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

Abstract

To provide an information processing device and the like capable of generating lending information using information other than financial indicators.SOLUTION: In an information processing method, a computer performs processes of transmitting a consent screen for lending to a business operator terminal due to a business operator operating a link for applying for lending set on a site where a platform provider provides a service to businesses operators, receiving consent information of the business operator from the business operator terminal, obtaining registration information of the business operator regarding the lending and service data regarding the business operator's use of the service of the platform provider, and transmitting information about lending for the business operator to the business operator terminal based on the obtained registration information and service data.SELECTED DRAWING: Figure 12

Description

Technical Field

[0001] The present invention relates to an information processing method and the like for transmitting information related to rendering for business operators.

Background Art

[0002] In enterprises, when the cash flow becomes tight, they receive financing from financial institutions. In preparation for financing, they always keep track of the funds that can be raised by themselves. However, for many small and medium-sized enterprises, it is not easy to grasp the funds that can be raised by themselves as an option for management.

[0003] In response to such a situation, an information processing device has been proposed (Patent Document 1) that can determine the financing conditions available for an enterprise without causing the enterprise to undergo complicated procedures by using one or more financial indicators based on the financial data of the target enterprise together with one or more reliabilities related to the financial data.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the information processing device described in Patent Document 1 determines the financing conditions based on financial indicators and only determines the financing conditions from one aspect of enterprise activities. The present invention has been made in view of such a situation. Its purpose is to provide an information processing device and the like that can use information other than financial indicators when generating rendering information.

Means for Solving the Problems

[0006] <0An information processing method according to one aspect of the present invention is characterized in that, when a business operator operates a link for applying for lending set up on a site where a platform provider provides services to a business operator, a computer transmits a consent screen for the lending to the business operator's terminal, receives the business operator's consent information from the business operator's terminal, obtains the business operator's registration information regarding the lending and service data regarding the business operator's use of the platform provider's services, and transmits information regarding the lending for the business operator to the business operator's terminal based on the obtained registration information and service data. [Effects of the Invention]

[0007] From one perspective of this invention, it becomes possible to use information other than financial indicators when generating lending information. [Brief explanation of the drawing]

[0008] [Figure 1] This is an explanatory diagram showing an example of an ecosystem configuration. [Figure 2] Block diagram showing an example of a server hardware configuration. [Figure 3] This is a block diagram showing an example of a terminal's hardware configuration. [Figure 4] This is an explanatory diagram showing an example of a user database. [Figure 5] This is an explanatory diagram showing an example of a linked account database. [Figure 6] This is an explanatory diagram showing an example of a deposit / withdrawal database. [Figure 7] This is an explanatory diagram illustrating an example of a platform database. [Figure 8] This is an explanatory diagram showing an example of a representative / business owner database. [Figure 9] This is an explanatory diagram showing an example of a corporate database. [Figure 10] This is an explanatory diagram showing an example of a credit scoring model structure. [Figure 11] This is an explanatory diagram showing an example of the structure of the third model. [Figure 12]It is a flowchart showing an example of the main processing procedure. [Figure 13] It is a flowchart showing an example of the data linkage processing procedure. [Figure 14] It is a flowchart showing an example of the preliminary examination processing procedure. [Figure 15] It is an explanatory diagram showing an example of the platform screen. [Figure 16] It is an explanatory diagram showing an example of the login screen. [Figure 17] It is an explanatory diagram showing an example of the home screen. [Figure 18] It is an explanatory diagram showing an example of the service selection screen. [Figure 19] It is an explanatory diagram showing an example of the login information input screen. [Figure 20] It is an explanatory diagram showing another example of the home screen. [Figure 21] It is an explanatory diagram showing another example of the home screen. [Figure 22] It is an explanatory diagram showing another structural example of the credit model. [Figure 23] It is an explanatory diagram showing the structural example of the business evaluation model. [Figure 24] It is an explanatory diagram showing an example of the evaluation result DB. [Figure 25] [[ID=३९]]It is a flowchart showing an example of the business evaluation processing procedure. [Figure 26] It is an explanatory diagram showing another example of the home screen. [Figure 27] It is an explanatory diagram showing another example of the home screen. [Figure 28] It is an explanatory diagram showing an example of the list screen. [Figure 29] It is a flowchart showing an example of the list screen creation processing procedure. [Figure 30] It is an explanatory diagram showing an example of the granting condition DB. [Figure 31] It is an explanatory diagram showing an example of the privilege DB. [Figure 32] It is an explanatory diagram showing an example of the granting history DB. [Figure 33]This flowchart shows an example of the procedure for awarding points. [Figure 34] This is an explanatory diagram showing an example of a grant notification screen. [Figure 35] This flowchart shows an example of the procedure for consistency verification. [Figure 36] This table shows an example of consistent and related data. [Figure 37] This graph shows an example of consistent and related data. [Figure 38] This table shows examples of related data whose consistency is questionable. [Figure 39] This graph shows an example of related data whose consistency is questionable. [Figure 40] This flowchart shows an example of the procedure for verifying the integrity of related data. [Figure 41] This is a flowchart showing an example of the review process. [Modes for carrying out the invention]

[0009] The following embodiments will be described with reference to the drawings. Figure 1 is an explanatory diagram showing an example of the ecosystem configuration. Ecosystem 100 is operated by a financial institution that provides lending to businesses. Ecosystem 100 includes Server 1 and Terminal 2. Platform 3 represents a system that can link data with Ecosystem 100. A platform provider is a business that provides and operates services and systems that serve as a platform connecting users and service providers on the internet, but here, the computer system operated by the platform provider is referred to as Platform 3. Accounting System 4 is a system that provides accounting services mainly through cloud services. Financial Institution Server 5 is a so-called core banking server that manages account deposit and withdrawal information, etc., at a financial institution. Financial Institution Server 5 includes a core banking server that manages account deposit and withdrawal information, etc., at the financial institution that operates Ecosystem 100. Model Vendor 6 is an information provider or credit information agency that provides services using scoring models, etc., to determine credit risk. Other Vendors 7 are companies that provide services used by financial institutions in conducting their business. The services envisioned for use by financial institutions include AML (Anti-Money Laundering) services, eKYC, and personal credit information provision services. AML services are designed to prevent money laundering. eKYC (electronic Know Your Customer) is a service that provides online identity verification. Personal credit information provision services are services that provide personal credit information by credit information agencies. Personal credit information includes attribute information such as an individual's annual income, housing information, and place of employment, as well as payment information for loans, utilities, etc. Server 1, terminal 2, platform 3, accounting system 4, financial institution server 5, model vendor 6, and other vendors 7 are connected to each other via network N, enabling communication. Network N is the internet, a public network, a mobile phone network, or a dedicated line network. Network N may also be a combination of these types of networks, or a virtual network such as a VPN (Virtual Private Network).

[0010] Figure 2 is a block diagram showing an example of a server hardware configuration. Server 1 includes a control unit 11, a main memory unit 12, an auxiliary memory unit 13, a communication unit 15, and a read unit 16. The control unit 11, main memory unit 12, auxiliary memory unit 13, communication unit 15, and read unit 16 are connected by bus B. Server 1 can be composed of a server computer, a workstation, a PC (Personal Computer), etc. Alternatively, Server 1 may be composed of a multi-computer system consisting of multiple computers, a virtual machine virtually constructed by software, or a quantum computer. Furthermore, the functions of Server 1 may be implemented as a cloud service.

[0011] The control unit 11 has one or more arithmetic processing units such as a CPU (Central Processing Unit), an MPU (Micro-Processing Unit), and a GPU (Graphics Processing Unit). The control unit 11 reads and executes a control program 1P (program, program product) stored in the auxiliary storage unit 13, thereby performing various information processing and control processing related to the server 1, and realizing functional units such as a first transmission unit, a reception unit, an acquisition unit, and a second transmission unit.

[0012] The main memory unit 12 consists of SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), flash memory, etc. The main memory unit 12 primarily temporarily stores data necessary for the control unit 11 to perform arithmetic processing.

[0013] The auxiliary storage unit 13 is a hard disk or SSD (Solid State Drive), and stores the control program 1P and various DBs (Databases) necessary for the control unit 11 to execute processing. The auxiliary storage unit 13 stores the user DB 131, linked account DB 132, deposit / withdrawal DB 133, platformer DB 134, representative / business owner DB 135, and corporate DB 136, etc. The auxiliary storage unit 13 also stores the credit scoring model 141 and the business feasibility assessment model 142. Furthermore, the auxiliary storage unit 13 may store the evaluation result DB 137, the granting conditions DB 138, the benefits DB 139, and the granting history DB 13A. The auxiliary storage unit 13 may be separate from the server 1 and may be an externally connected storage device. The various DBs stored in the auxiliary storage unit 13 may be stored on a database server or cloud storage different from the server 1. The databases stored in the auxiliary storage unit 13 are not limited to those shown in Figure 2, and the auxiliary storage unit 13 may store other databases as needed.

[0014] The communication unit 15 communicates with terminal 2, platform 3, accounting system 4, financial institution server 5, model vendor 6, and other vendors 7 via the network N. Alternatively, the control unit 11 may use the communication unit 15 to download a control program 1P from another computer via the network N, etc., and store it in the auxiliary storage unit 13.

[0015] The reading unit 16 reads a portable storage medium 1a, including CD (Compact Disc)-ROM and DVD (Digital Versatile Disc)-ROM. The control unit 11 may read the control program 1P from the portable storage medium 1a via the reading unit 16 and store it in the auxiliary storage unit 13. Alternatively, the control unit 11 may read the control program 1P from the semiconductor memory 1b.

[0016] Figure 3 is a block diagram showing an example of the hardware configuration of a terminal. Terminal 2 is a terminal used by an end user. Terminal 2 consists of a notebook computer, panel computer, tablet computer, smartphone, etc. Terminal 2 includes a control unit 21, main memory unit 22, auxiliary memory unit 23, communication unit 24, input unit 25, and display unit 26. Each component is connected by bus B.

[0017] The control unit 21 has one or more arithmetic processing units such as CPUs, MPUs, and GPUs. The control unit 21 provides various functions by reading and executing control programs 2P (programs, program products) stored in the auxiliary storage unit 23.

[0018] The main memory unit 22 is an SRAM, DRAM, flash memory, etc. The main memory unit 22 primarily temporarily stores data necessary for the control unit 21 to perform calculations.

[0019] The auxiliary storage unit 23 is a hard disk or SSD, and stores various data necessary for the control unit 21 to execute processing. The auxiliary storage unit 23 may be separate from the terminal 2 and may be an externally connected storage device. Various databases, etc., stored in the auxiliary storage unit 23 may be stored in a database server or cloud storage.

[0020] The communication unit 24 communicates with the server 1 and the platformer 3 via the network N. Alternatively, the control unit 21 may use the communication unit 24 to download the control program 2P from another computer via the network N, etc., and store it in the auxiliary storage unit 23.

[0021] The input unit 25 is a keyboard or mouse. The display unit 26 includes a liquid crystal display panel or the like. The display unit 26 displays lending information output by the server 1. Alternatively, the input unit 25 and the display unit 26 may be integrated to form a touch panel display. The terminal 2 may also display information on an external display device.

[0022] Figure 4 is an explanatory diagram showing an example of a user database. User DB 131 stores information about end users. End users are corporations or sole proprietors who raise funds from financial institutions, etc., using Ecosystem 100. User DB 131 includes columns for User ID, Type, Name, and Email Address. The User ID column stores a user ID that uniquely identifies the end user. The Type column stores the type of the end user. The type is, for example, a corporation or a sole proprietor. The Name column stores the name of the corporation or the name of the sole proprietor. The Email Address column stores the user's contact email address. Note that the email address may be used as the user ID. In this case, the value in the User ID column and the value in the Email Address column may match.

[0023] Figure 5 is an explanatory diagram showing an example of a linked account database. The linked account database 132 stores the end-user information necessary for data linkage with platform 3. The linked account database 132 includes a user ID column, a Pfer name column, and a token information column. The user ID column stores the user ID of the end-user. The Pfer name column stores the name of platform 3 with which data linkage is performed. The token information column stores access tokens, refresh tokens, etc., provided by platform 3.

[0024] Figure 6 is an explanatory diagram showing an example of a deposit / withdrawal database. The deposit / withdrawal database 133 stores deposit and withdrawal information for bank accounts used by end users. The deposit / withdrawal database 133 includes columns for User ID, Bank Code, Branch Number, Account Number, Account Type, Type, Date / Time, Amount, Transfer Destination, and Balance. The User ID column stores the user ID. The Bank Code column stores the bank code that identifies the bank. The Branch Number column stores the bank branch number. The Account Number column stores the account number. The Account Type column stores the account type. Account types include, for example, checking, time deposit, and savings. The Type column stores the type of transaction. Transaction types include, for example, deposit, withdrawal, and transfer. The Date / Time column stores the date and time the transaction took place. The Amount column stores the amount of the transaction. The Transfer Destination column stores the transfer destination. The Balance column stores the account balance. The deposit and withdrawal information stored in the deposit and withdrawal DB133 is obtained from the financial institution server 5. Alternatively, the deposit and withdrawal DB133 may be used as a temporary database, and when deposit and withdrawal information is needed, the necessary information may be obtained from the financial institution server 5 and the deposit and withdrawal DB133 may be constructed from there. Furthermore, if the user is using an aggregation service and the aggregation service holds deposit and withdrawal information from multiple financial institutions, the deposit and withdrawal information may be obtained from the aggregation service.

[0025] Figure 7 is an explanatory diagram illustrating an example of a platform database. Platform DB 134 stores information about platform 3 provided by platform 3. Platform DB 134 includes an ID column, a name column, a link column, and a tag column. The ID column stores an ID that uniquely identifies platform 3. The name column stores the name of platform 3. The link column stores link information for accessing platform 3. Link information is, for example, a URL (Uniform Resource Locator). The tag column stores tags that characterize platform 3. Platform DB 134 is an example of a platform storage unit.

[0026] Figure 8 is an explanatory diagram showing an example of a Representative / Business Owner Database. The Representative / Business Owner Database 135 stores information about the representative of a corporation when the end user is a corporation, and information about the sole proprietor when the end user is a sole proprietor. The Representative / Business Owner Database 135 includes columns for User ID, Name, Telephone Number, Email, and Mobile Phone Number. The User ID column stores the User ID. The Name column stores the name of the representative or sole proprietor. The Telephone Number column stores the telephone number. The Email column stores the email address of the representative or sole proprietor. The Mobile Phone Number column stores the mobile phone number of the representative or sole proprietor. Note that the contents stored in the Representative / Business Owner Database 135 can be stored in the User Database 131, and the Representative / Business Owner Database 135 may not be necessary.

[0027] Figure 9 is an explanatory diagram showing an example of a corporate database. Corporate DB 136 stores information about corporations. Corporate DB 136 includes columns for corporate number, user ID, address, and main telephone number. The corporate number column stores the identification number of the corporation. The identification number is, for example, a 13-digit corporate number assigned by the National Tax Agency. However, it is not limited to this, and a corporate identification code or securities code assigned by a credit rating agency may be used as the identification number. It is desirable that the identification number be stored, but it is not required. The user ID column stores the user ID. The address column stores the address of the corporation. The main telephone number column stores the main telephone number of the corporation. For the telephone number, a number other than the main telephone number may be stored. Note that the contents stored in Corporate DB 136 may be stored in User DB 131, and Corporate DB 136 may not be required.

[0028] Figure 10 is an explanatory diagram showing an example of the structure of a credit scoring model. Credit scoring model 141 takes end-user deposit and withdrawal data, accounting data, and service data as input and outputs a judgment result. Service data is usage history etc. obtained from platform 3. Deposit and withdrawal data is obtained from deposit and withdrawal DB 133. Accounting data is obtained from accounting system 4. The judgment result is whether or not a loan is approved, the loan limit, etc. For example, the loan limit includes the loan amount, repayment period, and interest rate. Credit scoring model 141 includes the first model 1411, the second model 1412, the third model 1413, and a combiner 1414. The first model 1411 determines whether or not a loan is approved to the end user using a predetermined judgment logic based on deposit and withdrawal data. The second model 1412 determines whether or not a loan is approved to the end user using a predetermined judgment logic based on accounting data. The third model 1413 determines whether or not a loan is approved to the end user from service data. The combiner 1414 combines the judgment results of the first model 1411, the second model 1412, and the third model 1413, and outputs the final judgment result. If the credit model 141 determines that a loan is possible, it sets a credit line. The credit model 141 may set the credit line, or it may be done separately using a predetermined logic. The server 1 does not necessarily have to provide all three components of the credit model 141: the first model 1411, the second model 1412, and the third model 1413; the model vendor 6 may provide them. In this case, the server 1 obtains the judgment results of the first model 1411, the second model 1412, or the third model 1413 from the model vendor 6. Furthermore, it is desirable that the credit model 141 be able to make an appropriate judgment not only when all three data sets (deposit / withdrawal data, accounting data, and service data) are available, but also when only any two data sets or any one data set is input. Credit model 141 includes, but is not limited to, three models; it may also include a single model or a configuration including two models.

[0029] Figure 11 is an explanatory diagram showing an example structure of the third model. The third model 1413 is a neural network that takes end-user service data as input and outputs an evaluation score for the end-user's business. The service data is usage history etc. obtained from platform 3. Figure 11 shows an example in which service data is obtained from three platform 3s and input into the third model 1413. The platform A data is service data obtained from platform A. Similarly, the platform B data and platform C data are service data obtained from platform B and platform C, respectively. The neural network is, for example, a CNN (Convolutional Neural Network) and has an input layer that accepts service data as input and an output layer that outputs an evaluation score.

[0030] The input layer has multiple neurons that accept service data as input and passes the input item values ​​to the hidden layer. The hidden layer has a configuration in which a convolution layer that convolves each value input from the input layer and a pooling layer that maps the values ​​convolved in the convolution layer are alternately connected, compressing the input information and finally extracting an evaluation value. The output layer outputs an evaluation score based on the evaluation value output from the hidden layer. The evaluation score can take values ​​from 0 to 1, for example. The evaluation score can also be a discrete value, for example, an integer value from 1 to 5.

[0031] Note that in the following explanation, we will assume that the third model 1413 is a CNN, but the third model 1413 is not limited to CNNs and may be a model constructed using other learning algorithms such as neural networks other than CNNs, Bayesian networks, or decision trees.

[0032] The third model 1413 is generated using training data consisting of service data and labels (ground truth scores) as follows: Server 1 inputs the service data included in the training data into the input layer, performs calculations in the hidden layer, and obtains the score from the output layer. Server 1 compares the score output from the output layer with the labels included in the training data, i.e., the ground truth values, and optimizes the parameters used in the calculations in the hidden layer so that the output value of the output node approaches the ground truth value. These parameters include, for example, the weights (connection coefficients) between neurons and the coefficients of the activation function used in each neuron. The method of parameter optimization is not particularly limited, but for example, Server 1 uses backpropagation to optimize various parameters. Server 1 performs the above learning process using all the training data and generates the trained third model 1413.

[0033] Next, we will explain the information processing performed in Ecosystem 100. Figure 12 is a flowchart showing an example of the main processing procedure. The main processing starts when the end user selects the lending start link on the Platform 3 screen. The control unit 21 of Terminal 2 sends a start request to Server 1 based on the link information (Step S1). The control unit 11 of Server 1 receives the start request (Step S2). The control unit 11 sends a login screen to Terminal 2 (Step S3). The control unit 21 of Terminal 2 receives the login screen (Step S4). The control unit 21 displays the login screen on the display unit 26 (Step S5). If the end user is already registered with Ecosystem 100, they enter their ID and password and perform the login operation. If the end user is not yet registered with Ecosystem 100, they perform the registration operation. The control unit 21 determines whether the user's operation is registration or not (Step S6). If the control unit 21 determines that the user's operation is registration (YES in Step S6), it performs the user registration process (Step S7). The user registration process is performed in cooperation with Server 1, but since it is a well-known technology, the explanation will be omitted. If the control unit 21 determines that the user's operation is not registration (NO in step S6), or after the user registration process is completed, it sends a login request to Server 1 (step S8). The login request includes an ID and a password. The control unit 11 of Server 1 performs user authentication using the ID and password included in the login request (step S9). If the end user has permitted data linkage with Platformer 3, it is desirable to perform authentication using a one-time password during user authentication. This is to further reduce the risk of information leakage due to unauthorized access. The control unit 11 sends the home screen to Terminal 2 (step S10). The control unit 21 of Terminal 2 receives the home screen (step S11). The control unit 21 displays the home screen on the display unit 26 (step S12). The end user selects the process they want to perform on the home screen. The processes assumed here are data linkage processing and preliminary screening processing. The preliminary review process cannot be performed unless data linkage processing has been performed at least once previously. This is because the data necessary for the review cannot be obtained otherwise.The control unit 21 determines whether the end user has selected data linkage processing (step S13). If the control unit 21 determines that the end user has selected data linkage processing (YES in step S13), it performs data linkage processing (step S14). After that, the control unit 21 returns to step S13. The details of the data linkage processing will be described later. If the control unit 21 determines that the end user has not selected data linkage processing (NO in step S13), it determines whether the end user has selected preliminary review processing (step S15). If the control unit 21 determines that the end user has selected preliminary review processing (YES in step S15), it performs preliminary review processing (step S16). After that, the control unit 21 returns to step S13. If the control unit 21 determines that the end user has not selected preliminary review processing (NO in step S15), it terminates the main processing.

[0034] Figure 13 is a flowchart illustrating an example of the data linkage process procedure. The control unit 21 of terminal 2 sends a data linkage process start request to server 1 (step S31). Here, it is assumed that there are three types of data linkage, and the start request includes information on the type selected by the end user. The three types are data linkage of deposit and withdrawal information from financial institutions, data linkage of accounting information, and linkage of usage data of other services provided by platform 3. The control unit 11 of server 1 receives the start request (step S32). The control unit 11 sends a selection screen to terminal 2 (step S33). The selection screen is a screen corresponding to the type. In the case of data linkage of deposit and withdrawal information from financial institutions, it is a screen for selecting a financial institution. In the case of data linkage of accounting information, it is a screen for selecting an accounting service. In the case of linkage of usage data of platform 3, it is a screen for selecting a platform 3 that can be linked. The control unit 21 of terminal 2 receives the selection screen and displays it on the display unit 26 (step S34). The end user selects the data linkage destination on the selection screen. The control unit 21 sends a data linkage request to the platform 3 selected by the end user as the data linkage destination (step S35). The platform 3 receives the data linkage request (step S36). The platform 3 sends an input screen to the terminal 2 (step S37). The input screen is a screen where information is entered in order to log in to the platform 3. In most cases, it is a screen that requests the user ID and password. The control unit 21 of the terminal 2 receives and displays the input screen (step S38). The end user enters the user ID, password, etc. via the input unit 25. The control unit 21 sends the login information such as the user ID and password to the platform 3 (step S39). The platform 3 receives the login information (step S40). After user authentication, the platform 3 issues a token for linkage and sends it to the server 1 (step S41). The control unit 11 of the server 1 receives the token and stores it in the linkage account DB 132 (step S42). The control unit 11 uses a token to send a data request from the end user to the platformer 3 (step S43). The request includes the end user's user ID. The platformer 3 receives the request (step S44).Platformer 3 extracts end-user data based on the user ID (step S45). Platformer 3 sends the extracted data to Server 1 (step S46). If the type of linkage is deposit and withdrawal information of a financial institution, the financial institution's system performs steps S36 and S37, S40 and S41, and S44 to S46. If the type of linkage is accounting information, the accounting information system performs steps S36 and S37, S40 and S41, and S44 to S46. The control unit 11 of Server 1 receives the data and stores it in the auxiliary storage unit 13 (step S47). The control unit 11 sends the updated home screen to Terminal 2 (step S48). The control unit 21 of Terminal 2 receives and displays the home screen (step S49). After that, the control unit 21 returns processing to the caller of the data linkage. The control unit 11 also stores the user ID and password entered on the input screen in the linked account DB 132.

[0035] Figure 14 is a flowchart showing an example of the preliminary screening process. The control unit 21 of terminal 2 sends a preliminary screening request to server 1 (step S61). The control unit 11 of server 1 receives the request (step S62). The control unit 11 acquires end-user data (step S63). The control unit 11 acquires at least one data from among deposit / withdrawal data, accounting data, or service data. The control unit 11 inputs the acquired deposit / withdrawal data, accounting data, or service data into the model (step S64). The control unit 11 inputs the deposit / withdrawal data, accounting data, or service data into the credit model 141. The control unit 11 obtains an evaluation from the credit model 141 (step S65). Based on the evaluation from the credit model 141, the control unit 11 generates loan conditions for the end-user (step S66). The control unit 11 generates a results screen including the loan conditions and sends it to terminal 2 (step S67). The control unit 21 of terminal 2 receives and displays the results screen (step S68). The control unit 21 returns the process to the caller.

[0036] Next, we will explain the screen displayed on terminal 2. Figure 15 is an explanatory diagram showing an example of a platformer screen. Platformer screen d01 is the screen displayed on terminal 2 when an end user uses a service provided by platformer 3. Platformer screen d01 displays a guidance display d011 informing the user about the pre-screening process as preparation for applying for a loan to a partner financial institution, and a reference button d012 for viewing the guidance. Figure 15 is an example screen of platformer 3 that provides crowdfunding, but platformer 3 that provides services other than crowdfunding will similarly display the guidance display d011 and the reference button d012. When the end user clicks the reference button d012, the guidance page about the pre-screening process will be displayed. If the business operator operating platformer 3 has obtained a banking agency license under the Banking Act, the reference button d012 may be used as an application button for pre-screening. In this case, when the end user clicks the application button, a request to start pre-screening is sent from terminal 2 to server 1, and the main process described above begins. For example, the application button has a hyperlink set to a URL that requests Server 1 to start the pre-screening process. If Terminal 2 is already logged into Ecosystem 100, clicking the application button will initiate the pre-screening process. If Terminal 2 is not logged into Ecosystem 100, the login screen will be displayed, and once login is complete, the pre-screening process will be initiated.

[0037] Figure 16 is an explanatory diagram showing an example of a login screen. Login screen d02 is the screen for logging into Ecosystem 100. Login screen d02 includes an ID input field d021, a password input field d022, a login button d023, and a registration button d024. The ID input field d021 is the field for entering the login ID for Ecosystem 100. The login ID is either an ID assigned by Ecosystem 100 or an email address used by the end user. The password input field d022 is the field for entering the login password. When the end user selects the login button d023, a login request is sent to Server 1. End users who have not yet registered with Ecosystem 100 select the registration button d024 to proceed with the registration process.

[0038] Figure 17 is an explanatory diagram showing an example of a home screen. Home screen d03 is the screen displayed after logging into Ecosystem 100. Home screen d03 includes a preliminary screening button d031, account linkage display d032, accounting linkage display d033, PFer linkage display d034, account linkage button d035, accounting linkage button d036, PFer linkage button d037, application button d038, list button d039, and amount display d03A. When an end user selects the preliminary screening button d031, the preliminary screening process described above is started, and a preliminary screening request is sent from terminal 2 to server 1. In Figure 17, since it is not possible to apply for a preliminary screening, the text is displayed in a thin font and the outline of the button is a dotted line. In this case, even if the preliminary screening button d031 is selected, it is not possible to apply for a preliminary screening. The account linkage display d032 shows the status of linkage with financial institutions. Figure 17 shows a situation where no linkage has been made with any financial institutions. The Accounting Linkage Display d033 shows the status of integration with accounting services. Figure 17 shows a situation where no integration with any accounting services is performed. In this embodiment, preliminary screening and loan applications cannot be made unless data integration with at least one financial institution or accounting service is performed, so as described above, the preliminary screening button d031 is not functioning. The PFer Linkage Display d034 shows the status of integration with Platformer 3. Figure 17 shows a situation where no integration with any Platformer 3 is performed. The Account Linkage Button d035 is a button for setting up integration with financial institutions. The Accounting Linkage Button d036 is a button for setting up integration with accounting services. The PFer Linkage Button d037 is a button for setting up integration with Platformer 3. When the Account Linkage Button d035, Accounting Linkage Button d036, or PFer Linkage Button d037 is selected, the data integration process described above is started, and a start request is sent from Terminal 2 to Server 1. When the end user selects the application button d038, a loan application request is sent from terminal 2 to server 1. In Figure 17, the system is not in a state where a loan application can be made, so the text is displayed in a thin font and the button outline is dotted. In this case, even if the application button d038 is selected, the loan application cannot be made.Selecting the list button d039 displays a list of financial institutions, accounting services, and platform 3 that can be linked to the data. The amount display d03A shows the amount the end user can borrow. In Figure 17, no amount is displayed because no preliminary screening has been conducted. Note that the preliminary screening button d031 may always be functional regardless of whether the linkage has been established or not. In this case, when the preliminary screening button d031 is selected, if data linkage is required to proceed to the preliminary screening, it is desirable to display a message indicating that data linkage is required and prompt the end user to configure the linkage settings. Alternatively, the preliminary screening button d031 may not be included as a component of the screen, and the preliminary screening may be executed when data linkage is configured or when the end user logs in.

[0039] Figure 18 is an explanatory diagram showing an example of a service selection screen. The service selection screen d04 is a screen for selecting services to perform data integration with. The service selection screen d04 includes selection buttons d041. In Figure 18, four selection buttons d041 are displayed, but there may be three or fewer, or five or more. Also, if there are many services that can be integrated, it may become difficult to select the desired service, so it may be possible to search for the service name or to narrow down the results by service content. Furthermore, the services displayed on the service selection screen d04 should not include services that the end user has already configured for data integration. Services that have already configured for data integration can be determined by referring to the integration account DB132. The service selection screen is an example of a screen that displays a list of platform 3.

[0040] Figure 19 is an explanatory diagram showing an example of a login information input screen. The login information input screen (hereinafter referred to as the "input screen") d05 is a screen for entering login information to log in to platform 3, the data linkage destination. Input screen d05 includes an email address input field d051, a password input field d052, an accept button d053, and a cancel button d054. The email address input field d051 is for entering the email address to be used as the login ID. For platform 3 where an email address cannot be used as the login ID, this field becomes for entering the login ID instead of the email address. The password input field d052 is for entering the login password. When the end user selects the accept button d053, it is considered that they have consented to the collection of data from platform 3. The login information is also sent to platform 3, and user authentication is performed. If authentication is successful, platform 3 issues an access token and sends it to server 1. Server 1 requests data from platform 3. If the cancel button d054 is selected, data linkage will not be performed, and the user will return to the home screen. Input screen d05 is an example of a consent screen. Information indicating that the accept button d053 has been selected is sent to server 1. This information is an example of consent information. A token is issued when the end user selects the accept button d053, and server 1 receives this token; therefore, this token can also be considered consent information.

[0041] Figure 20 is an explanatory diagram showing another example of the home screen. Home screen d06 is the home screen when a preliminary screening application is possible. Home screen d06 includes a preliminary screening button d061, account linkage display d062, accounting linkage display d063, PFer linkage display d064, account linkage button d065, accounting linkage button d066, PFer linkage button d067, application button d068, list button d069, and amount display d06A. Each of the preliminary screening buttons d061 to amount display d06A is the same as the preliminary screening buttons d031 to amount display d03A on home screen d03. The following explanation will mainly describe a configuration that differs from Figure 17. In Figure 20, since a preliminary screening application is possible, the preliminary screening button d061 is displayed as selectable. As mentioned above, the preliminary screening button d061 may always be displayed as selectable. The end user can select the preliminary screening button d061 to start the preliminary screening process described above. In Figure 20, data linkage with financial institutions is complete. Therefore, the account linkage display d062 shows an end-user evaluation value of 70, based on deposit and withdrawal information in the linked account. In Figure 20, however, no linkage with any accounting services has been established, so no evaluation value is displayed in the accounting linkage display d063. In Figure 20, linkage with at least one platform 3 is complete, so the PFer linkage display d064 shows an end-user evaluation value of 10. In Figure 20, the preliminary screening is not complete, so, as in Figure 17, the application button d068 is displayed as inoperable. Also, as in Figure 17, the preliminary screening has not been performed, so no amount is displayed in the amount display d06A.

[0042] Figure 21 is an explanatory diagram showing another example of the home screen. Home screen d07 is the home screen when a loan application is possible. Home screen d07 includes account linkage display d072, accounting linkage display d073, PFer linkage display d074, account linkage button d075, accounting linkage button d076, PFer linkage button d077, application button d078, list button d079, and amount display d07A. Each of the account linkage display d072 to amount display d07A is the same as the account linkage display d062 to amount display d06A on home screen d06. The following explanation will mainly describe the configuration that differs from Figure 20. In Figure 21, the preliminary screening button d071 is not displayed because the preliminary screening has been completed. In Figure 21, the application button d078 is displayed as selectable because the preliminary screening has been completed. The end user can apply for a loan by selecting the application button d078. Furthermore, the amount displayed in d07A shows the amount that was determined to be eligible for loan based on the preliminary screening results. The amount displayed in d07A on the home screen d07 is an example of loan conditions and also an example of information related to lending.

[0043] In Figure 21, if an end user adds a linked account by operating the account linking button d075, accounting linking button d076, or PFer linking button d077, the loan terms may change. In this case, even if the end user does not apply for a preliminary screening, the home screen d07 reflecting the preliminary screening results may be displayed after the preliminary screening is performed following the data linking. Alternatively, the preliminary screening button d071 may be displayed on the home screen d07 displayed after the data linking, allowing the end user to apply for a preliminary screening.

[0044] Furthermore, if an end user logs out of Ecosystem 100 after undergoing a preliminary screening or applying for a loan, and then logs in again a few days later, the following process will be performed: When displaying the home screen, a preliminary screening will be performed based on the latest deposit and withdrawal information and service information (latest data) from Platformer 3, and the home screen reflecting the results will be displayed. Alternatively, a preliminary screening based on the latest data may be performed each time the end user logs in, without requiring any action from the end user, and the home screen d07 reflecting the results may be displayed. Alternatively, even if the end user does not log in, for example, once a month, Server 1 may perform the preliminary screening process based on the latest data using batch processing or similar methods. The home screen referred to here is assumed to be the home screen d07 shown in Figure 21.

[0045] This embodiment provides the following benefits: It becomes possible to generate lending information, such as the amount of money that can be borrowed, using not only financial information but also information such as deposit and withdrawal information from financial institutions' accounts, accounting data from accounting systems, and usage history of Platform 3.

[0046] (modified version) Figure 10 above shows an example of the credit scoring model 141, but a preliminary assessment may also be performed using a model that integrates the three models that constitute the credit scoring model 141. Figure 22 is an explanatory diagram showing another example of the structure of the credit scoring model. The credit scoring model 141 is a neural network that takes end-user deposit and withdrawal data, accounting data, service data, etc. as input and outputs an evaluation score of the end-user. The service data is usage history etc. obtained from platform 3. The neural network is, for example, an RNN (Recurrent Neural Network), a Long Short-Term Memory (LSTM) network, or a Transformer, and has an input layer that accepts deposit and withdrawal data, accounting data, and service data as input, and an output layer that outputs an evaluation score. Note that the credit scoring model 141 may also be a model constructed with other learning algorithms other than neural networks, such as Bayesian networks or decision trees.

[0047] Furthermore, instead of entering accounting data, which is information on the use of the accounting system, into the credit model 141, the cash flow derived from the accounting data may be entered. The deposit and withdrawal data may also include other account information, such as the number of years elapsed since opening or the average balance for each specified period. In addition, the service data entered into the credit model 141 may be a business viability assessment value derived from the usage history, rather than the usage history of Platform 3. For example, the business viability assessment may be performed based on the frequency of use and the amount of use derived from the usage history.

[0048] The input layer has multiple neurons that accept deposit / withdrawal data, accounting data, and service data as inputs, and passes the input item values ​​to the hidden layer. The hidden layer has a configuration in which a convolution layer that convolves each value input from the input layer and a pooling layer that maps the values ​​convolved in the convolution layer are alternately connected, compressing the input information and finally extracting an evaluation value. The output layer outputs an evaluation score based on the evaluation value output from the hidden layer. The evaluation score is, for example, a default probability and takes a value from 0 to 1. Alternatively, the evaluation score may be a value equivalent to a rating.

[0049] The credit scoring model 141 is generated using training data consisting of deposit and withdrawal data, accounting data, service data, and labels (ground truth scores) as follows: Server 1 inputs the deposit and withdrawal data, accounting data, and service data included in the training data into the input layer, performs calculations in the hidden layer, and obtains the score from the output layer. Server 1 compares the score output from the output layer with the labels included in the training data, i.e., the ground truth values, and optimizes the parameters used in the calculations in the hidden layer so that the output value of the output node approaches the ground truth value. These parameters include, for example, the weights (connection coefficients) between neurons and the coefficients of the activation function used in each neuron. The method of parameter optimization is not particularly limited, but for example, Server 1 uses backpropagation to optimize various parameters. Server 1 performs the above learning process using all the training data and generates the trained credit scoring model 141.

[0050] When using credit model 141 for preliminary screening, the control unit 11 of server 1 acquires the evaluation score or rating value output by credit model 141. The control unit 11 determines the loan amount, etc., based on the evaluation score or rating value, the end user's account balance and changes in the account balance, sales, capital, etc.

[0051] The credit scoring model 141 shown in Figure 22 takes four types of data as input: deposit and withdrawal data, accounting data, platform A data, and platform B data. However, it is desirable to train the credit scoring model 141 so that it can produce a reasonable output even when only one type of data is input. Furthermore, regarding the platform data, it is desirable to train the credit scoring model 141 so that it can produce a reasonable output not only when two types of data are input, but also when one type or three or more types of data are input.

[0052] (Embodiment 2) This embodiment relates to a method for evaluating the business viability of an end-user from multiple perspectives. Figure 23 is an explanatory diagram showing an example structure of a business viability evaluation model. The business viability evaluation model 142 is a neural network that takes data from platform 3 used by the end-user as input, evaluates the business viability of the end-user from multiple perspectives, and outputs evaluation values ​​for each perspective. The input data is the usage history of platform 3 obtained from platform 3. The neural network is, for example, a CNN, and has an input layer that accepts data input and an output layer that outputs evaluation values ​​for each perspective. The perspectives are, for example, management efficiency, transaction opportunities, competitive environment, market size, and need for fundraising. Other sets of perspectives may include product strength, production capacity, sales and marketing capabilities, customer base, and organizational management capabilities. The input data may also include deposit and withdrawal data and accounting data.

[0053] The input layer has multiple neurons that accept various data as inputs and passes the input values ​​to the hidden layer. The hidden layer has a configuration in which convolution layers that convolve each value input from the input layer and pooling layers that map the values ​​convolved in the convolution layer are alternately connected, compressing the input information and finally extracting evaluation values. The output layer outputs evaluation values ​​for each aspect based on the evaluation values ​​output from the hidden layer. The evaluation values ​​may be discrete values ​​such as 1, 2, 3, 4, or 5, or continuous values ​​from 0 to 1.

[0054] In the following explanation, we will assume that the business feasibility assessment model 142 is a CNN, but the business feasibility assessment model 142 is not limited to CNNs and may be a model constructed with other learning algorithms such as neural networks other than CNNs, Bayesian networks, or decision trees.

[0055] The business feasibility assessment model 142 is generated as follows using training data consisting of various input data and labels (ground truth evaluation values) for each perspective. Server 1 inputs the various data included in the training data into the input layer, performs calculations in the hidden layer, and obtains evaluation values ​​for each perspective from the output layer. Server 1 compares the evaluation values ​​for each perspective output from the output layer with the labels for each perspective included in the training data, i.e., the ground truth values ​​for each perspective, and optimizes the parameters used in the calculations in the hidden layer so that the output value of the output node approaches the ground truth value. These parameters include, for example, the weights (connection coefficients) between neurons and the coefficients of the activation function used in each neuron. The method of parameter optimization is not particularly limited, but for example, Server 1 optimizes various parameters using backpropagation. Server 1 performs the above learning process using all the training data and generates the trained business feasibility assessment model 142. The business feasibility assessment model 142 may also be used as the third model 1413 that constitutes the credit scoring model 141.

[0056] Figure 24 is an explanatory diagram showing an example of an evaluation results database. Evaluation results database 137 stores the results of the business feasibility evaluation for each end user. Evaluation results database 137 includes columns for User ID, Overall Evaluation Score, Management Efficiency, Transaction Opportunities, Competitive Environment, Market Size, and Need for Funding. The User ID column stores the user ID. The Overall Evaluation Score column stores the overall score of the business feasibility evaluation. The overall score is calculated based on the scores for each perspective. For example, the overall score is the average score of the evaluation for each perspective. The overall score may also be the sum of the scores for each perspective. The Management Efficiency column stores the evaluation score for management efficiency. The Transaction Opportunities column stores the evaluation score for transaction opportunities. The Competitive Environment column stores the evaluation score for the competitive environment. The Market Size column stores the evaluation score for market size. The Need for Funding column stores the evaluation score for the need for funding.

[0057] Figure 25 is a flowchart illustrating an example of the business feasibility assessment process. The business feasibility assessment process evaluates the business feasibility of an end user from data on platform 3. The control unit 11 of server 1 acquires data (step S81). The data to be acquired is data from platform 3 that has already been linked. The control unit 11 inputs the acquired data into the business feasibility assessment model 142 (step S82). The control unit 11 obtains evaluation values ​​for each perspective from the business feasibility assessment model 142 (step S83). The control unit 11 calculates an overall evaluation score from the evaluation values ​​for each perspective (step S84). The control unit 11 stores the evaluation values ​​for each perspective and the overall evaluation score in the evaluation result DB 137 (step S85) and terminates the process. The business feasibility assessment process is executed when an end user logs in. It can also be executed periodically by batch processing, etc.

[0058] Next, we will describe the screens displayed by terminal 2. Most of the screens displayed by terminal 2 are the same as in Embodiment 1, but we will describe a home screen that is different from Embodiment 1. Figure 26 is an explanatory diagram showing another example of the home screen. Home screen d08 shown in Figure 26 is the screen displayed after data linkage and preliminary screening have been completed. Home screen d08 includes deposit / withdrawal information display d081, deposit / withdrawal evaluation value d082, accounting information display d083, accounting evaluation value d084, business feasibility evaluation display d085, business feasibility evaluation value d086, bank display d087, accounting service display d088, application button d089, list button d08A, and amount display d08B. Deposit / withdrawal information display d081, accounting information display d083, and business feasibility evaluation display d085 indicate the evaluation items for the end user. The deposit / withdrawal evaluation value d082, accounting evaluation value d084, and business viability evaluation value d086 represent the end user's evaluation based on deposit / withdrawal information, accounting information, and service information obtained from Platform 3, respectively. The bank display d087 shows the bank with which deposit / withdrawal information is linked. The accounting service display d088 shows the accounting service with which accounting information is linked. When the end user selects the application button d089, a loan application request is sent from Terminal 2 to Server 1. Selecting the list button d08A displays a list of financial institutions, accounting services, and Platform 3 with which data can be linked. The amount display d08B shows the amount the end user can borrow.

[0059] This embodiment provides the following benefits: By utilizing the business feasibility assessment model 142, it becomes possible to evaluate the business feasibility of end users from multiple common perspectives (common evaluation axes) using service data acquired from multiple platform providers 3.

[0060] (Utilization of business feasibility assessment) This section describes the functions provided by Ecosystem 100 to enable end users to utilize the results of the business feasibility assessment. Figure 27 is an explanatory diagram showing another example of the home screen. In the configuration of home screen d09 shown in Figure 27, the symbols and explanations are omitted for configurations that are similar to those already described. Home screen d09 shown in Figure 27 shows the results of the business feasibility assessment by perspective. Home screen d09 includes evaluation results d091 and linked service display d092. Evaluation results d091 shows the business feasibility assessment by perspective. In the example shown in Figure 27, the perspectives of the business feasibility assessment are five: management efficiency, transaction opportunities, competitive environment, market size, and need for funding. These five perspectives are consistent with the business feasibility assessment model 142. The evaluation value for each perspective is based on the output from the business feasibility assessment model 142. Each perspective of the business feasibility assessment is rated on a 5-point scale, with 1 being the lowest rating and 5 being the highest rating. Black stars indicate the evaluation value. For example, management efficiency shows 2 stars and an evaluation value of 2. In Figure 27, market size has not been evaluated, so to indicate this, it is displayed in a smaller font and with thinner text than other perspectives. The linked service display d092 shows services provided by Platformer 3 that enable data linkage. Within the linked service display d092, the normal display shows services for which the end user has already set up data linkage. Services displayed in a smaller font and with thinner text show services for which data linkage has not been set up. For services for which data linkage has not been set up, the linked service display d092 may select and display services that the end user should set up and use, based on the results of the end user's business feasibility evaluation. Note that the method of displaying evaluation values ​​for each perspective is not limited to that shown in Figure 27. For example, it may be shown using a radar chart. Also, multiple evaluation values ​​for each perspective may be stored in association with the evaluation time, and the trend of evaluation values ​​may be displayed using a line graph or the like.

[0061] Figure 28 is an explanatory diagram showing an example of a list screen. The list screen d10 displays a list of financial institutions, platform 3, or services provided by platform 3 that can be linked with data. The list screen d10 includes a linking partner name field d101, a type field d102, a legend display d103, a processing selection field d104, radio buttons d105, and an add button d106. The linking partner name field d101 displays the name of the financial institution or service provided that can be linked with data. The type field d102 displays the type of information obtained through data linking, or the perspectives of business feasibility assessment that can be evaluated. The legend display d103 displays the legend for the type field d102. In the type field d102, the corresponding perspective is displayed in inverted black and white. For example, it indicates that data linking with IJ Net Service will provide data for business feasibility assessment regarding market size and the need for fundraising. The data for setting the type field d102 is stored in the platform DB134 in advance. The processing selection field d104 is where you select the processing for each data link destination. In Figure 28, three types of processing are displayed: New Use, Link, and Cancel. New Use is selected when you wish to open an account or register as a user. Link is selected when you wish to link data. If you do not have an account with the selected financial institution or have not completed user registration for the selected service, and you select Link, the end user will be prompted to select a hyperlink on the login information input screen that will take them to the screen where they can open an account or register as a user. Selecting Cancel will cancel the data link. For financial institutions and services that are already linked, New Use and Link are not selectable, and only Cancel is selectable. Radio button d105 is used to select the target financial institution or service when starting data linkage with multiple financial institutions or platform 3. Selecting the Add button d106 will execute the setup process for data linkage with the financial institution or platform 3 selected with radio button d105, and the data linkage process described above.In the example in Figure 28, EF Net Service, IJ Net Service, KL Net Service, MN Net Service, and OP Net Service are selected by radio button d105. Therefore, selecting the add button d106 will sequentially execute data linkage processing for these five services. Note that the type of information displayed in the type column d102 and the business feasibility evaluation criteria are examples only; other types and criteria can also be used.

[0062] Figure 29 is a flowchart showing an example of the procedure for creating a list screen. The control unit 11 of Server 1 receives a request for a list of data linkage destinations from Terminal 2 (Step S101). The control unit 11 obtains services that the end user has already linked data with (linked services) (Step S102). Linked services can be obtained from the linkage account DB 132. The control unit 11 selects services that are candidates for data linkage (candidate services) (Step S103). The control unit 11 extracts linkable services from Platform DB 134. The services extracted by the control unit 11, excluding linked services, become candidate services. The control unit 11 performs filtering. For each candidate service, it obtains the business feasibility evaluation perspectives that can be evaluated through data linkage from Platform DB 134. It also obtains the evaluation values ​​for each business feasibility evaluation perspective from the evaluation results DB 137, etc. The control unit 11 sorts the evaluation values ​​in ascending order and selects the top two perspectives. The control unit 11 narrows down the candidate services to those corresponding to the selected perspective (step S104), and creates a list of the narrowed-down services (step S105). The control unit 11 sends the created list to terminal 2 (step S106), and terminates the process.

[0063] In this way, by utilizing the results of end-user business feasibility assessments when displaying a list of candidate services for data integration, it becomes possible to display a list of services provided by Platform 3 that contribute to the growth of end-users. This list display is an example of recommended information. As a result, it is expected that end-users will start using Platform 3's services and their business feasibility assessments will improve. Consequently, Ecosystem 100 will enable end-users and Platform 3 to build a win-win relationship.

[0064] (Incentives provided) Incentives may be offered to encourage end users to link their data with Platform 3. Examples of incentive provision are described below.

[0065] Figure 30 is an explanatory diagram showing an example of a grant condition database. Grant condition database 138 stores the conditions for granting incentives, in this case points, to end users. Grant condition database 138 includes columns for condition ID, business feasibility evaluation, grant interval, expiration date, and number of points. The condition ID column stores a condition ID that uniquely identifies the grant condition. The business feasibility evaluation column stores the conditions for business feasibility evaluation required to receive the grant. The business feasibility evaluation column further includes columns for overall evaluation score, management efficiency, transaction opportunities, competitive environment, market size, and need for funding. The overall evaluation score column stores the overall score of the business feasibility evaluation. The management efficiency, transaction opportunities, competitive environment, market size, and need for funding columns each store evaluation values ​​from the perspectives of management efficiency, transaction opportunities, competitive environment, market size, and need for funding, respectively. The grant interval column stores the interval at which points are granted. The expiration date column stores the expiration date of the points. The point sequence stores the number of points to be awarded.

[0066] Figure 31 is an explanatory diagram showing an example of a rewards database. Rewards database 139 stores information about rewards obtained by using points. Rewards database 139 includes a reward ID column, an eligible recipient column, a content column, and a point count column. The reward ID column stores a reward ID that can uniquely identify the reward. The eligible recipient column stores the ID of the financial institution or platform 3 that can use the reward. The content column stores the content of the reward. The point count column stores the number of points required to use the reward.

[0067] Figure 32 is an explanatory diagram showing an example of a point grant history database. The point grant history database 13A stores the history of point grants to end users. The point grant history database 13A includes columns for User ID, Condition ID, Grant Date, Expiry Date, Status, and Points. The User ID column stores the User ID of the end user to whom points were granted. The Condition ID column stores the Condition ID of the grant condition that triggered the point grant. The Grant Date column stores the date on which points were granted to the end user. The Expiry Date column stores the expiration date of the points. The Status column stores the status of the points. The status can be, for example, Unused or Used. The Points column stores the quantity of points granted to the end user.

[0068] Figure 33 is a flowchart illustrating an example of the point granting process. The point granting process is executed when an end user logs in, when a preliminary review is performed, etc. The control unit 11 of Server 1 obtains the results of the end user's business feasibility assessment (step S121). The control unit 11 refers to the granting condition DB 138 and extracts granting conditions that match the results of the business feasibility assessment (step S122). The control unit 11 selects one of the extracted granting conditions (step S123). The control unit 11 obtains the most recent point granting date based on the selected granting condition (step S124). The control unit 11 determines whether or not to grant points (step S125). If the granting interval condition included in the granting condition is met based on the obtained granting date and the current date, the control unit 11 determines to grant points. If the granting interval condition is not met, the control unit 11 determines not to grant points. If the control unit 11 determines to grant points (YES in step S125), it stores the points to be granted in the granting history DB 13A (step S126). After step S126, or if the control unit 11 determines that no points should be awarded (NO in step S125), it determines whether there are any unprocessed awarding conditions (step S127). If the control unit 11 determines that there are unprocessed awarding conditions (YES in step S127), it returns to step S123 and processes the unprocessed awarding conditions. If the control unit 11 determines that there are no unprocessed awarding conditions (NO in step S127), it refers to the rewards DB 139 and extracts the rewards to which the awarded points can be used (step S128). The control unit 11 sends an awarding message to terminal 2 indicating that points have been awarded, along with information on the available rewards (step S129), and terminates the process.

[0069] Figure 34 is an explanatory diagram showing an example of a point award notification screen. The point award notification screen d11 is displayed as a pop-up screen, for example, overlaid on the home screen. The point award notification screen d11 includes an award message d111, an available benefits display d112, and a close button d113. The award message d111 is a message informing the user that points have been awarded and includes the number of points awarded. The available benefits display d112 displays the benefits that can be used with the awarded points. When the end user selects the close button d113, the control unit 21 of terminal 2 closes the point award notification screen.

[0070] End users can expect an increase in their business viability rating and the corresponding point gain by using the services provided by Platform 3. This, in turn, motivates end users to increase their use of Platform 3 and improve its rating.

[0071] The results of the point awarding process may be notified to Platform 3, which the end user is using. The aforementioned point awarding notification screen may then be displayed when the end user logs into Platform 3. Furthermore, it is desirable that Platform 3 be able to access the awarding history DB13A, and that end users be able to check the number of points they hold on the Platform 3 user screen. It is also desirable that the benefits that can be received using points be displayed in a list on the Platform 3 user screen.

[0072] The method of awarding points is not limited to those described above. Regardless of the results of the business feasibility assessment, points may be awarded periodically, for example, monthly, based on the number and duration of data linkages with Platform 3. Regarding benefits, they are not limited to being usable in exchange for points; end users who have data linkages with Platform 3 may be allowed to use the benefits.

[0073] (Verification of the integrity of personal data) The verification of the integrity of personal data is as follows: This function aims to enhance the reliability of user information by verifying the consistency between the user information held by Server 1 and the user information held by the linked platform 3. Specifically, when the above data linkage process is executed, Server 1 becomes able to obtain user information from platform 3, and then executes the process to verify the integrity of personal data.

[0074] Figure 35 is a flowchart illustrating an example of the consistency verification process. The control unit 11 of Server 1 acquires personal information (step S131). The control unit 11 acquires personal information from a platform that has already completed data linkage processing and stores it in the auxiliary storage unit 13. The control unit 11 verifies the consistency between the end user's personal information acquired from the platform and the end user information stored in the user DB 131 (step S132). The control unit 11 verifies the consistency between items common to the received personal information and the user information stored in the user DB 131, such as name, email address, and address. The control unit 11 stores the consistency verification result (step S133) and terminates the process. For example, the verification result may be "Consistent" or "Inconsistent".

[0075] The verification results may be scored. For end users who have completed data linkage with multiple platform providers, the score is determined by the number of platform provider personal information entries that are determined to be consistent with the personal information stored in user DB131. Additionally, when obtaining personal information from platform provider 3, information on whether verification has been performed via eKYC, etc., is also obtained, and the score may be reduced if personal verification has not been performed on platform provider 3.

[0076] The consistency check process is intended to be performed during the final review, which follows the preliminary review. Therefore, the results of the consistency check will not be notified to the end user during the consistency check process. However, if the check result is "no consistency" and the "final review" is terminated at that point, the end user may be notified accordingly.

[0077] If Platform 3 performs account aggregation and holds deposit and withdrawal data for financial institution accounts used by end users, Platform 3 may send the personal information linked to those accounts to Server 1. Financial institutions are particularly careful in verifying identity, so if the information is consistent with the data held by the financial institution, the reliability of the information will be increased.

[0078] (Checking the consistency of related data) The related data consistency verification function is as follows: When an end user has configured data linkage with multiple platform 3s, this function verifies whether the data is consistent by using the relationships between the data provided by each platform 3. If the data is consistent, it can be said that the owner of the data linked from each platform 3 is the same person. For example, if Server 1 can access inventory data from the first platform 3, order data from the second platform 3, and account data from the third platform 3, it is possible to verify the consistency of the data using the relationships between these three types of data. The following explanation describes an example of verifying the consistency of inventory data, accounting data, and account data.

[0079] Figure 36 is a table illustrating an example of consistent related data. The rows "Inventory Decrease (Sales)", "Inventory Increase (Purchases)", and "Inventory Value (End of Month)" represent inventory data. The rows "Sales Amount" and "Purchases Amount" represent accounting data. "Received Amount" and "Payment Amount" represent account data. For example, in January 2022, inventory decreased due to sales, and the value in the "Inventory Decrease (Sales)" row is 100. Correspondingly, a sales amount of 120 is recorded in the "Sales Amount" row. Then, in March 2022, a receipt of 120 corresponding to the sales is recorded in the "Received Amount" row, confirming the consistency of inventory data, accounting data, and account data. Furthermore, the value in the "Inventory Decrease (Sales)" row indicates that inventory decreased by 120 due to sales in February 2022. Correspondingly, the value in the "Inventory Increase (Purchases)" row indicates that a purchase of 120 was made in March 2022. Accordingly, 120 is recorded in the "Purchases Amount" row. Then, in May 2022, payment for the purchase was made, and 120 was recorded in the "Payment Amount" line. This sequence of events confirms that the inventory data, accounting data, and account data are consistent.

[0080] Figure 37 is a graph illustrating an example of consistent related data. The vertical axis represents monetary value, for example, in millions of yen. The horizontal axis represents months and years. Figure 37 shows the time progression of inventory reduction (sales) and payment received. As mentioned above, there is a time lag between the sale and the receipt of payment, and the amounts do not match, but the shape of the graph visually confirms that the two data sets are consistent.

[0081] Figure 38 is a table showing an example of related data whose consistency is questionable. In Figure 38, the relationship between "Inventory Decrease (Sales)" and "Sales Amount" has changed since September 2022. Since "Sales Amount" and "Receipt Amount" are related, it can be detected that the relationship between "Inventory Decrease (Sales)" and "Receipt Amount" has changed, raising concerns about the consistency of inventory data, accounting data, and account data.

[0082] Figure 39 is a graph showing an example of related data whose consistency is questionable. The axes and values ​​shown are the same as in Figure 37. As mentioned above, there is a time lag between "inventory decrease (sales)" and "amount received," and although the amounts do not match, the shape of the graphs should be similar. However, in the area enclosed by the ellipse, the shapes of the two graphs are clearly different, and it is clear that the data consistency is questionable.

[0083] Figure 40 is a flowchart showing an example of the procedure for verifying the consistency of related data. The control unit 11 of server 1 acquires data items (hereinafter referred to as "integrated items") obtained from platform 3 through data linkage (step S151). The linked items are stored in the auxiliary storage unit 13. The control unit 11 uses the linked items (for example, data items included in inventory data, accounting data, and account data) to search for rules that can be used to verify consistency (step S152). The rules are stored in the auxiliary storage unit 13 in advance. The control unit 11 determines whether or not there are usable rules (step S153). If there is a hit in the search, the control unit 11 determines that there are rules; if there is no hit in the search, the control unit 11 determines that there are no rules. If the control unit 11 determines that there are usable rules (YES in step S153), it acquires data to verify consistency based on the rules (step S154). The control unit 11 verifies the consistency of the acquired data (step S155). For example, it calculates "sales ÷ inventory decrease amount" on a monthly basis. Based on the calculated values, the control unit 11 determines that there is an inconsistency if there are three consecutive months where the average value for all companies (or the same industry) falls outside the range of 1.0 to 1.4, using 1.2 (standard deviation of 0.1) as the baseline. The control unit 11 stores the consistency check result (step S156) and terminates the process. For example, the check result may be "Consistency found" or "Inconsistency not found". If the control unit 11 determines that there are no usable rules (NO in step S153), it sets the result to "Unable to confirm" (step S157) and terminates the process.

[0084] The related data integrity verification process is intended to be performed during the final review, which follows the preliminary review. Therefore, the results of the integrity verification process will not be notified to the end user. However, if the verification result is "no integrity" and the "final review" is terminated at that point, the end user may be notified accordingly. In addition, restrictions on the end user's use of Ecosystem 100 may be imposed.

[0085] (Integration function for results from multiple models) As shown in Figure 10, the credit scoring model 141 can also be configured to combine the results of multiple models and output a review result such as whether or not to grant a loan. The function of integrating the results of multiple models will be explained below. In Figure 10, the symbol 1414 represents a combiner, and it was stated that the combiner 1414 combines the judgment results of the first model 1411, the second model 1412, and the third model 1413 and outputs a final judgment result. However, the following explanation will use the term "integration" rather than "combination" because the latter is a more appropriate term.

[0086] The following explanation shows an example of integrating the results of two models, Model A and Model B. The two models may be the accounting model, deposit / withdrawal model, or service model mentioned above, or they may not be. Models A and B take end-user accounting data, deposit / withdrawal information from financial accounts, inventory data, etc. as input and output a judgment result. The judgment result is assumed to include the PD (Probability of Default) value and the loanable amount. A larger PD value indicates a higher probability of default, and a smaller PD value indicates a lower probability of default. The PD value output by Model A is used to determine the PD A The PD value output by Model B is PD B Let's assume that the end user's PD value is calculated as follows.

[0087] PD value = α × PD A +β×PD B 0≦α≦1, 0≦β≦1

[0088] α and β are coefficients. α and β depend on the end user's industry and PD. A and PD B It may be varied depending on the range of values.

[0089] Next, I will explain how interest rates are determined. First, the base interest rate is calculated. For example, the base interest rate may be the sum of the PD value, the expense ratio, and the profit margin. The expense ratio and profit margin are predetermined, but it is desirable to review them periodically.

[0090] Next, the preferential interest rate is calculated. The value of the preferential interest rate is determined by the number of data points obtained (number of data types provided) and the number of business feasibility assessments that can be performed through data linkage (number of business feasibility assessment scores), which are determined by the end user's permission to link data between other systems and Ecosystem 100. For example, it is calculated as follows:

[0091] X = r1 × (number of data types provided) Y = r² × (number of project evaluation scores) 0 <r1<1、0<r2<1 Preferential interest rate = min{upper limit,X+Y}

[0092] min{value1, value2} means that the smaller of value1 and value2 will be used. The lending interest rate will be the base interest rate minus the preferential interest rate.

[0093] Furthermore, if the PD values ​​output by the learning models (in this case, Model A and Model B) can be evaluated as having taken into full consideration the number of data types provided and the number of business evaluation scores, then it is not necessary to calculate the preferential interest rate.

[0094] Let's explain how the loan amount can be determined. For example, similar to the PD value, the loan amount can be determined by adding the weighted sum of the loan amounts output by the two learning models.

[0095] Loan amount = γ × (Loan amount for Model A) + δ × (Loan amount for Model B) 0≦γ≦1, 0≦δ≦1, where γ≠0 or δ≠0

[0096] γ and δ are coefficients. γ and δ depend on the end user's industry and PD. A and PD B The value range may be adjusted accordingly. If the learning model does not output the loan amount, the loan amount may be calculated based on the data input to the learning model. Furthermore, if the end user has taken out a loan between the reference point when the learning model determined the loan amount and the processing point, it is desirable to use the amount obtained by subtracting the amount of that loan from the loan amount output by the learning model as the loan amount determined by the learning model.

[0097] Next, we will explain the review process using the function to integrate the results of multiple models. Figure 41 is a flowchart of an example of the review process procedure. The review process is performed on server 1 and is executed upon request from terminal 2, etc. The control unit 11 of server 1 collects the data necessary for the review (step S171). The control unit 11 checks whether the data obtained from platform 3 with which data is linked is up to date, and updates the data if it is not up to date. The control unit 11 inputs the input data required by each model to multiple learning models and obtains the PD value output by each learning model (step S172). The control unit 11 determines one PD value (default probability of use) from the multiple PD values ​​(step S173). The control unit 11 calculates the loan interest rate using the determined PD value (step S174). The control unit 11 calculates the loan amount (step S175). The control unit 11 outputs the results (interest rate, loan amount) to terminal 2 which made the review request (step S176) and terminates the process.

[0098] The technical features (constituent elements) described in each embodiment are combinable with each other, and by combining them, new technical features can be formed. The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the present invention is indicated by the claims, not in the sense described above, and all modifications within the sense and scope equivalent to the claims are intended. [Explanation of Symbols]

[0099] 100 Ecosystems 1 server 11 Control Unit 12 Main memory 13 Auxiliary storage 131 User DB 132 Linked Account Database 133 Deposit and Withdrawal Database 134 Platformer DB 135 Representative / Business owner DB 136 Corporate Databases 137 Evaluation Results Database 138 Grant Conditions DB 139 Bonus DB 13A Assignment History DB 141 Credit Models 142 Business Feasibility Assessment Model 15 Communications Department 16 Reading section 1P Control Program 1a Portable storage medium 1b Semiconductor memory 2 terminals 21 Control Unit 22 Main memory 23 Auxiliary storage 24 Communications Department 25 Input section 26 Display section 2P control program 3 Platform B Bus N Network

Claims

1. Refer to a storage unit that stores information of platform providers that agree to provide service data to banks regarding the use of services provided by a platform provider by the said business operator, and extract the platform providers that agree to provide the service data to banks, The extracted service data of the platform provider, the account deposit and withdrawal information of the provider, or the usage information of the provider's accounting system are obtained. A model that outputs information regarding the evaluation of a business operator when the service data of the business operator's platform provider, account deposit and withdrawal information, or accounting system usage information of the business operator is input will output information regarding the evaluation of the business operator when the acquired service data of the business operator, account deposit and withdrawal information of the business operator, or accounting system usage information of the business operator is input. An information processing method characterized in that the processing is performed by a computer.

2. The information relating to the evaluation of the business operator includes evaluation values ​​for business feasibility evaluation from multiple perspectives. The information processing method according to feature 1.

3. Transmit an integrated evaluation value, which is an integrated evaluation value obtained by combining the evaluation values ​​of each of the multiple perspectives of the business feasibility evaluation, to the business operator's terminal. The information processing method according to claim 2, characterized in that the processing is performed by the computer.

4. Based on information regarding the evaluation of the business operator, the loan terms for the business operator are derived. The information processing method according to any one of claims 1 to 3, characterized in that the processing is performed by the computer.

5. After receiving the login information of the said business operator, information regarding the evaluation of the said business operator is obtained based on the service data of the said business operator's platform provider, the said account deposit and withdrawal information, or the said accounting system usage information. Based on the information obtained regarding the evaluation of the aforementioned business operator, the loan terms will be updated. The information processing method according to claim 4, characterized in that the processing is performed by the computer.

6. The platform provider acquires the personal information of the business operator that it possesses, The system checks for consistency between the acquired personal information and the user information stored in advance, and verifies the consistency of common data item values. Output the verification results. The information processing method according to any one of claims 1 to 3, characterized in that the processing is performed by the computer.

7. Retrieve multiple relevant data item values ​​included in the service data obtained from different platforms, Based on the aforementioned relationship, the consistency of the multiple data item values ​​obtained is confirmed. Output the verification results. The information processing method according to any one of claims 1 to 3, characterized in that the processing is performed by the computer.

8. Refer to a storage unit that stores information of platform providers that agree to provide service data relating to the use of services provided by a platform provider to a bank, in association with a business operator, and extract the platform providers that agree to provide the service data to a bank. The extracted service data of the platform provider, the account deposit and withdrawal information of the provider, or the usage information of the provider's accounting system are obtained. A model that outputs information regarding the evaluation of a business operator when the service data of the business operator's platform provider, account deposit and withdrawal information, or accounting system usage information of the business operator is input will output information regarding the evaluation of the business operator when the acquired service data of the business operator, account deposit and withdrawal information of the business operator, or accounting system usage information of the business operator is input. An information processing program characterized by having a computer perform the processing.

9. In an information processing device having a control unit, The control unit, The system associates a business with a platform provider and refers to a storage unit that stores information on platform providers that have agreed to provide service data regarding the business's use of the services provided by the platform provider to the bank, and extracts the platform providers that have agreed to provide the service data to the bank. The extracted service data of the platform provider, the account deposit and withdrawal information of the provider, or the usage information of the provider's accounting system are obtained. A model that outputs information regarding the evaluation of a business operator when the service data of the business operator's platform provider, account deposit and withdrawal information, or accounting system usage information of the business operator is input will output information regarding the evaluation of the business operator when the acquired service data of the business operator, account deposit and withdrawal information of the business operator, or accounting system usage information of the business operator is input. An information processing device characterized by the following:

Images