN code or product ID, etc.), product name, product image, product description, product price, product inventory, product category, and various other information related to the product. Contains information. Note that the above is only an example, and the "merchandise information" may include various information about the merchandise. In the example of FIG. 9, the item information corresponding to the store is stored, although indicated by an abstract code such as "merchandise information #1".

"Category information" indicates information about the category of products traded in the store. "Category information" includes information indicating the category of products traded at the store. The "category information" includes information indicating the main category, which is the category of products that the store mainly trades, and the subcategory, which is the category of products that the store trades in other than the main category.

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

"Sales information" indicates information on store sales. "Sales information" includes information indicating sales at the store. The "sales information" includes information indicating the number of items sold at the store and information indicating the sales amount of the item at the store. For example, "sales information" includes information indicating sales for each period such as one day, one week, and one month. The “sales information” may include various information regarding sales, such as information indicating sales for each product traded at the store, information indicating sales for each category, and the like.

The "sales information" may include information such as the number of sales and the amount of sales for each product. "Sales information" may include various information related to the number of sales and the amount of sales, such as the number of products sold and the amount of sales, the ratio of the number of sales to the number of products handled, and the period for counting the number of sales and the amount. good. Note that the above is only an example, and the "sales information" may include various information regarding sales. In the example of FIG. 9, sales information corresponding to the store is stored, although indicated by an abstract code such as "sales information #1".

"Evaluation information" indicates information on evaluations of the business operator, the store opened by the business operator, and the products traded at the store. "Evaluation information" includes information indicating evaluations from users. For example, the "evaluation information" includes the number of daily accesses (page views) to the page corresponding to the store on the commercial transaction site, the number of store reviews indicating the number of reviews posted by users to the store, and the number of reviews posted by users. It includes information such as the store rating that the store was rated in the reviews that were given. The number of page views may include the number of page views not only for one day but also for a predetermined period (one week, etc.). For example, the number of store reviews may be the daily average number of store reviews in the store.

For example, the store score may be five grades from the lowest point "1" to the highest point "5". Note that the store score may be an average score of reviews posted by users until the store closes. Note that the number of store reviews and the store rating may be stored as an average of the number or rating accumulated over a predetermined period (for example, one week), or may be stored as an accumulated number up to the present time. Information aggregated in various ways may be stored, such as the cumulative number divided by the age of the store. For example, the "evaluation information" may include information indicating the ratio of the number of reviews posted to page views.

For example, the "evaluation information" includes information such as the number of product reviews indicating the number of reviews posted on the product, and the product rating indicating the rating of reviews posted by users on the product. For example, the product rating may be five grades from the lowest point "1" to the highest point "5". Note that, for example, the product rating may be an average score of reviews posted by users until the product is sold in the store. Note that the above is merely an example, and the "evaluation information" may include various information regarding evaluation. In the example of FIG. 9, an abstract code such as "evaluation information #1" is used, but the evaluation information corresponding to the store is stored.

"Score information" indicates score information for the store. The “score information” includes various information estimated by the information processing apparatus 100 . For example, "score information" stores the score output by the model. Note that, as shown in FIG. 9, for stores that are not subject to score calculation, such as stores that have already closed, the score information items are blank ("-" (hyphen)).

"Exit" indicates the probability (possibility) that the store will exit from the commercial transaction site. Store closure score indicating the probability (possibility) of closure of the store is stored in "store closure". For example, the "exit" stores the score (exit score) output by the exit model (for example, model M1). In the example of FIG. 9, an abstract code such as "store closing score #1" is used, but a specific value (numerical value) such as "0.7" is stored.

"Future Potential" indicates the future potential of the store. "future potential" stores a future potential score indicating the future potential of the store. For example, "future potential" stores a score (future score) output by a potential model (for example, model M2). In the example of FIG. 9, an abstract code such as "future score #1" is used, but specific values (numerical values) such as "0.5" and "10" are stored.

Note that the shop owner information storage unit 121 may store various types of information, not limited to the above, depending on the purpose. For example, the store owner information storage unit 121 may store information indicating the reason for closing the store. For example, the reason for leaving the store is used for distinguishing correct information in the model generation process described later. For example, the store owner information storage unit 121 stores information such as forced closure indicating that the store was forced to leave the commercial transaction site, or closed store indicating that the store was voluntarily closed by the business operator. It may be stored as information indicating the store reason.

(Model information storage unit 122)
The model information storage unit 122 according to the embodiment stores information about models. For example, the model information storage unit 122 stores information (model data) of a learned model (model) learned (generated) by the learning process. The model information storage unit 122 stores data used for learning (learning data) in association with a learned model (model). 10 is a diagram illustrating an example of a model information storage unit according to the embodiment; FIG. In the example shown in FIG. 10, the model information storage unit 122 includes items such as "model ID", "usage", "model data", and "learning data". In the example of FIG. 10, the model information storage unit 122 stores data used for learning (learning data) in association with a learned model (model).

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

“Learning data” indicates data used for learning of a trained model (model). "Learning data" stores information indicating a data set used for learning the corresponding model. For example, "learning data" is stored as learning data (also referred to as "learning data") by associating data (input information) with correct information (output information) corresponding to the data. FIG. 10 shows an example in which conceptual information such as "LDT1" is stored in "learning data", but in reality, data (input information) and correct answer information (output information) corresponding to that data are stored. It contains various information about the data used to train the model.

In FIG. 10, the model (model M1) identified by the model ID "M1" indicates that the application is "exit". That is, the model M1 is a model that outputs information (score) indicating the probability (possibility) that the store corresponding to the input data will withdraw from the commercial transaction site. It also indicates that the model data of the model M1 is the model data MDT1. It also indicates that the learning data used for learning the model M1 is the learning data LDT1.

Also, the model (model M2) identified by the model ID "M2" indicates that the application is "future potential". That is, the model M2 is a model that outputs information (score) indicating the future potential of the store corresponding to the input data. For example, the model M2 outputs information (score) for estimating changes in store sales corresponding to the input data. The model data of model M2 is model data MDT2. It also indicates that the learning data used for learning the model M2 is the learning data LDT2.

The model (model M11) identified by the model ID "M11" indicates that the application is "store closed in January". That is, the model M11 is a model that outputs information (score) indicating the probability (possibility) that the store corresponding to the input data will exit the commercial transaction site within one month. It also indicates that the model data of the model M11 is the model data MDT11. It also indicates that the learning data used for learning the model M11 is the learning data LDT11.

The model (model M12) identified by the model ID "M12" indicates that the application is "retirement store in February". That is, the model M12 is a model that outputs information (score) indicating the probability (possibility) that the store corresponding to the input data will exit the commercial transaction site within two months. Also, the model data of the model M12 indicates that it is the model data MDT12. It also indicates that the learning data used for learning the model M12 is the learning data LDT12.

The model (model M13) identified by the model ID "M13" indicates that the application is "retirement store in March". That is, the model M13 is a model that outputs information (score) indicating the probability (possibility) that the store corresponding to the input data will exit the commercial transaction site within three months. Also, the model data of the model M13 indicates that it is the model data MDT13. It also indicates that the learning data used for learning the model M13 is the learning data LDT13.

Although FIG. 10 shows models up to model M13, the model information storage unit 122 stores models for estimating (predicting) the probability of store closures corresponding to various periods, such as model M14 for predicting store closures in April. You can remember.

The model (model M31) identified by the model ID "M31" indicates that the usage is "number of store closings". In other words, the model M31 is a model that outputs information (score) indicating the number of stores closing from the commercial transaction site (number of closings). Also, the model data of the model M31 is model data MDT31. It also indicates that the learning data used for learning the model M31 is the learning data LDT31.

Note that the model M31 is merely an example, and the model information storage unit 122 may store not only the model M31 used for estimating the number of store exits, but also models for estimating (predicting) the number of occurrences of various negative actions. .

The model (model M41) identified by the model ID "M41" indicates that the application is "category sales". In other words, the model M41 is a model that outputs information (score) indicating the sales at the commercial transaction site for the product of the category corresponding to the input data. Also, it indicates that the model data of the model M41 is the model data MDT41. It also indicates that the learning data used for learning the model M41 is the learning data LDT41. When a model is learned for each category, the model information storage unit 122 may store the model for each category in association with the category.

Note that the model information storage unit 122 may store various types of information, not limited to the above, depending on the purpose.

(Threshold information storage unit 123)
The threshold information storage unit 123 according to the embodiment stores various information regarding thresholds. 11 is a diagram illustrating an example of a threshold information storage unit according to the embodiment; FIG. The threshold information storage unit 123 shown in FIG. 11 includes items such as "threshold", "value", and "usage".

"Threshold" indicates information for identifying a threshold. "Value" indicates a specific numerical value (value) of the corresponding threshold. "Application" indicates the application for which the corresponding threshold is used.

The example of FIG. 11 indicates that the value of the threshold (threshold TH1) identified by the threshold "TH1" is "0.9". The use of the threshold TH1 indicates grouping (classification). That is, the threshold TH1 indicates that it is the first threshold used for grouping (classification) of stores. For example, threshold TH1 is the first threshold used to sort the first group of stores.

The value of the threshold (threshold TH2) identified by the threshold "TH2" indicates that it is "0.8". The purpose of the threshold TH2 is grouping (classification). That is, the threshold TH2 indicates that it is the second threshold used for grouping (classification) of stores. For example, threshold TH2 is the second threshold used to sort the second group of stores.

The value of the threshold (threshold TH11) identified by the threshold "TH11" indicates "VL11". The purpose of the threshold TH11 is to estimate the closing time of the store. That is, the threshold TH11 indicates that it is a threshold used for estimating when the store will leave the commercial transaction site. In the example of FIG. 11, abstract codes such as "VL11" are used, but each threshold value is a specific numerical value according to the application.

The value of the threshold (threshold TH21) identified by the threshold "TH21" indicates "VL21". The purpose of the threshold TH21 is to determine the proposal destination. That is, the threshold TH21 indicates that it is a threshold used for determining which store to propose.

It should be noted that the threshold information storage unit 123 may store various types of information, not limited to the above, depending on the purpose.

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

"Group ID" indicates identification information for identifying a group. "Group information" indicates group information in the corresponding group. For example, "group information" indicates group information including information such as an 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'. be.

"Member" indicates a member of a group. For example, "member" stores information (store ID, etc.) that identifies members (stores) belonging to the group.

FIG. 12 shows that the group information of the group (first group) identified by the group ID "GP1" is group information SM1. FIG. 12 shows 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 the group GP1, which is the first group. Stores SP2, SP12, etc. belong to group GP1 as members.

Note that the group information storage unit 124 may store various types of information, not limited to the above, depending on the purpose.

(Social situation information storage unit 125)
The social situation information storage unit 125 according to the embodiment stores various information about social situations. In the example of FIG. 13, it stores social situation information related to business conditions. 13 is a diagram illustrating an example of a social situation information storage unit according to the embodiment; FIG. The social situation information storage unit 125 shown in FIG. 13 includes items such as "social situation ID", "time point", and "social situation information".

"Social Situation ID" indicates identification information for identifying a social situation (object). Character information or the like for identifying the social situation corresponding to the social situation ID may be stored in association with each social situation ID. "Time point" indicates the time (time point) when the corresponding social situation was present. For example, "point of time" indicates the time (point of time) 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 point #1", but information indicating the corresponding period such as "19XY year Z month ..." in parentheses is included. good too.

"Social situation information" indicates information about the social situation identified by the social situation ID. In the example of FIG. 13, the social situation information is indicated by an abstract code such as "SDT1", but each social situation information is related to the economy (economic situation) at the time corresponding to the social situation identified by the social situation ID. Information indicating various social conditions such as information is included. For example, social condition information includes various information indicating economic conditions such as stock prices, unemployment rates, and interest rates.

The example of FIG. 13 indicates that the social situation identified by the social situation ID "SC1" is the social situation corresponding to time #1. The social situation information of the social situation identified by the social situation ID "SC1" is social situation information SDT1.

It should be noted that the social situation information storage unit 125 may store various types of information, not limited to the above, depending on the purpose.

(Commercial transaction site information storage unit 126)
The commercial transaction site information storage unit 126 according to the embodiment stores various information regarding commercial transaction sites. For example, the commercial transaction site information storage unit 126 stores statistical information regarding the commercial transaction site, such as overall sales at the commercial transaction site. 14 is a diagram illustrating an example of a commercial transaction site information storage unit according to the embodiment; FIG. The commercial transaction site information storage unit 126 shown in FIG. 14 includes items such as "category" and "sales information by category". In the example of FIG. 14, the case of storing sales information for each category is shown as an example, but the commercial transaction site information storage unit 126 may store various information other than sales information for each category.

"Category" indicates identification information for identifying the category. FIG. 14 shows an example in which conceptual information such as "category #1" is stored in "category". Information is stored.

"Category-specific sales information" indicates sales on the commercial transaction site of products belonging to the corresponding category. FIG. 14 shows an example in which conceptual information such as "category sales #1" is stored in "category-specific sales information", but actually information indicating the sales of the corresponding category is stored. Note that the sales information by category is not limited to category sales, and may include various types of information related to category sales, such as the number of categories sold.

FIG. 14 shows that the sales of category #1 are category sales #1. For example, the sales of products belonging to category #1 on a commercial transaction site are the values indicated by category sales #1. Sales of category #2 are category sales #2, and sales of category #3 are category sales #3.

Note that the commercial transaction site information storage unit 126 may store various types of information, not limited to the above, depending on the purpose.

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

"Store" indicates identification information for identifying the store. "Factoring information" indicates information (factoring information) about factoring of the corresponding store. For example, "factoring information" indicates whether 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.

A store whose "factoring information" is factoring information #* (* is an arbitrary number) indicates that the store is currently using factoring. FIG. 15 shows an example where conceptual information such as "factoring information #12" is stored in "factoring information", but in reality, the amount of factoring and its collection mode (collection period, collection interval, etc.), etc. Specific information about factoring is stored.

FIG. 15 shows that the store SP1 does not use factoring. Also, the store SP12 indicates that factoring is being used and the factoring information is factoring information #12.

It should be noted that the factoring information storage unit 127 may store various types of information, not limited to the above, depending on the purpose.

(control unit 130)
Returning to the description of FIG. 8, the control unit 130 is a controller, and is stored in a storage device inside the information processing apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of an information processing program) are executed by using the RAM as a work area. Also, the control unit 130 is a controller, and is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 8, the control unit 130 includes an acquisition unit 131, a learning unit 132, an estimation unit 133, a classification unit 134, a determination unit 135, a determination unit 136, and a provision unit 137. It implements or executes the information processing functions and actions 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 another configuration as long as it performs information processing described later.

(Acquisition unit 131)
The acquisition unit 131 acquires various information. The acquisition unit 131 acquires various types of information from an external device such as the user terminal 10 . Also, the acquisition unit 131 acquires various types of information from the storage unit 120 . In addition, the acquisition unit 131 includes the store 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, and the commercial transaction site information storage unit 126. Also, various information is acquired from the factoring information storage unit 127 or the like.

Acquisition unit 131 receives various types of information from an external information processing device via communication unit 110 . Acquisition unit 131 stores the received information in storage unit 120 . Acquisition unit 131 receives various types of information from user terminal 10 , store device 20 , or web server 30 . The acquisition unit 131 acquires information from the user terminal 10 used by the user. The acquisition unit 131 acquires various types of information from the store device 20 . For example, the acquiring unit 131 acquires information about a store opened by a store owner on a commercial transaction site from the store device 20 used by the store owner. For example, the acquisition unit 131 acquires various information from the web server 30 . For example, the acquisition unit 131 acquires information on commercial transaction sites from the web server 30 . For example, the acquisition unit 131 acquires information about the store of the commercial transaction site from the web server 30 .

Acquisition unit 131 acquires store information about each of a plurality of stores opened on a commercial transaction site on the network. The acquisition unit 131 acquires a learning model (model). The acquiring unit 131 acquires store sales information indicating past sales of a target store, which is a store opened 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 acquiring unit 131 acquires store sales information indicating past sales trends of a target store, which is a store opened on a commercial transaction site on the network. The acquisition unit 131 acquires category sales information indicating past sales trends for each category of products handled on the commercial transaction site.

The acquiring unit 131 acquires a first learning model for predicting the probability of occurrence of a negative event, which is an event caused by a store opened on a commercial transaction site on the network and is a negative event for the commercial transaction site. Acquisition unit 131 acquires a second learning model that predicts the future possibility of sales of a store that opens on a commercial transaction site. The acquisition unit 131 acquires the first learning model that receives the store information of the store as an input and outputs a score indicating the probability of occurrence of a negative event caused by the store.

Acquisition unit 131 acquires a second learning model that receives store information of a store as an input and outputs a score indicating the future possibility of sales of the store. The acquisition unit 131 acquires a first learning model that predicts the probability of occurrence of uncollectible receivables of the store. Acquisition unit 131 acquires a first learning model for predicting the probability of a store closing from a commercial transaction site.

Acquisition unit 131 acquires store information about each of a plurality of stores opened on a commercial transaction site on the network. Acquisition unit 131 acquires store information including information indicating whether or not each of the plurality of stores is advertising. Acquisition unit 131 acquires store information including information indicating products handled by each of the plurality of stores.

(learning unit 132)
The learning unit 132 executes learning processing for learning a learning model (model). For example, the learning unit 132 executes learning processing based on various information acquired by the acquisition unit 131 . The learning unit 132 executes learning processing based on information from an external information processing device and information stored in the storage unit 120 . The learning section 132 executes learning processing based on the information stored in the model information storage section 122 . The learning unit 132 stores the model generated by learning in the model information storage unit 122 .

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

The learning unit 132 learns a learning model that predicts the probability that the store receivables will become uncollectible. The learning unit 132 learns a learning model for predicting the probability of store closures from commercial transaction sites.

The learning unit 132 learns a plurality of learning models each corresponding to a different period and predicting the probability of occurrence of a negative event caused by the store within the corresponding period. The learning unit 132 learns a plurality of learning models each outputting a score indicating the probability of occurrence of a negative event caused by the store within a corresponding period.

The learning unit 132 performs learning processing. The learning unit 132 performs various types of learning. The learning unit 132 learns various types 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 types of information such as models. The learning unit 132 generates a model through learning. The learning unit 132 learns the model using various machine learning techniques. For example, the learning unit 132 learns model (network) parameters. The learning unit 132 learns the model using various machine learning techniques.

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 learning processing using the learning data stored in the model information storage unit 122, thereby obtaining various models such as models M1, M2, M11, M12, M13, M21, M22, M31, and M41. Generate a learning model. For example, the learning unit 132 generates models used for speech recognition. The learning unit 132 learns the parameters of the networks of various learning models such as the models M1, M2, M11, M12, M13, M21, M22, M31, and M41, thereby obtaining the models M1, M2, M11, M12, M13, Various learning models such as M21, M22, M31, and M41 are generated.

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

For example, the learning unit 132 generates a model used for estimating the probability (possibility) of store closing. For example, the learning unit 132 generates a model that outputs a score indicating the probability (possibility) that the store corresponding to the store information will withdraw from the commercial transaction site when the store information of the store is input. The learning unit 132 generates the model M1 by learning the parameters of the network of the model M1.

The method of learning by the learning unit 132 is not particularly limited. It may be learned by inputting it into a calculation model. Also, for example, a technique based on DNN (Deep Neural Network) such as CNN (Convolutional Neural Network) and 3D-CNN may be used. When the learning unit 132 targets time-series data such as voice, a recurrent neural network (RNN) or a method based on LSTM (Long Short-Term Memory units) that is an extension of RNN is used. good too.

(Estimation unit 133)
The estimation unit 133 executes estimation processing for estimating various information. The estimation unit 133 stores information estimated by the estimation process in the storage unit 120 . For example, the estimation unit 133 executes estimation processing based on various information acquired by the acquisition unit 131 . The estimation unit 133 executes estimation processing based on various information stored in the storage unit 120 . The estimation unit 133 executes estimation processing based on various information received from an external information processing device.

The estimation unit 133 uses the model learned by the learning unit 132 to perform estimation processing. For example, the estimation unit 133 executes estimation processing based on information classified by the classification unit 134 . For example, the estimation unit 133 executes estimation processing based on information determined by the determination unit 135 . For example, the estimation unit 133 performs estimation processing based on information determined by the determination unit 136 .

The estimating unit 133 estimates the number of occurrences of negative events, which are events caused by a store opened on a commercial transaction site on the network and is a negative event for the commercial transaction site, using social situation information indicating the economic situation of society. . The estimation unit 133 estimates the number of irrecoverable claims of the store as the number of occurrences. The estimation unit 133 estimates the number of stores exiting the commercial transaction site as the number of occurrences. The estimating unit 133 estimates the number of stores that will exit the commercial transaction site using a learning model that has learned the characteristics of the relationship between the economic situation of society and the number of stores that have exited the commercial transaction site.

The estimation unit 133 estimates a store exit probability, which is the probability that a target store, which is a store that opens on a commercial transaction site on the network, will exit the commercial transaction site after a predetermined period of time. The estimating unit 133 estimates the closing probability of the target store using a learning model that has learned the characteristics of the relationship between the store opening on the commercial transaction site and the store closing from the commercial transaction site.

The estimating unit 133 estimates the store closing probability of the target store using a plurality of learning models each corresponding to a different period and estimating the probability of the store closing within the corresponding period. to estimate The estimating unit 133 estimates the closing probability of the target store using a plurality of learning models, each of which outputs a score indicating the probability that the store will close within the corresponding period. The estimating unit 133 updates the closing probability of the target store when the collection of the accounts receivable corresponding to the future credit of the target store satisfies the condition regarding the delay.

(Classification unit 134)
The classification unit 134 executes classification processing for classifying various types of information. The classification unit 134 stores information classified by the classification process in the storage unit 120 . For example, the classification unit 134 executes classification processing based on various information acquired by the acquisition unit 131 . The classification unit 134 executes classification processing based on various information stored in the storage unit 120 . The classification unit 134 performs classification processing based on various types of information received from an external information processing device.

The classification unit 134 uses the model learned by the learning unit 132 to perform classification processing. For example, the classification unit 134 executes classification processing based on information determined by the determination unit 136 . For example, the classification unit 134 executes classification processing based on information determined by the determination unit 135 . For example, the classification unit 134 performs classification processing based on information estimated by the estimation unit 133 .

The classification unit 134 classifies a plurality of stores into a plurality of groups based on store information relating to each of the plurality of stores opened on the commercial transaction site on the network. The classification unit 134 classifies a plurality of stores into a plurality of groups according to the risk of uncollectible claims of each of the plurality of stores based on the store information. The classification unit 134 classifies a plurality of stores into a plurality of groups according to the possibility of leaving the commercial transaction site.

The classification unit 134 classifies a plurality of stores into a plurality of groups using a learning model that has learned characteristics of relationships between stores that open on the commercial transaction site and stores that exit the commercial transaction site. The classification unit 134 classifies a plurality of stores into a plurality of groups based on store information including information on products sold by each of the plurality of stores. The classification unit 134 classifies a plurality of stores into a plurality of groups based on store information including sales information of each of the plurality of stores. The classification unit 134 classifies a plurality of stores opened on the commercial transaction site into a plurality of groups using thresholds based on the number of occurrences estimated by the estimation unit 133 .

(Determination unit 135)
The determination unit 135 executes determination processing for determining various types of information. For example, the determination unit 135 executes determination processing based on various information acquired by the acquisition unit 131 . For example, the determination unit 135 executes determination processing based on information stored in the storage unit 120 .

The determination unit 135 uses the model learned by the learning unit 132 to perform determination processing. For example, the determination unit 135 executes determination processing based on information estimated by the estimation unit 133 . For example, the determination unit 135 executes determination processing based on information classified by the classification unit 134 . For example, the determination unit 135 executes determination processing based on information determined by the determination unit 136 .

The determining unit 135 determines the trend of sales for each category based on the past sales for each category. The determining unit 135 determines the trend of sales for each category based on the transition of past sales for each category. For example, the determination unit 135 uses the score output by the model M41 to determine the trend of sales for each category. For example, when the score output by the model M41 is equal to or greater than a predetermined threshold value (for example, 1.2), the determination unit 135 determines that the sales trend of the category corresponding to the model input information input to the model M41 is an upward trend. Determine that there is. For example, when the score output by the model M41 is less than a predetermined threshold value (for example, 0.8), the determination unit 135 determines that the sales trend of the category corresponding to the model input information input to the model M41 is a downward trend. Determine that there is.

The determination unit 135 may execute generation processing for generating various information. The determination unit 135 stores the generated information in the storage unit 120 . For example, the determination unit 135 executes generation processing based on various information acquired by the acquisition unit 131 . The determination unit 135 executes generation processing based on various information stored in the storage unit 120 . The determination unit 135 executes generation processing based on various types of information received from an external information processing device.

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

The determination unit 135 generates content. For example, the determination unit 135 appropriately uses various techniques such as Java (registered trademark) to generate a screen (content) to be provided to the user terminal 10 . Note that the determination unit 135 may generate a screen (content) to be provided to the user terminal 10 based on CSS, JavaScript (registered trademark), or HTML formats. Further, for example, the determination unit 135 may generate screens (contents) in various formats such as JPEG (Joint Photographic Experts Group), GIF (Graphics Interchange Format), and PNG (Portable Network Graphics).

(Determination unit 136)
The determination unit 136 executes determination processing 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 determination processing based on various information acquired by the acquisition unit 131 . The determination unit 136 executes determination processing based on various information stored in the storage unit 120 . For example, the determination unit 136 executes determination processing based on various information received from an external information processing device.

The decision unit 136 uses the model learned by the learning unit 132 to execute decision processing. For example, the determination unit 136 executes determination processing based on information estimated by the estimation unit 133 . For example, the determination unit 136 executes determination processing based on information classified by the classification unit 134 . For example, the determination unit 136 executes determination processing based on information determined by the determination unit 135 .

For example, the determining unit 136 calculates various information based on information estimated by the estimating unit 133 . For example, the determination unit 136 calculates various information based on information determined by the determination unit 135 . For example, the determination unit 136 calculates various information based on 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 models. For example, the determination unit 136 calculates various scores.

The determination unit 136 determines conditions for purchasing bonds for each group classified by the classification unit 134 . The decision unit 136 decides conditions that are advantageous to stores belonging to a group with a lower risk. The decision unit 136 decides conditions that are more advantageous to the stores belonging to the group for which the possibility of closing is lower.

The determination unit 136 determines conditions for purchasing future bonds for each group. The determination unit 136 determines an index value for purchase of future bonds for each group. The determining unit 136 determines the maximum purchase amount of future bonds of one store based on the index value of the group to which the one store belongs and the sales of the one store. The determining unit 136 determines the purchase upper limit of one store based on the value obtained by multiplying the index value of the group to which the one store belongs by the sales of the one store. The determining unit 136 determines, for each group, the number of months for which future bonds are to be purchased as an index value.

The determining unit 136 determines the conditions for purchasing the bond 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 that the claim of the target store becomes uncollectible is lower. The decision unit 136 decides a condition that is more advantageous to the target store as the probability of closing of the target store is lower.

The determining unit 136 determines the conditions for purchasing the future bond of the target store based on the occurrence probability of the negative event by the target store. The determination unit 136 determines an index value for purchase of future bonds of the target store. The determining unit 136 determines the maximum purchase amount of future bonds of the target store based on the index value of the target store and the sales of the target store. The determining unit 136 determines the maximum purchase amount of the target store based on the product of the index value of the target store and the sales of the target store. The determining unit 136 determines the number of months for which the future bond of the target store is to be purchased as an index value.

The determining unit 136 determines, as an index value, the number of months for which the future bond of the target store is to be purchased, using a plurality of learning models. The determination unit 136 determines the number of months to purchase the future bonds 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 the threshold.

The determining unit 136 determines the conditions regarding the purchase of bonds based on the number of occurrences estimated by the estimating unit 133 .

The determining unit 136 decides the amount of claims 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 product handled by the target store indicated by the category sales information. Determine the maximum purchase amount. The determination unit 136 selects 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 product handled by the target store indicated by the category sales information. Determining the purchase limit of receivables. The determination unit 136 determines the target category corresponding to the target store based on the products handled by the target store, and determines the maximum purchase amount of the bond of the target store based on the sales transition trend of the determined target category.

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 purchases the credits of the target store based on the trend of sales transition of each of the determined target categories. Determine the maximum amount. The determination unit 136 determines the maximum purchase amount of the bond of the target store based on the 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 purchase amount of the bond of the target store by assigning a greater weight to a category with a larger number of products handled on the commercial transaction site.

The determining unit 136 determines a main category from among the plurality of target categories, and determines the upper limit of the purchase amount of the bond of the target store based on the trend of sales transition of the determined main category. The determining unit 136 determines the maximum purchase amount of the bond of the target store by giving greater weight to the main category than categories different from the main category among the plurality of target categories.

The determination unit 136 learns the characteristics of the relationship between the store sales transition trend up to a predetermined point in time, the sales transition trend in the category corresponding to the products handled by the store, and the store sales after the predetermined point in time. Using the learned model, determine the upper limit of the purchase amount of the bond of the target store.

The decision unit 136 decides the purchase upper limit of the future bond of the target store. The determination unit 136 determines an index value for purchase of future bonds of the target store based on the sales transition trend of the target store and the sales trend of the category corresponding to the product handled by the target store, and determines the determined index. The value is used to determine the maximum purchase amount of future receivables for the target store. The determining unit 136 determines the maximum purchase amount of the bond of the target store according to the determination result of the determining unit 135 .

For example, when the determination unit 135 determines that the sales of the category of the target store are on an upward trend, the determination unit 136 may increase the maximum purchase amount of the bond of the target store. In this case, when the determination unit 135 determines that the sales of the main category of the target store are in an upward trend, the determination unit 136 may increase the maximum purchase amount of the bond of the target store. Further, for example, when the determination unit 135 determines that the sales of the category of the target store are in a downward trend, the determination unit 136 may decrease the maximum purchase amount of the bond of the target store. In this case, if the determination unit 135 determines that the sales of the main category of the target store are in a downward trend, the determination unit 136 may decrease the maximum purchase amount of the bond of the target store.

The determination unit 136 determines the credits of the target store based on the probability of occurrence of a negative event at the target store predicted using the first learning model and the future sales potential of the target store predicted using the second learning model. determine the conditions for the purchase of The determination unit 136 determines conditions that are more advantageous to the target store as the probability of occurrence that the claim of the target store becomes uncollectible is lower. The decision unit 136 decides a condition that is more advantageous to the target store as the probability of closing of the target store is lower.

The determination unit 136 determines the conditions for purchasing the bond of the target store by using the first learning model that has learned the characteristics of the relationship between the store opening on the commercial transaction site and the store closing from the commercial transaction site. The determining unit 136 determines the conditions for purchasing the future bond of the target store based on the probability of occurrence of a negative event by the target store and the future sales potential of the target store.

The determining unit 136 determines the mode of collection of accounts receivable corresponding to future claims of the target store based on the closing probability of the target store estimated by the estimating unit 133 . The determining unit 136 determines the collection rate of the accounts receivable corresponding to future claims of the target store based on the store closing probability of the target store. The determination unit 136 determines the mode of collection of accounts receivable corresponding to future claims of the target store based on the closing probability of the target store for each period.

The determining unit 136 determines the collection mode of the accounts receivable corresponding to future claims 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 the threshold. The determination unit 136 determines 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 as the collection period for the accounts receivable corresponding to the future receivables of the target store, and determines the collection period according to the collection period. , to determine the collection rate of accounts receivable corresponding to the future receivables of the subject store.

If the collection of the accounts receivable corresponding to the future claims of the target store satisfies a predetermined condition, the determining unit 136 updates the collection mode of the accounts receivable corresponding to the future claims of the target store. The determination unit 136 updates the collection mode of the accounts receivable corresponding to the future claims of the target store when the collection of the accounts receivable corresponding to the future claims of the target store satisfies the condition regarding the delay. The determining unit 136 updates the collection mode of the accounts receivable corresponding to the future claim of the target store based on the updated closing probability of the target store.

The determination unit 136 determines, from among the plurality of stores, the proposed store to which the purchase of the bond is to be proposed, based on the store information regarding each of the plurality of stores. The determination unit 136 determines the suggested store depending on whether or not the advertisement is being displayed. The determination unit 136 determines a store that does not advertise as a proposed store.

The decision unit 136 decides the proposed store according to the products handled. The determination unit 136 determines a store whose number of products handled is less than a predetermined threshold as a proposal destination store.

The determination unit 136 determines the store to be proposed by using a learning model that has learned the characteristics of the relationship between the store that opens on the commercial transaction site and the change in sales when the store implements measures to increase sales. do. The determining unit 136 determines a proposed store by using a learning model that receives store information of a store as input and outputs a score indicating a change in sales when a measure is implemented. The determining unit 136 determines a store whose score output by the learning model is equal to or greater than a predetermined threshold as a proposed store.

(Providing unit 137)
The providing unit 137 provides various information. The providing unit 137 transmits various types of information to an external information processing device via the communication unit 110 . The providing unit 137 transmits various types of 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 .

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

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 purchase upper limit determined by the determining unit 136 . The providing unit 137 provides information indicating the collection mode of accounts receivable corresponding to future claims of the target store determined by the determining unit 136 . The providing unit 137 provides the proposed store determined by the determining unit 136 with information proposing the purchase of the bond.

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

First, FIG. 16 will be described. For example, FIG. 16 shows an example of determination of conditions for purchasing bonds for each group performed by the information processing apparatus 100 . In FIG. 16, the information processing apparatus 100 classifies a plurality of stores into a plurality of groups based on store information relating to each of the plurality of stores opened on the commercial transaction site on the network (step S101). Then, the information processing device 100 determines the conditions for purchasing the bond for each group (step S102).

Next, FIG. 17 will be described. For example, FIG. 17 shows an example of model learning performed by the information processing apparatus 100 and processing using the learned model. In FIG. 17, the information processing apparatus 100 creates a learning model for predicting the probability of occurrence of a negative event, which is an event that occurs within a predetermined period of time due to a store opening on a commercial transaction site on the network and is a negative event for the commercial transaction site. It learns (step S201). Then, the information processing apparatus 100 determines the conditions for purchasing the bond of the target store based on the probability of occurrence of a negative event by the target store predicted using the learning model (step S202).

Next, FIG. 18 will be described. For example, FIG. 18 shows an example of how the information processing apparatus 100 decides the conditions regarding the purchase of bonds according to the social economic conditions. In FIG. 18, the information processing apparatus 100 calculates the number of occurrences of negative events, which are events caused by a store opened on a commercial transaction site on the network and is negative for the commercial transaction site, as social situation information indicating the economic situation of society. (step S301). Then, the information processing apparatus 100 determines the conditions for purchasing the bond based on the estimated number of occurrences (step S302).

Next, FIG. 19 will be described. For example, FIG. 19 shows an example of how the information processing apparatus 100 determines the maximum purchase amount of a bond. In FIG. 19, the information processing apparatus 100 acquires store sales information indicating past sales of a target store, which is a store opened on a commercial transaction site on the network (step S401). The information processing apparatus 100 also acquires category sales information indicating past sales for each category of products handled on the commercial transaction site (step S402). Then, the information processing device 100, based on the sales tendency of the target store indicated by the store sales information and the sales tendency of the category corresponding to the products handled by the target store indicated by the category sales information, is determined (step S403).

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 apparatus 100 . In FIG. 20, the information processing apparatus 100 acquires a first learning model that predicts the probability of occurrence of a negative event, which is an event caused by a store that opens on a commercial transaction site on the network and is a negative event for the commercial transaction site ( step S501). The information processing apparatus 100 also acquires a second learning model that predicts the future possibility of the sales of the store that opens on the commercial transaction site (step S502). Then, the information processing device 100, based on the probability of occurrence of a negative event 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, the target The conditions for purchasing the credits of the store are determined (step S503).

Next, FIG. 21 will be described. For example, FIG. 21 shows an example of how the information processing apparatus 100 determines the collection mode of accounts receivable corresponding to future claims. In FIG. 21, the information processing apparatus 100 estimates a store exit probability, which is the probability that a target store, which is a store that opens on a commercial transaction site on the network, will exit the commercial transaction site after a predetermined period of time (step S601). Then, the information processing apparatus 100 determines the mode of collection of accounts receivable corresponding to future claims of the target store based on the closing probability of the target store (step S602).

Next, FIG. 22 will be described. For example, FIG. 22 shows an example of determination of a party to whom the purchase of a bond is proposed by the information processing apparatus 100 . In FIG. 22, the information processing apparatus 100 acquires store information about each of a plurality of stores opened on a commercial transaction site on the network (step S701). Then, the information processing apparatus 100 determines, from among the plurality of stores, the proposed store to which the purchase of the bond is proposed, based on the store information regarding each of the plurality of stores (step S702).

[4. effect〕
As described above, the information processing apparatus 100 according to the embodiment has the classification section 134 and the determination section 136 . The classification unit 134 classifies a plurality of stores into a plurality of groups based on store information relating to each of the plurality of stores opened on the commercial transaction site on the network. The determination unit 136 determines conditions for purchasing bonds for each group classified by the classification unit 134 .

In this way, the information processing apparatus 100 according to the embodiment classifies a plurality of stores that open on a commercial transaction site into a plurality of groups, and determines conditions related to the purchase of bonds for each of the classified groups. Therefore, it is possible to provide appropriate services related to the purchase of claims.

Further, in the information processing apparatus 100 according to the embodiment, the classification unit 134 classifies a plurality of stores into a plurality of groups according to the risk of uncollectible claims of each of the plurality of stores based on the store information.

As described above, the information processing apparatus 100 according to the embodiment classifies a plurality of stores into a plurality of groups according to the risk of uncollectible claims, thereby appropriately classifying the stores. can be made available to provide appropriate services for

In addition, in the information processing apparatus 100 according to the embodiment, the decision unit 136 decides conditions that are advantageous to stores belonging to a group with a lower risk.

In this way, the information processing apparatus 100 according to the embodiment can provide an appropriate service regarding the purchase of claims by determining conditions that are more advantageous to stores belonging to a group with a lower risk. .

Further, in the information processing apparatus 100 according to the embodiment, the classification unit 134 classifies a plurality of stores into a plurality of groups according to the possibility of leaving the commercial transaction site.

In this way, the information processing apparatus 100 according to the embodiment classifies a plurality of stores into a plurality of groups according to the possibility of leaving the commercial transaction site, thereby appropriately classifying the stores. Appropriate services regarding the purchase of receivables can be provided.

Further, in the information processing apparatus 100 according to the embodiment, the decision unit 136 decides conditions that are more advantageous to the stores belonging to the group for which the possibility of closing is lower.

In this way, the information processing apparatus 100 according to the embodiment can provide an appropriate service related to the purchase of claims by determining favorable conditions for stores belonging to a group with a lower possibility of closing. can do.

Further, in the information processing apparatus 100 according to the embodiment, the classification unit 134 classifies a plurality of stores using a learning model that has learned the characteristics of the relationship between stores that open on the commercial transaction site and stores that leave the commercial transaction site. Categorize into multiple groups.

As described above, the information processing apparatus 100 according to the embodiment can classify a plurality of stores into a plurality of groups using a learning model, thereby appropriately classifying the stores and providing an appropriate service related to purchase of claims. can be made available.

In addition, in the information processing apparatus 100 according to the embodiment, the determination unit 136 determines conditions for purchasing future bonds for each group.

In this manner, the information processing apparatus 100 according to the embodiment can provide an appropriate service regarding the purchase of future claims by determining the conditions regarding the purchase of future claims for each group.

Further, in the information processing apparatus 100 according to the embodiment, the determining unit 136 determines an index value for purchasing future bonds for each group.

In this way, the information processing apparatus 100 according to the embodiment can provide an appropriate service related to the purchase of future claims by determining the index value for the purchase of future claims for each group.

In addition, in the information processing apparatus 100 according to the embodiment, the determination unit 136 determines the upper limit purchase amount of future bonds of one store based on the index value of the group to which the one store belongs and the sales of the one store. do.

In this way, the information processing apparatus 100 according to the embodiment determines the maximum purchase amount of future claims of one store based on the index value and sales of one store, thereby providing an appropriate service related to the purchase of claims. can be provided.

Further, in the information processing apparatus 100 according to the embodiment, the determining unit 136 sets the purchase upper limit amount of one store based on the value obtained by multiplying the index value of the group to which the one store belongs by the sales of the one store. decide.

As described above, the information processing apparatus 100 according to the embodiment determines the maximum purchase amount of future claims of one store based on the value obtained by multiplying the index value of the one store by the sales. can be made available to provide appropriate services for

In addition, in the information processing apparatus 100 according to the embodiment, the determination unit 136 determines the number of months for which future claims are to be purchased as an index value for each group.

As described above, the information processing apparatus 100 according to the embodiment determines the number of months for which future claims are to be purchased as an index value for each group, thereby making it possible to provide appropriate services related to the purchase of claims. can.

Further, in the information processing apparatus 100 according to the embodiment, the classification unit 134 classifies the plurality of stores into the plurality of groups based on the store information including the information of the products sold by each of the plurality of stores.

In this way, the information processing apparatus 100 according to the embodiment can classify a plurality of stores into a plurality of groups based on the information on the products sold by each of the plurality of stores, and provide appropriate services related to the purchase of claims. can be provided.

Further, in the information processing apparatus 100 according to the embodiment, the classification unit 134 classifies a plurality of stores into a plurality of groups based on store information including sales information of each of the plurality of stores.

As described above, the information processing apparatus 100 according to the embodiment can classify a plurality of stores into a plurality of groups based on the sales information of each of the plurality of stores, and provide an appropriate service regarding the purchase of bonds. can be made possible.

The information processing apparatus 100 according to the embodiment also has a providing unit 137 . The providing unit 137 provides information indicating the conditions determined by the determining unit 136 .

Thus, the information processing apparatus 100 according to the embodiment can provide appropriate information by providing information indicating conditions.

[5. Hardware configuration]
The information processing apparatus 100 according to the embodiments described above is implemented by a computer 1000 configured as shown in FIG. 23, for example. FIG. 23 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus. Computer 1000 has CPU 1100 , RAM 1200 , ROM 1300 , HDD (Hard Disk Drive) 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

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

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via network N, sends the data to CPU 1100, and transmits data generated by CPU 1100 to other devices via network N. FIG.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . CPU 1100 also outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1200 via 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. etc.

For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control unit 130 by executing programs loaded on the RAM 1200 . The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired via the network N from another device.

As described above, some of the embodiments and modifications of the present application have been described in detail with reference to the drawings. It is possible to carry out the present invention in other forms with modifications and improvements.

[6. others〕
Further, 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 described as being performed manually. All or part of the processing can also be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Also, the above-described embodiments and modifications can be appropriately combined within a range that does not contradict the processing content.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

1 information processing system 100 information processing device 121 store owner 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 unit 131 Acquisition unit 132 Learning unit 133 Estimation unit 134 Classification unit 135 Determination unit 136 Determination unit 137 Provider 10 User terminal 20 Store device 30 Web server N Network

Claims (11)

A damage score that is a score of each store calculated based on store information about each of a plurality of stores that open on a commercial transaction site on the network, and that is a score related to damage when each of the stores exits the commercial transaction site. a classifier that classifies the plurality of stores into a plurality of groups using
a decision unit that decides conditions for purchasing bonds for each group classified by the classification unit;
An information processing device comprising: The decision unit
2. The information processing apparatus according to claim 1, wherein conditions for purchasing future claims are determined for each group. The decision unit
3. The information processing apparatus according to claim 2 , wherein an index value for purchase of said future bond is determined for each group. The decision unit
4. The information according to claim 3 , wherein an upper limit purchase amount of the future bond of the one store is determined based on the index value of the group to which the one store belongs and the sales of the one store. processing equipment. The decision unit
5. The purchase limit amount of the one store is determined based on a value obtained by multiplying the index value of the group to which the one store belongs by the sales of the one store. The information processing device described. The decision unit
6. The information processing apparatus according to any one of claims 3 to 5 , wherein the number of months for which the future claims are to be purchased is determined as the index value for each group. The classification unit
7. The store according to any one of claims 1 to 6 , wherein the plurality of stores are classified into the plurality of groups based on the store information including information on products sold by each of the plurality of stores. information processing equipment. The classification unit
The information according to any one of claims 1 to 7 , wherein the plurality of stores are classified into the plurality of groups based on the store information including sales information of each of the plurality of stores. processing equipment. a providing unit that provides information indicating the condition determined by the determining unit;
The information processing apparatus according to any one of claims 1 to 8 , further comprising: A computer-executed information processing method comprising:
A damage score that is a score of each store calculated based on store information about each of a plurality of stores that open on a commercial transaction site on the network, and that is a score related to damage when each of the stores exits the commercial transaction site. a sorting step of sorting the plurality of stores into a plurality of groups using
a determination step of determining conditions related to the purchase of bonds for each group classified by the classification step;
An information processing method comprising: A damage score that is a score of each store calculated based on store information about each of a plurality of stores that open on a commercial transaction site on the network, and that is a score related to damage when each of the stores exits the commercial transaction site. a classification procedure for classifying the plurality of stores into a plurality of groups using
a determination procedure for determining conditions relating to the purchase of bonds for each group classified by the classification procedure;
An information processing program characterized by causing a computer to execute

Images