JP2018160258A - Information processor, method for processing information, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processor, a method for information processing, and a program which can select a target person and can output information including needs information on the possibility that the target person can use a specific article or risk information of using the article by the person.SOLUTION: The information processor includes: a generation unit 11 with an artificial intelligence function; and an output unit 30 for outputting the information generated by the generation unit 11. The generation unit 11 generates a plurality of pieces of target information on a plurality of target persons, and generates needs information on the possibility that one of the target persons can use a specific article or risk information on the risk of loaning money to the person, using previous record data of the target persons. The plurality of target persons include a first target person, of which information is acquired by a banking institution, and a second target person, of which information is acquired by an institution other than a banking institution.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing apparatus, an information processing method, and a program including a generation unit having an artificial intelligence function.

Conventionally, the utilization of artificial intelligence functions has been attempted, and the research field has also been diversified (see Patent Document 1). On the other hand, when providing various products (including services) to customers (including new customers), there is a need to provide the products and the risks associated with providing the products. For example, the person in charge of a company decided on its own to conduct sales activities.

JP-A-10-207504

In view of the background as described above, the present invention can select the target person himself and output the information including the risk information when the target person uses the necessary information regarding the possibility of using the predetermined product or the product. An information processing apparatus, an information processing method, and a program are provided.

An information processing apparatus according to the present invention includes:
A generation unit having an artificial intelligence function, which relates to the possibility that a certain target person uses a predetermined product using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons A generating unit that generates risk information when lending money to needs information or a certain target person;
An output unit that outputs the needs information or the risk information generated by the generation unit;
With
The generation unit selects a target person, generates the needs information or the risk information for the target person,
The plurality of target persons may include a first target person whose target person information is acquired by a financial institution and a second target person whose target person information is acquired by a person other than the financial institution.

In the information processing apparatus according to the present invention,
The generation unit may generate the needs information or the risk information for a target person other than the first target person using a plurality of first target person information regarding the plurality of first target persons.

An information processing apparatus according to the present invention includes:
A generation unit having an artificial intelligence function, which relates to the possibility that a certain target person uses a predetermined product using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons A generating unit that generates risk information when lending money to needs information or a certain target person;
An output unit that outputs the needs information or the risk information generated by the generation unit;
With
The generation unit selects a target person, generates the needs information or the risk information for the target person,
The plurality of target persons may include a second target person whose target person information is acquired by a person other than the financial institution.

In the information processing apparatus according to the present invention,
The generation unit may be able to generate the need information or the risk information for a target person other than the second target person using a plurality of second target person information regarding the plurality of second target persons.

In the information processing apparatus according to the present invention,
The generation unit uses the plurality of first subject information regarding the plurality of first subjects and the plurality of second subject information regarding the plurality of second subjects, and uses the first subject and the second subject. The need information or the risk information may be generated for a target person including a person.

In the information processing apparatus according to the present invention,
The second subject information regarding the second subject may include credit information, accounting information, or commercial flow information.

In the information processing apparatus according to the present invention,
The second subject information regarding the second subject may include inter-company electronic commerce information.

In the information processing apparatus according to the present invention,
The second subject information regarding the second subject may include payment information or product purchase information.

An information processing apparatus according to the present invention includes:
A search unit for searching for information generated by the generation unit;
The result searched by the search unit may be output by the output unit.

An information processing apparatus according to the present invention includes:
A verification unit for verifying whether or not the predetermined product is actually used by the certain target person, or whether or not the loan is actually overdue or delinquency occurs when lending money to the certain target person Prepared,
The verification result by the verification unit may be used as the past performance data regarding the need information or the risk information generated after the verification result is output.

In the information processing apparatus according to the present invention,
The generation unit may generate an employment variable and a coefficient for the employment variable using a plurality of the target person information.

In the information processing apparatus according to the present invention,
The artificial intelligence function of the generation unit may generate the needs information or the risk information using different adoption variables and different coefficients for different products.

In the information processing apparatus according to the present invention,
You may further provide the calculation part which calculates the creditable amount with respect to the said certain target person or the applicable interest rate with respect to the said certain target person from the said risk information produced | generated by the said production | generation part.

In the information processing apparatus according to the present invention,
The first target person information regarding the first target person may be generated based on information acquired by a plurality of financial institutions.

An information processing method according to the present invention includes:
Need information on the possibility that a target person uses a predetermined product by using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons by a generation unit having an artificial intelligence function Or generating risk information when lending money to the target person,
Outputting the needs information or the risk information generated by the generation unit;
With
The generation unit selects a target person, generates the needs information or the risk information for the target person,
The plurality of target persons include a first target person whose target person information is acquired by a financial institution and a second target person whose target person information is acquired by a person other than the financial institution, or a target person who is not a financial institution. The information processing method characterized by including the 2nd subject person from which information is acquired.

The program according to the present invention is:
A program for executing an information processing method,
The information processing method includes:
Need information on the possibility that a target person uses a predetermined product by using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons by a generation unit having an artificial intelligence function Or generating risk information when lending money to the target person,
Outputting the needs information or the risk information generated by the generation unit;
With
The generation unit selects a plurality of subjects, generates the needs information or the risk information for the subjects.
The plurality of target persons include a first target person whose target person information is acquired by a financial institution and a second target person whose target person information is acquired by a person other than the financial institution, or a target person who is not a financial institution. A method involving a second subject from whom information is obtained may be executed.

In the present invention, the generation unit uses a plurality of pieces of subject information for a plurality of subjects and past performance data for the plurality of subjects, and needs information relating to the possibility that a certain subject uses a predetermined product or When generating risk information when lending money to a certain target person, when the generation unit selects a certain target person and adopts an aspect that generates needs information or risk information for the target person The generating unit generates the need information or risk information for the “certain subject”. For this reason, the person in charge of a company can perform business based on the generated information, and can increase sales efficiency.

FIG. 1 is a schematic block diagram for explaining an example of a system outline including an information processing apparatus according to an embodiment of the present invention. FIG. 2 is a schematic block diagram for explaining an example of a system outline including the information processing apparatus according to the embodiment of the present invention from a viewpoint different from FIG. FIG. 3 is a diagram for explaining an aspect of information processing in the information processing apparatus according to the embodiment of the present invention. FIG. 4 is a diagram showing an aspect of information output from the information processing apparatus according to the embodiment of the present invention. FIG. 5A is a diagram showing, as an example, recruitment variables, coefficients, and the like in a card loan, and FIG. 5B is a diagram showing recruitment variables, coefficients, etc. in an automobile loan as an example. FIG. 6 is a schematic block diagram for explaining another example of the system outline including the information processing apparatus according to the embodiment of the present invention. FIG. 7 is a schematic block diagram for explaining still another example of the system outline including the information processing apparatus according to the embodiment of the present invention. FIG. 8 is a diagram showing an aspect when an analysis according to a region is performed in the embodiment of the present invention. FIG. 9 is a diagram showing another aspect of information output from the information processing apparatus according to the embodiment of the present invention. FIG. 10 is a diagram showing still another aspect of information output from the information processing apparatus according to the embodiment of the present invention.

Embodiment << Configuration >>
Embodiments of an information processing apparatus according to the present invention will be described below with reference to the drawings.

As shown in FIGS. 1, 2, 6, and 7, in this embodiment, the information processing apparatus will be described using an aspect in which it is installed in an external engine different from the first engine and the second engine described later. However, it is not limited to this. The information processing apparatus may be installed in the first engine or the second engine,
In this case, the first engine or the second engine may own and / or manage the information processing apparatus. The information processing apparatus according to the present embodiment may be composed of a single device or a plurality of devices. Further, when an information processing apparatus is configured from a plurality of devices, each device does not need to be provided in the same space such as the same room, and may be provided in different rooms, different buildings, different areas, and the like. In addition, when an information processing apparatus is configured from a plurality of devices, a part of the information processing device may be owned and / or managed by the first or second organization, and the rest may be owned and / or managed by an external organization .

In the present embodiment, the main explanation is given by taking a financial institution as an example as the first institution, but is not limited to this. As an example, the first organization includes “product” (“service” (service)).
), An external organization is an organization that provides a service using the information processing apparatus or information processing method described in this embodiment, and the second organization is an organization other than the first organization and the second organization. It may be.

As illustrated in FIG. 1, the information processing apparatus according to the present embodiment has an artificial intelligence function, a generation unit 11 that generates predetermined information, and an output unit 30 that outputs information generated by the generation unit 11. You may have. The generation unit 11 uses a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons, or needs information regarding the possibility that a target person uses a predetermined product or a target person Risk information may be generated when money is lent. The generation unit 11 may select a plurality of subjects and generate needs information or risk information for the subjects. In the present embodiment, description will be made using an aspect in which “financial products” are mainly used as “products”. However, the present invention is not limited to this, and examples of “products” include real estate, automobiles, audio equipment, art. Any product such as goods, health supplies, stationery, etc. may be included.
For these products, it is possible to generate needs information about the possibility of needing the product, and not only the risk of collecting accounts receivable (credit risk) when the product is provided, but also claims from the product provider It is also possible to generate risk information including troubles such as being issued and compliance risk that the product provider is an anti-social force. It should be noted that the “product” in the present embodiment includes a mode of providing services (services). That is, in this embodiment, even when some service (service) is provided, the provision of the service is regarded as a “product”.

The generation unit 11 may generate need information or risk information for the first target person and / or the second target person based only on the first target person information (using only the first target person information). Also,
The generation unit 11 may generate need information or risk information for the first target person and / or the second target person based only on the second target person information (using only the second target person information). In addition, the generation unit 11 may use the first target person and / or the second target person information and the second target person information (using both the first target person information and the second target person information). Need information or risk information for two subjects may be generated. The first target person and / or the second target person for which needs information or risk information is generated may be plural or singular.

The generation unit 11 uses the adoption variable generated from the subject information and the coefficient for the adoption variable, and needs information on the possibility that a certain subject uses or purchases a predetermined product and / or pays money to the subject. You may generate | occur | produce the risk information regarding the credit-failure risk at the time of loan, or a credit risk. The recruitment variable and the coefficient may be determined by the generation unit 11 based on past performance data. The past result data may include past result data input in advance and a verification result by the verification unit 16 described later (more precisely, needs information and risk information are given to the target person concerned). Verification results verified before generation may be included.)

As illustrated in FIG. 1, the information processing apparatus may include a device storage unit 20 that stores various information and a device control unit 10 that performs various controls. The generation unit 11 described above and a calculation unit 15 described later.
The verification unit 16 may be included in the device control unit 10. The device storage unit 20 may store a verification result by the verification unit 16 to be described later, in addition to data input in advance for automatically generating needs information and risk information. In addition, when a certain amount of data is accumulated, the data input in advance for generating the needs information and the risk information may be deleted. In addition, data including verification results older than a certain period (for example, two years) may be deleted. In this way, when generating needs information and risk information based only on data within a certain period (for example, within 2 years), highly accurate needs information and risk information are generated and output in line with the times. can do.

As an example of the artificial intelligence function, a classifier using a machine learning technique can be used. According to this classifier, target information such as probability of credit loss (in the case of risk model), product application (in case of needs model), etc. is targeted from target person information in a certain past period (for example, 2 years) Can be output for each person. This classifier uses machine learning technology to adopt variables that are used to make the probability of a target event most likely from past performance data (
Element) and its coefficient (weight). Then, by applying the defined recruitment variables (elements) and their coefficients (weights) to data related to the target person (= “a certain target person”), the need rate for each product related to the target person and the absolute Needs information including specific figures,
Risk information including the risk rate and absolute numerical values related to the risk is generated.

In order to output the probability that a target event will occur with respect to the target person, the generation unit 11 performs “learning” of the need model and the risk model for each product. Here, “learning” specifies the “feature” that you want to find from the data, that is, the need event such as the purchase of a product (for example, financial product) or the risk event that the loan has been delinquent. This means that adopted variables (elements) that can be classified best and their coefficients (weights) are determined by automatic trial and error. That is, in the generation unit 11, the first target person information and / or the second target person information based on the past result data is aggregated, and repeated learning is performed so that the error is minimized while changing the parameters (the tree model is changed). If it is adopted, a plurality of trees are created, and learning is repeatedly performed so as to reduce an error from past performance data), and a need model and a risk model to be applied to the target person are determined. Then, by applying the determined employment variable (element) and its coefficient (weight) to the data related to the target person, the needs information and risk information for each product related to the target person are calculated. These adopted variables (elements) and coefficients (weights) may be expressed as feature quantities.

Examples of the parameter to be changed include, for example, the number of iteration learning (for example, the number of trees in the tree model), and a coefficient used when the feature amount obtained immediately before the iteration learning is used in the next learning ( (Weight), percentage of data used during learning (meaning the amount of data used, for example, the ratio of whether 100,000 or 200,000 are used out of 1 million parameters) And the depth level at the time of learning (for example, the number of branches of the tree in the tree model). For example, when the number of iteration learning is large, the number of trees in the tree model is increased. On the other hand, when the number of iteration learning is small, the number of trees in the tree model is decreased. Further, when the depth level during learning is deep, the number of tree branches in the tree model increases, and when the depth level during learning is shallow, the number of tree branches in the tree model decreases. Note that the above-described parameters are merely examples, and the present invention is not limited to this, and the above-described parameters can be reduced or other elements can be used as parameters. In the present embodiment, the tree model is shown as an example, but the present invention is not limited to this.

The target person may include a first target person whose target person information is acquired by a first institution (for example, a financial institution). The first target person information regarding the first target person is any one of the attribute information of the first target person, the examination information regarding the first target person, and the transaction information in the first organization of the first target person. The above may be included.

The target person may include a second target person whose target person information is acquired by the second institution.
The second institution includes credit bureaus, accountant offices, tax accountant offices, accountant groups, tax accountant groups,
Organizations such as an inter-electronic e-commerce platform service provider, a supermarket, a convenience store, a department store, an electric company, a gas company, a water company, and a mobile phone company may be included.

The second target person information may include, for example, corporate credit information and personal credit information acquired by a credit research company. In addition, the second target person information includes, for example, corporate accounting information (such as financial statements) and individual accounting information (such as household account book information) acquired by an accountant office, tax accountant office, accountant organization, tax accountant organization, etc. May be. The accounting information may be acquired by accounting software or by tax consultation.

The corporate credit information may include financial information and bankruptcy information. The financial information may include corporate accounting information including financial statements and closing date data, and the financial statements may include journal information, general ledger information, balance sheet, income statement, and cash flow statement. The bankruptcy information includes, for example, the background information on how the bankruptcy resulted from bankruptcy as a result of tracing the financial statements, the closing date data, the borrowing status from financial institutions, and the like. It may be used for learning functions. If it is related to an individual rather than a company, the second target person information may include household account book information. The household account book information may be provided as, for example, a mobile phone application including a smartphone, and the household account book information registered using the application may be used.

The business credit information may include commercial flow information. The commercial flow information may include capital-related information and information related to customers of the company. As an example, this type of commercial flow information can be judged as low risk of bankruptcy if there is a company that can be trusted by affiliated companies, and continued if the group company is a top customer. It can be used as an element of needs information or risk information as a prospect of sales.

In the present embodiment, “use as one element” means, for example, adopting the element as an adopted variable and increasing the weight for the adopted variable.

The second target person information includes information indicating the size of the company and each region (including the region in the prefecture).
) Area information indicating sales and customer segment information indicating sales for each customer segment. When the regional information of a company is output, it is particularly useful for sales to corporations. In other words, sales to corporations are often carried out by sales representatives, and it may be a problem whether the sales representatives can be spent depending on the area where the corporation is located.

The second target information includes, for example, business-to-business e-commerce information such as B to B platform information (business-to-business platform information) acquired by a business-to-business e-commerce platform service provider. Service, amount, transaction date, payment date, etc. may be included.

The second target person information may include, for example, product purchase information related to the purchase of products such as POS information, electronic money information, and card information acquired by retail stores such as supermarkets, convenience stores, and department stores.

The second target information includes, for example, payment information associated with receiving provision of services such as payment information for utility bills, payment information for mobile phones, etc. acquired by electric companies, gas companies, water companies, and mobile phone companies. May be included.

The second target person information may include description information in the SNS and related information (market related information) with the market (stock price, currency exchange, etc.). When market-related information is included in the second target person information, information on the market when the second target person invests may be included. For example, the target person “A” Information that investment is made, conversely “B
May include information that an investment will be made when the stock price rises. Also,
For example, information that the target person “C” makes an investment when the yen becomes strong may be included, and conversely, information that the target person “D” makes an investment when the yen becomes weak may be included. When using such information, a rating of needs may be given as an increase in needs when the target person is likely to make an investment. As an example of the case where the description content in SNS is included in the second target person information, for example, the target person “E” borrows money when the content indicating that the money is insufficient is described in the SNS. It can be mentioned that the second subject information includes information such as

The first subject and the second subject may have overlapping portions, or all of them may overlap. That is, the first target person whose target person information is acquired by the first institution and the second target person whose target person information is acquired by the second institution may partially or entirely overlap. However, even if the target person overlaps in this way, the contents of the first target person information and the second target person information may be different. That is, the content of the first target information acquired by the first organization and the content of the second target information acquired by the second organization may be different. For example, when information is unified, the content of 1st object information and the content of 2nd object person information may be the same content.

The first target information and the second target person information may include attribute information, examination information, transaction information, other information, and the like.

As attribute information used (see FIG. 3), for example, the name, gender, date of birth, age, address, etc. can be given for individuals, and the company name, trade name, date of establishment for corporations. You can list the date, business years, location, etc. Each of the first subject information and the second subject information may include attribute information.

The attribute information may include name identification information for collectively managing the same target person. As for the case where the first information is a financial institution, a single financial institution may have a plurality of accounts. By using this name identification information, the holders of a plurality of accounts can be identified as a single target person and managed or used in subsequent processes. The name identification information includes a store number, a CIF number (Customer Information File number), a personal name identification number, a corporate number, and the like. Further, the attribute information may include an optimum approach method to the target person. That is, what means such as direct mail, telemarketing, smartphone, Internet banking, or the like is useful for the approach to the target person may be included.

Further, the attribute information may include information on persons belonging to the same household, such as information on the target person's family. Examples of the family include a person other than the person described in various application forms such as loans, a person other than the person having the same address, and a person other than the person having the same telephone number. Collecting information on persons belonging to the same household can be called household name identification. According to this household identification, if a household has multiple accounts at one financial institution,
It is possible to collect information about the account as one household and use the result to create a needs model and a risk model.

The examination information used (see FIG. 3) may include one or more of information related to the borrowing application of the subject person and credit information of the subject person. More specifically, the examination information can include, for example, occupation, place of work, place of work, annual income, and the like. The review information includes, among other things, loan review application date, “credit / loan application-related information” such as acceptance / rejection results, “internal credit information” such as black information, debtor classification, debtor rating, rating obtained from the outside Examples include “external credit information” including credit information such as information. Each of the first subject information and the second subject information may include attribute information.

The transaction information to be used (see FIG. 3) may include one or more of deposit transaction information, loan transaction information, contract information, usage service usage information, and settlement information. More specifically, as transaction information in a financial institution, for example, information relating to deposit, withdrawal, transfer, arrears and the like can be mentioned. The transaction information at financial institutions includes “deposit transaction information” such as current deposit balances, deposit / withdrawal details, deposit / withdrawal summary columns, “loan transactions” such as loan balance, credit limit, credit limit, and loan delinquency status. Information ”,“ Loan possession status, card loan contract presence / absence ”,“ Contract information ”/“ Usage information ”such as Internet banking service usage status,“ Payment information ”, etc. May be. The above-mentioned deposit / withdrawal details can include information on the deposit frequency, deposit amount, withdrawal frequency, withdrawal amount, transfer destination, transfer amount, and the like. Each of the first subject information and the second subject information may include transaction information.

Further, the transaction information may include information (for example, information on the CRM system) indicating the response (attitude) of the target person when the product is provided. Such information indicating the correspondence of the target person may be registered, for example, by the person in charge who has served the customer. The person in charge may be a person who visits a customer, a person who handles customers at a window, or a person who handles customers at a call center. Information indicating the correspondence of the target person may be acquired from a questionnaire on the Internet. Transaction information includes Internet login history, viewing / listening
Log information such as search history information may be included.

Other information used (see FIG. 3) can include information (proposal availability information) regarding whether or not direct mail or telephone contact is desired. When it is supposed that contact is not desired, the need information may not be created from the beginning, or the offer of goods for the need information may not be made to the target person.

The target person may be an individual or a corporation. Information such as attribute information related to the subject may be obtained from stores, the Internet, e-mail, direct mail, telephone, etc., or may be obtained from ATM or the like if it is the first target information in a financial institution. . When the target person is a corporation, in addition to the above, information such as attribute information may be acquired by visiting. It should be noted that examination information, transaction information, etc. of the subject person are associated with the attribute information obtained in this way by the first engine control unit 60 or the second engine control unit 160, and the first engine storage unit 61. And / or stored in the second engine storage unit 161. As shown in FIG. 1, in the present embodiment, a description is given using a mode in which a first institution control unit 60 and a first institution storage unit 61 are provided in a financial institution. However, the present invention is not limited to this. Instead, the first engine control unit 60 and / or the first engine storage unit 61 may be provided in an external engine. Similarly, as shown in FIG. 6, in the present embodiment, the second engine is described using a mode in which a second engine control unit 160 and a second engine storage unit 161 are provided. The second engine control unit 160 and / or the second engine storage unit 161 may be provided in an external engine without being limited thereto.

Also, a plurality of systems may be responsible for the functions of the first engine storage unit 61 and the first engine control unit 60, and it is assumed that the first engine control unit 60 and the first engine storage unit 61 are provided in the financial institution. Then, any one or more of the MCIF, the examination system, the approval system, the core system, the CRM system, and the EBM system, which will be described later, are included in the first engine storage unit 61 and the first engine control unit 6.
It may have a zero function. Similarly, a plurality of systems may serve the functions of the second engine storage unit 161 and the second engine control unit 160, and one or more systems may function the second engine storage unit 161 and the second engine control unit 160. You may be responsible.

Each of the first engine and the second engine has a first engine display unit 62 (see FIG. 1) and a second engine display unit 162 (see FIG. 6) on which information output from the output unit 30 is displayed. The information processing apparatus may include the apparatus display unit 19 (see FIGS. 1 and 6).

The flow of information in a financial institution will be described as an example. As shown in FIG. 2, based on the target person information acquired from the target person, the target person is examined in the financial institution, booked, and accounted for. It is stored in the first engine storage unit 61 as information or the like. “Target Person Information” is MCIF (Marketing Customer Infor, a customer database that uses financial institutions.
mation file), examination system, approval system, core system, etc. The first engine control unit 60 and the first engine storage unit 61 may be included in the MCIF, the examination system, the approval system, the backbone system, and the like.

Financial institutions include CRM (Customer Relations), which records and manages the attributes and contact history of the subject.
Hip Management) system and EBM (Event Based Marketing) to infer the events (events) that happened to the target people such as employment, marriage, home purchase, retirement, etc., and to propose appropriate products and services at the optimal timing A system may be provided (see FIG. 2). The first engine storage unit 61 and the first engine control unit 60 described above may be included in these CRM systems and / or EBM systems.

Examples of the predetermined financial products include card loans, education loans, mortgages, car loans, insurance, investment trusts and the like for individuals. On the other hand, for corporations, working capital loans, capital investment loans, insurance, operational products and the like can be cited.

Whether or not needs information and risk information are created may be determined in accordance with the contents of a product such as a financial product. The embodiment shown in FIG. 3 uses an example in which financial products are provided, but needs models and risk models for new card loans, extreme card loan increase / decrease frames, education loans, car loans, mortgages and other loans. The generation part 11 can generate | occur | produce and both needs information and risk information are produced about these. On the other hand, for insurance and investment trust, the generation unit 11 generates only the needs model,
For these, only needs information is created and risk information is not created. Note that “AI” in FIG. 3 is an acronym for “artificial intelligence” and means “artificial intelligence”.

The generation unit 11 may generate needs information and risk information for different products using different adoption variables and different coefficients. As an example of financial products, different recruitment variables differ for different financial products such as card loans, education loans, mortgages, car loans, insurance, investment trusts, working capital loans, capital investment loans, and investment products. A coefficient may be used. In FIG. 5A, as an example, the adoption variable (“Feature” in the figure) and the coefficient (“Gain” in the figure) in the card loan are shown, and in FIG. 5B, as another example, the automobile Employment variables ("Feature" in the figure) and coefficients ("Gain" in the figure)
"It is shown. By comparing FIG. 5A and FIG. 5B, it can be understood that different adoption variables and different coefficients are used in these card loans and automobile loans.

As illustrated in FIG. 1, the information processing apparatus may include a calculation unit 15 that calculates predetermined data. The calculation unit 15 may have a function of calculating an assumed profit for the target person using the borrowing amount of the target person, interest rate and expense information for the borrowing, and the like. In addition to or instead of this function, the calculation unit 15 calculates the creditable amount for the target person and / or the applicable interest rate for the target person from the attribute information and risk information generated by the generation unit 11. It may have a function. In addition, when the calculation unit 15 has a function of calculating the assumed revenue,
The borrowing amount may be determined within a creditable amount determined based on the attribute information and risk information for the target person, and the interest rate (= applicable interest rate) may also be determined based on the attribute information and risk information. If the borrowing amount or interest rate is changed, based on the changed borrowing amount and interest rate,
Risk information for the subject may be generated again. Within the range of creditable amount may be the maximum amount of creditable amount or any amount less than that. The calculation unit may determine the borrowing amount with a plurality of amounts and calculate the assumed profit for each borrowing amount.

As shown in FIG. 1, the information processing apparatus determines whether or not a predetermined product is actually used by a target person (including whether or not an application has been made for the predetermined product) or a certain target. It may further include a verification unit 16 that verifies whether or not an actual loan has occurred or an overdue has occurred when lending money to a person. When such a verification unit 16 is provided, the generation unit 11 adds the verification result by the verification unit 16 in addition to or instead of the information input in advance (more precisely, to a certain target person). On the other hand, needs information and / or risk information may be generated using a verification result verified before generating needs information and risk information. The “
The verification result by the verification unit 16 regarding the “certain subject” is used as past performance data regarding the need information and / or risk information generated after the verification result is issued.

The information processing apparatus relates to each of a plurality of products (for example, financial products) provided by the first organization.
The generation unit 11 may generate needs information and / or risk information. Each of the plurality of needs information and risk information generated in this way may be output as a list by the output unit 30. If it demonstrates using the aspect shown in FIG. 3, a new card loan,
The output unit 30 outputs a list of needs information and risk information about card loan extreme increase / decrease frames, education loans, car loans, mortgages and other loans, and needs information about insurance and investment trusts.

The output needs information and risk information are sent to the first engine or the second engine and stored in the first engine storage unit 61 (see FIG. 1) of the first engine or the second engine storage unit 161 of the second engine. Will be. And offer of goods to a candidate is proposed via a CRM system of an 1st organization, an EBM system, etc. (refer to Drawing 2), or a system of a 2nd organization. This proposal may be made to the person in charge of the first or second organization, or may be made directly to the subject.
When a proposal is made to the person in charge of the first or second institution, the first institution is a financial institution such as a contact or call center of the first or second institution, e-mail, direct mail, etc. In such a case, use of the product may be proposed to the target person from the person in charge through ATM or Internet banking. On the other hand, if the above proposal is made directly to the subject, the subject is automatically sent by e-mail, direct mail, etc., or if the first institution is a financial institution, by ATM or Internet banking. The use of a product may be proposed. In addition, for those who use inter-company e-commerce information, on-site lending (on-line financing) should be proposed on a site that uses inter-company e-commerce (for example, the login screen of the target person). Also good.

Whether or not there was an application for the proposed product from the proposed audience (within a certain period of time)
In addition, whether or not a loan is actually overdue or arrears occurred when lending money to a target person is managed and stored in, for example, a financial institution examination system, a CRM system, an EBM system, or a second institution system. Also good. In addition, the above information (whether there has been an application for the proposed product from the target person who made the proposal, and whether the loan was actually made or overdue when money was loaned to the target person) Alternatively, it may be sent from the second institution to the verification unit 16 (included in the “subject information” in FIG. 2), and verification by the verification unit 16 may be performed.
Such verification may be performed at any time, or may be performed collectively at regular intervals (for example, every week, every month, etc.). The verification result is stored in the device storage unit 20.

The generation unit 11 may randomly select a target person, and generate needs information and risk information for the target person. All the results may be output by the output unit 30, but only those that satisfy certain requirements may be output by the output unit 30. As an example, the output unit 30 may be a target person whose needs value such as a need rate or an absolute numerical value related to needs is a certain threshold (needs threshold) and / or an absolute rate related to the risk rate or risk. Only subjects whose risk values such as various numerical values are below a certain threshold (risk threshold) may be output. In particular, according to an aspect in which only those who have a need value that is greater than or equal to the need threshold and whose risk value is less than or equal to the risk threshold are targeted for output, the operator must carefully select the subject to which the product should be provided. It is beneficial in that the person can be confirmed at a glance.
It should be noted that even if a target person who satisfies the above requirements and is an output target, if he / she does not wish to contact, he / she may not make a proposal to provide a product to the target person.

The calculation unit 15 tentatively determines the borrowing amount of the target person and the balance of the account, the applicable interest rate applied to the target person, the expenses required for processing, the risk of credit collapse, credit information, and inter-company electronic commerce information. It may be calculated how much expected revenue can be expected when a loan is made to a target person. In addition, when the credit risk exceeds the first threshold, the calculation unit 15 calculates a specific applicable interest rate and / or credit amount by resetting the applied interest rate higher or reducing the credit amount. Also good. Conversely, when the credit loss risk falls below the second threshold (where the second threshold <the first threshold), the calculation unit 15 resets the applicable interest rate or increases the credit amount. Alternatively, a specific applicable interest rate and / or credit amount may be calculated. When calculating the applicable interest rate and / or credit amount, a specific interest rate and / or amount may be calculated, or an interest rate and / or amount having a certain range may be calculated.

When the first institution is a financial institution and the financial institution has, for example, a bank and a guarantee company as a group, the calculation unit 15 calculates the expected bank revenue and guarantee company revenue. You may calculate the profit as a group. As an example, the accumulated balance of money lent and the number obtained by subtracting the cost rate such as the guarantee fee rate, procurement cost rate, and administrative cost rate from the interest rate (
As an example, bank revenue may be calculated from interest rate-guarantee fee rate-procurement cost rate-office cost rate. In addition, even if the guarantee company's revenue is calculated from the accumulated balance of the loaned money, the number obtained by subtracting the cost rate such as the administrative cost rate from the guaranteed fee rate (for example, the guaranteed fee rate minus the administrative cost rate), and the credit cost Good.

When the calculation unit 15 has a function of calculating the expected revenue, the expected revenue is calculated, and the expected rate of return and the expected revenue amount when credited may be output (see FIG. 3).

The generation unit 11 includes attribute information, based on the name person or the household to which the person belongs.
The recruitment variable generated from the examination information and the transaction information and the coefficient for the recruitment variable are used to generate the needs information and risk information as a “list” for each target person, and the output unit 3 outputs the “list”.
0 may be output. At this time, needs information and risk information for a plurality of products (for example, financial products) may be generated as a “list”, and the output unit 30 may output the “list” (see FIG. 4). By making a “list” in this way, the operator can confirm at a glance which products to propose to the target person.

As shown in FIG. 4, for example, a needs rate and a needs rating may be output as the needs information. For example, a risk rate and a risk rating may be output as the risk information. Further, the need rate and the risk rate may be indicated by “%”, but may be indicated in a graph format so as to be understood at a glance (see FIG. 9). Needs ratings and risk ratings are assigned so that the target audience can be easily recognized. Further, when the calculation unit 15 calculates the creditable amount and the applicable interest rate, as shown in FIG. 4, the creditable amount and the applicable interest rate may be output as a list. In the mode shown in FIG. 4, the need rate and the need rating, the risk rate and the risk rating, and the creditable amount (shown as “advance credit amount” in FIG. 4) and for each target person and each financial product. The applicable interest rate (shown as “applicable interest rate” in FIG. 4) is shown.

The generation unit 11 generates an employment variable and a coefficient for the employment variable from any one or more of attribute information, examination information, and transaction information in “multiple” financial institutions, and uses the employment variable and the coefficient to Information and / or risk information may be generated. At this time, not only financial institutions that are affiliated but also financial institutions that have no capital relationship may use each other.

"Method"
When the information processing apparatus according to the present embodiment generates and outputs needs information and / or risk information, as an example, the following steps are performed. It should be noted that since this overlaps with the above, only a brief description will be given, but all aspects described in the above “configuration” can be applied in the “method”. In addition, a program for executing the information processing method described below may be provided. Such a program may be recorded on a recording medium, and the recording medium is stored in a PC.
By connecting to such a device, an information processing method as described below is executed by the device.

The generation unit 11 generates needs information and / or risk information for the target person using the first target person information regarding the plurality of first target persons and / or the second target person information regarding the plurality of second target persons. . At this time, the recruitment variable and the coefficient for the recruitment variable may be generated using the first subject information regarding the plurality of first subjects and / or the second subject information regarding the plurality of second subjects. Further, the employment variable and the coefficient may be determined by the generation unit 11 based on past performance data.

  Then, the information generated by the generation unit 11 is output by the output unit 30.

And based on the output information, offer of goods, such as a financial product, is proposed with respect to an object person.

The verification unit 16 determines whether or not the predetermined product is actually used by the target person, or whether or not the target product is actually overwritten or overdue when money is lent to the target person.
May be verified by Further, the subsequent needs information and / or risk information may be generated using the verification result by the verification unit 16.

《Action ・ Effect》
Next, operations and effects according to the present embodiment having the above-described configuration, which have not been described yet, will be mainly described. Note that any configuration described in “Operation / Effect” can be used as the configuration of the present embodiment.

In the present embodiment, the generation unit 11 uses a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons, and relates to the possibility that a target person uses a predetermined product. Needs information or risk information when lending money to a certain target person, and the generation unit selects a target person and adopts an aspect in which needs information or risk information for the target person is generated In such a case, the generation unit 11 generates needs information or risk information for a “subject”. For this reason,
You can know in advance from the needs information the expected success rate by providing the product,
Further, it is possible to grasp in advance the risk expected by providing the product from the risk information. As a result, the person in charge of the company can conduct business based on the generated information, and the business efficiency can be improved. As an example, a person in charge of a company with respect to customers (including new customers) who have high needs and low risk among a plurality of “subjects” generated by the generation unit 11 and output by the output unit 30. Can be considered as a business.

The “certain subject” may or may not be included in the subject who is the source of the subject information. More specifically, when outputting the need information or risk information based on the first target person information, the need information or risk information for the first target person may be generated and output. Need information or risk information for a second target person (not included in the person) may be generated and output. Conversely, when outputting the need information or risk information based on the second target person information, the need information or risk information for the second target person may be generated and output.
Need information or risk information for the first target (not included in the second target) may be generated and output.

When providing needs information or risk information for a “certain subject” included in the second subject from the first subject information, it is conceivable to adopt the following mode. First,
A model is created based on the past data for the subject who is the first subject and the second subject (for example, recruitment variables and coefficients are determined). By this, the production | generation part 11 can learn relations, such as a correlation of 1st subject information and 2nd subject information, so that needs information or risk information can be produced | generated only from 2nd subject information. Become. As a result, the generation unit 1
1 can provide needs information or risk information for “a certain target person” included in the second target person based on the second target person information (of course, the first target person information may be used). It becomes like this. It is conceivable to adopt the same mode when providing needs information or risk information for “a certain subject” included in the first subject from the second subject information. That is, first, a model is created based on past data for the target person who is the second target person and the first target person (for example, recruitment variables and coefficients are determined). By this, the production | generation part 11 can learn relations, such as a correlation of 2nd subject information and 1st subject information, and it can produce | generate needs information or risk information only from 1st subject information. Become. As a result, the generation unit 11 may use the second target person information (of course, based on the first target person information).
), It becomes possible to provide needs information or risk information for a “certain subject” included in the first subject.

When the generation unit 11 selects a plurality of target persons and generates and outputs needs information or risk information for the plurality of target persons, a plurality of target persons (arbitrary target persons) ) Needs information or risk information.

The generation unit 11 having the artificial intelligence function uses the attribute information of the target person, the examination information regarding the target person, and the transaction information in the target person's institution, and the customer or the new customer When generating and outputting needs information and / or risk information for (= a subject), the needs information and / or risk information can be output based on objective data. In addition, when using the employment variable and the coefficient with respect to the employment variable, the employment variable and the coefficient may be determined based on past performance data.

Since the production | generation part 11 can produce | generate needs information and / or risk information using attribute information, examination information, and transaction information, more highly accurate needs information and / or risk information can be output. If there is information that does not exist (for example, examination information) for the subject,
The information is processed as not existing.

In the case where the first institution is a financial institution, the target person information is acquired by the target person from whom the target person information is acquired by a person other than the first target person and the financial institution from which the target person information is acquired. In the case of adopting an aspect in which the target person is included, the need information is obtained using not only the first target person information acquired by the financial institution but also the second target person information acquired by the second institution other than the financial institution. Or it is beneficial in that it can provide risk information.

Moreover, it is a case where a financial institution uses the information processing apparatus or information processing method by this Embodiment, Comprising: A 2nd subject person is included in the subject person (a certain subject person) by which needs information or risk information is produced | generated Can be expected to provide appropriate products (for example, financial products) to individuals and / or corporations who do not use the financial institution using the generated needs information or risk information. . For this reason, it is beneficial in that financial institutions can expect to efficiently pioneer new excellent customers (new customers).

In addition, when a second institution other than a financial institution uses the information processing apparatus or information processing method according to the present embodiment, the first target is given to a target person (a target person) for which needs information or risk information is generated. In the case of adopting an aspect that includes a person, it is possible to consider whether to propose the provision of products to individuals and corporations that do not use the second institution using the generated needs information or risk information. it can. For this reason, the second organization is beneficial in that it can be expected to efficiently pioneer new excellent customers (new customers).

In addition, when both the financial institution and the second institution other than the financial institution use the information processing apparatus or the information processing method according to the present embodiment, a target person (a certain target person) for which needs information or risk information is generated ), The financial institution can not only provide existing customers (first target) with appropriate products, but also introduce new We can expect to provide appropriate products to customers (new customers) and efficiently develop new customers, and the second organization can only provide appropriate products to existing customers (second target audience) Instead, we can expect new customers to be efficiently cultivated by providing appropriate products to new superior customers (new customers).

In addition, in FIG. 10, the figure which showed typically the aspect at the time of selecting a customer (including a new customer) with a high need and a low risk using a short-term borrowing needs model and a bankruptcy forecast model is shown. . In FIG. 10, specific target persons (including target companies) are shown in the matrix, and it is shown that it is beneficial to conduct sales for the customers shown in the upper left column. Yes. In this manner, the generation unit 11 generates two or more different models (premodels) (the premodel related to risk information and the premodel related to needs information in the embodiment shown in FIG. 10), and the generation unit 11 further generates these models (premodels). Need information or risk information may be generated using a model. When such an aspect is adopted, it is beneficial in that information in the pre-model can also be used.

Based on the information generated by the generation unit 11, the output unit 30 has a good new customer.
The region, business type, company size, etc. may be output. When such an aspect is adopted, the person in charge can grasp the target person to whom the product is to be provided, and it is advantageous in that the target person to whom the business should be performed can be narrowed down. The mode shown in FIG. 9 shows a mode in which annual sales indicating the business type and the company scale are displayed.

In addition, when the person who uses the information processing apparatus or the information processing method according to the present embodiment is, for example, a local financial institution, regarding the information output from the output unit 30, by adding the area to the condition, You may make it output the data narrowed down to the target person in the sales area of a financial institution of. In this case, the data may be displayed on the first engine display unit 62 and / or the second engine display unit 162 or may be displayed on the device display unit 19. According to such an aspect, it is also advantageous in that it is possible to narrow down the target person who should conduct business while taking into account geographical elements. In the example shown in FIG. 8, an excellent new customer in the eastern region (“promising customer” in FIG. 8).
), It is possible to develop an overall sales strategy that focuses on sales in the eastern region and then focuses on sales in the western region.

The output unit 30 may separately output whether there is an existing transaction between the user and the target person. The contents output in this way may be displayed on the first engine display unit 62 and / or the second engine display unit 162. In the aspect shown in FIG. 9, after distinguishing between new customers (non-transactions) and existing customers (business partners), the needs ratings, which are needs information, and the risk ratings represented by the risk information are displayed on the display units 19, 62, 162. It is supposed to be.

When the second target person information includes business partner information and credit information, it can be expected that the main business partner (shown as “main bank” in FIG. 9) is grasped as shown in FIG. For this reason, when the first institution is a financial institution, it is possible to make a sales strategy while considering not only the output needs information and risk information but also where the main bank is. Further, the need information may be generated based on the data indicating which bank was the main bank and the past sales were successful. In other words, as one element when generating needs information,
Main bank information may be used.

A search unit may be provided, and the information generated by the generation unit 11 may be searchable. When searching for data using the search unit, it may be possible to search by inputting the region, sales, ranking of needs information (top 10 or more), product type, and the like. When such an aspect is adopted, it is advantageous in that only necessary information can be output from the output unit 30. The search unit may be provided in the first engine (“first engine search unit 67” in FIG. 1).
(See FIG. 6) (see “second engine search unit 167”), or may be provided in the first engine and the second engine. In addition to or instead of being provided in the first engine and / or the second engine, the search unit may be provided in the external engine as the device search unit 17 (FIGS. 1, 6 and 6). In FIG. 7, it is indicated as “search section”.

When the second target person information includes credit information, the risk information and needs information can be provided by incorporating the credit information. For example, if credit quality declines to a certain extent, the need to use financial products including money lending will be used as an element of needs information. It can be used as an element of risk information as high.

In particular, there is a huge amount of corporate credit information. For this reason, the accuracy of needs information and risk information can be particularly increased by using such corporate credit information. In addition, since there is a huge amount of corporate credit information in this way, for example, based on information that covers most companies that exist in Japan or that exist in a specific area, Needs information or risk information can be generated. This is beneficial in that it can be expected to find more potential good customers, for example, those with high needs and low risk customers. In addition, when corporate credit information includes bankruptcy information, the actual bankruptcy, trend, signs, cause of bankruptcy, form, total debt, bankruptcy date, bank, industry, representative name, etc. Thus, risk information can be generated by the artificial intelligence function of the generation unit 11, which is advantageous in that accuracy can be improved.

In addition, corporate credit information may be obtained by investigating a target company (target company) and investigating the target company. When the company credit information is generated in this way, for example, it can be expected to obtain information about whether the representative of the target company has a successor, whether the target company is vibrant, or the like. By using such corporate credit information by the generation unit 11, in addition to data that can be generally grasped, it is also possible to reflect information on the site, providing highly reliable needs information, risk information, etc. it can. The corporate credit information may include the final educational background of the representative or officer of the target company.

When the second target person information includes accounting information, it is possible to reflect an increase or decrease in borrowings or an increase or decrease in cash, and the accuracy of needs information and risk information can be improved. For example, one element of needs information is that the need to use financial products including investments increases when cash increases to a certain degree, and the need to use financial products including loans increases when borrowings increase to a certain degree. It can be used as an element of risk information, assuming that the risk of credit loss is high when the borrowing amount is excessive. In addition, the use of accounting information is beneficial in that it is possible to use overall information such as the presence of surplus funds and the change in sales. In other words, although the actual money flow can be seen only by transaction information at the financial institution, only the money flow through the financial institution can be seen. On the other hand, when using accounting information including financial statements and closing date data, information from a more macro perspective (for example, information including changes in sales, changes in net income, the amount of securities held, etc.) It is useful in that it can be obtained and highly accurate needs information or risk information can be obtained.

When the second subject information includes payment information, for example, whether payment is overdue may be used as an element of risk information in financial products including loans, for example, the delay fee is minimal. In such cases, it may be used as an element of needs information in financial products including loans.

In the case where the second target person information includes product purchase information, for example, investment includes information on purchasing high-priced products continuously, information on purchasing high-priced products and a certain period of time, etc. You may use as an element of the needs information in a financial product, for example, you may use as information of the risk information in a financial product including a loan, such as information that it continues buying small amount goods.

If the second target information includes inter-company e-commerce information, for example, information indicating that the product is selling and sales are increasing in some cases in real time before the financial statements or closing date data is created or issued. Can be grasped. In addition, when the second target person information includes inter-company e-commerce information, for example, it is possible to grasp the period from the time when the accounts receivable is generated until payment is made. It can be grasped in real time. In this way, when the second target person information includes inter-company e-commerce information,
This is advantageous in that business transactions can be quickly picked up and needs information or risk information can be generated based on the picked up information. With regard to needs information, if the timing is missed, the needs may be lost. Therefore, it is very useful to grasp business-to-business transactions in this way and generate needs information as a result. In addition, if the second target person information includes inter-company e-commerce information, other information that is investing heavily,
It is also possible to grasp information that has passed a certain period of time since a large investment was made.
Information in such inter-company electronic commerce information may be used as an element of needs information or risk information.

The device search unit 17 automatically performs a search at an appropriate timing, and the output unit 30 outputs the result and can be displayed on the device display unit 19, the first engine display unit 62, and / or the second engine display unit 162. It is good. Adopting such an embodiment is advantageous in that the latest information can be automatically displayed. In particular, when the situation changes in real time, for example, when using inter-company electronic commerce information, market-related information, or the like, a great effect can be expected by adopting such an aspect.

In particular, when the first target is an existing customer of a financial institution and the second target information includes corporate credit information and inter-company e-commerce information, it is useful for developing customers targeting the company. . Risk information is an important factor when a financial institution selects a loan. In order to grasp this risk information with higher accuracy, it is preferable to adopt a mode in which the second target person information includes business credit information. On the other hand, when a financial institution selects a loan destination efficiently, needs information becomes important information, but by adopting a mode in which the second target person information includes business-to-business e-commerce information, it is possible to achieve early timing. Since it is possible to grasp the accounts receivable, settlement conditions, etc., it is useful in that it is possible to quickly grasp the occurrence of needs and to expect that financial products can be proposed at an appropriate timing.

If the attribute information includes name identification information for managing the same target person collectively, even if the target person has multiple accounts etc., they are managed as one target person. Can collect information. For this reason, since needs information and / or risk information can be produced | generated based on more information, more highly accurate needs information and / or risk information can be output.

When the attribute information includes information about the household such as the target person's family, the needs information and / or risk information can be generated based on the information in the same household, so more accurate needs information and / or risk information. Can be output. When using family information in this way, needs information and / or risk information is generated based on the individual information of the target person, and needs information and / or risk information is generated based on the family information of the target person. May be. According to such an aspect, the result based on the need information and / or risk information of two patterns can be output.

The transaction information includes deposit transaction information, loan transaction information, contract information with the first institution and / or the second institution, usage information of the service provided by the first institution and / or the second institution or settlement information. By appropriately selecting from many types of information, more accurate needs information and / or risk information can be output.

The examination information includes, for example, information related to the subject's borrowing application to the financial institution or the subject's credit information, but more appropriate needs information and / or risk information can be selected by appropriately selecting from many types of information. Can be output.

In general, as the amount of information increases, it can be expected that highly accurate needs information and / or risk information can be obtained. However, if the amount of information is too large, processing may take time or unimportant information may be captured. It should be noted that a certain degree of pawl is necessary because of the possibility.

When the artificial intelligence function of the generation unit 11 generates needs information and / or risk information using different employment variables and different coefficients for different products (for example, financial products), more appropriate adoption according to the products Variables and coefficients can be used. For this reason, more accurate needs information and / or risk information can be output. When providing information on financial products, information on short-term loans may be output.

Because short-term loans can be expected to have more frequent needs than long-term loans,
Need information or risk information about short-term loans in that you can expect to gain new customers by selling financial products, or even if you are an existing customer, you can expect to gain more credit by selling financial products in a timely manner. It is useful to generate and output.

In the case where the first institution is a financial institution, when the calculation unit 15 calculates the profit using the borrowing amount of the target person, the interest rate and expense information at the time of the borrowing, etc., the operator also acquires information on the profit It is possible to determine whether or not to provide a financial product based on information on the obtained profit. In addition, when the borrowing amount is determined within the creditable amount determined based on the risk information for the target person and the interest rate (= applicable interest rate) is also determined based on the risk information for the target person Providing appropriately customized financial products and securing an appropriate range of profits.

In addition, when the calculation unit 15 calculates the creditable amount for the target person and / or the applicable interest rate for the target person from the risk information generated by the generation unit 11, the calculation unit 15 is based on the creditable amount and / or the applicable interest rate. Propose to provide financial products to the target audience. For this reason, it is possible to provide an appropriately customized financial product and to secure an appropriate range of profits.

When the generation unit 11 generates and outputs needs information and / or risk information for each of a plurality of products (for example, financial products), the operator needs information and / or risks for each of the output products. Information can be grasped, and it can be judged by comparing which product should be proposed.

In the case where the first institution is a financial institution, the generation unit 11 is not limited to information of one financial institution, and the adopted variable and the relevant information from any one or more of attribute information, examination information, and transaction information in a plurality of financial institutions Generate a coefficient for the hiring variable, and use the hiring variable and the coefficient,
When generating needs information and / or risk information, needs information and / or risk information can be generated based on broader and overall information about the subject.
Furthermore, highly accurate needs information and / or risk information can be output.

When the verification unit 16 verifies whether or not the predetermined product is actually used by the target person, or whether or not the target product is actually overwritten or overdue when lending money to the target person, Since verification results updated as needed can be used as past performance data, it is possible to generate and output needs information and / or risk information based on information with higher reliability. As described above, needs information and risk information may be generated based only on data within a certain period (for example, within two years). /
Alternatively, risk information can be generated and output.

By the way, when the need rate of card loans is high, if the deposit balance is small,
An example is when there are many withdrawals with a small amount. When the need rate for educational loans is high, if the transfer account contains the words "junior high school" or "high school", there is a child whose age is likely to require an educational loan due to household identification Can be mentioned. An example of a case where the mortgage needs rate is high is that a mortgage with a high interest rate is currently being paid.

Lastly, the description of the above-described embodiment and the disclosure of the drawings are merely examples for explaining the invention described in the claims, and are based on the description of the above-described embodiment or the disclosure of the drawings. The invention described in the claims is not limited. For example, even information that provides information other than needs information and risk information falls under the information processing apparatus in the present application. Needless to say, the description of the scope of claims at the beginning of the application can be changed as appropriate within the scope of the patent specification, and the scope can be expanded.

10 device control unit 11 generation unit 15 calculation unit 16 verification unit 17 device search unit 20 device storage unit 30 output unit 60 first engine control unit 61 first engine storage unit 67 first search unit 160 second engine control unit 161 second Engine storage unit 167 Second search unit

Claims (16)

A generation unit having an artificial intelligence function, which relates to the possibility that a certain target person uses a predetermined product using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons A generating unit that generates risk information when lending money to needs information or a certain target person;
An output unit that outputs the needs information or the risk information generated by the generation unit;
With
The generation unit selects a target person, generates the needs information or the risk information for the target person,
The information processing apparatus according to claim 1, wherein the plurality of target persons include a first target person whose target person information is acquired by a financial institution and a second target person whose target person information is acquired by a person other than the financial institution. The generation unit can generate the needs information or the risk information for a target person other than the first target person using a plurality of first target person information regarding the plurality of first target persons. Item 4. The information processing apparatus according to Item 1. A generation unit having an artificial intelligence function, which relates to the possibility that a certain target person uses a predetermined product using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons A generating unit that generates risk information when lending money to needs information or a certain target person;
An output unit that outputs the needs information or the risk information generated by the generation unit;
With
The generation unit selects a target person, generates the needs information or the risk information for the target person,
The information processing apparatus according to claim 1, wherein the plurality of target persons include a second target person whose target person information is acquired by a person other than a financial institution. The generation unit can generate the needs information or the risk information for a target person other than the second target person using a plurality of second target person information regarding the plurality of second target persons. Item 4. The information processing apparatus according to any one of Items 1 to 3. The generation unit uses the plurality of first subject information regarding the plurality of first subjects and the plurality of second subject information regarding the plurality of second subjects, and uses the first subject and the second subject. 5. The information processing apparatus according to claim 1, wherein the need information or the risk information is generated for a target person including a person. 6. The information processing apparatus according to claim 1, wherein the second target person information regarding the second target person includes credit information, accounting information, or commercial flow information. The information processing apparatus according to claim 1, wherein the second target person information regarding the second target person includes inter-company electronic commerce information. The information processing apparatus according to any one of claims 1 to 7, wherein the second target person information regarding the second target person includes payment information or product purchase information. A search unit for searching for information generated by the generation unit;
The information processing apparatus according to any one of claims 1 to 8, wherein a result searched by the search unit is output by the output unit. A verification unit for verifying whether or not the predetermined product is actually used by the certain target person, or whether or not the loan is actually overdue or delinquency occurs when lending money to the certain target person Prepared,
The verification result by the verification unit is used as the past performance data with respect to the needs information or the risk information generated after the verification result is output. The information processing apparatus according to item 1. The information processing apparatus according to claim 1, wherein the generation unit generates a recruitment variable and a coefficient for the recruitment variable using a plurality of the target person information. The information processing apparatus according to claim 11, wherein the artificial intelligence function of the generation unit generates the needs information or the risk information using different adoption variables and different coefficients for different products. The calculation unit for calculating the creditable amount for the certain target person or the applicable interest rate for the certain target person from the risk information generated by the generating unit. The information processing apparatus according to item 1. The information processing apparatus according to claim 1, wherein the first target person information related to the first target person is generated based on information acquired by a plurality of financial institutions. Need information on the possibility that a target person uses a predetermined product by using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons by a generation unit having an artificial intelligence function Or generating risk information when lending money to the target person,
Outputting the needs information or the risk information generated by the generation unit;
With
The generation unit selects a target person, generates the needs information or the risk information for the target person,
The plurality of target persons include a first target person whose target person information is acquired by a financial institution and a second target person whose target person information is acquired by a person other than the financial institution, or a target person who is not a financial institution. The information processing method characterized by including the 2nd subject person from which information is acquired. A program for executing an information processing method,
The information processing method includes:
Need information on the possibility that a target person uses a predetermined product by using a plurality of target person information for a plurality of target persons and past performance data for the plurality of target persons by a generation unit having an artificial intelligence function Or generating risk information when lending money to the target person,
Outputting the needs information or the risk information generated by the generation unit;
With
The generation unit selects a plurality of subjects, generates the needs information or the risk information for the subjects.
The plurality of target persons include a first target person whose target person information is acquired by a financial institution and a second target person whose target person information is acquired by a person other than the financial institution, or a target person who is not a financial institution. A program for executing a method including a second subject from whom information is acquired.