JP2021140205A - Loan customer credibility determination program - Google Patents

Abstract

To provide a loan credibility determination program allowing a financial institution to automatically and highly accurately determine credibility of a loan customer.SOLUTION: A loan customer credibility determination system 1 includes an information acquisition section 9, a search device 2 connected to the information acquisition section 9, and a database 3 connected to the search device 2. The information acquisition section 9 is a device in which a person utilizing this system inputs various types of commands and information. The database 3 accumulates reference financial information including a composition of finances of an enterprise, reference business planning information relating to business planning, etc. The search device 2 is comprised of electronic devices such as a PC. A user can acquire a search solution by the search device 2.SELECTED DRAWING: Figure 1

Description

The present invention relates to a lender creditworthiness determination program suitable for determining the creditworthiness of an individual or a company of the lender with high accuracy in determining whether or not to make a loan.

When a financial institution makes a loan to an individual or a company, a bank employee determines the creditworthiness of the individual or the company to which the loan is made. This credit rating is determined after considering various information such as the past financial statements and business results of the lender. However, when the number of loanee companies that must be judged is large, the judgment work may be delayed, and it is also necessary to reduce the labor burden of the judgment work. On the other hand, this loan judgment requires high judgment accuracy because it may be a matter of life and death for one company whether or not it can receive a loan. In the past, there has been no proposal for a system that automatically and accurately makes such a loan decision.

Therefore, the present invention was devised in view of the above-mentioned problems, and the purpose of the present invention is to automatically determine the creditworthiness of the lender company in determining whether or not a financial institution provides a loan. The purpose is to provide a lender credit judgment program that can make a judgment with high accuracy.

In order to solve the above-mentioned problems, the lender credit determination program according to the present invention relates to the credit history of the individual of the lender who newly determines the creditworthiness in the lender credit determination program for determining the creditworthiness of the individual of the lender. Refer to the information acquisition step for acquiring credit history information, the reference credit history information regarding the personal credit history of the past loanee acquired in advance, and the degree of association with the credit rating of three or more levels, and acquire it in the above information acquisition step. It is characterized in that a computer is made to execute a determination step of determining the creditworthiness of an individual of a loanee based on the credit history information obtained.

Even if there is no special skill or experience, it is possible to automatically and highly accurately determine the creditworthiness of a lender in determining whether or not a financial institution will provide a loan.

It is a block diagram which shows the whole structure of the system to which this invention is applied. It is a figure which shows the specific configuration example of a search device. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention. It is a figure for demonstrating the operation of this invention.

Hereinafter, the creditworthiness determination program to which the present invention is applied will be described in detail with reference to the drawings.

The first embodiment FIG . 1 is a block diagram showing an overall configuration of a lender creditworthiness determination system 1 in which a lender creditworthiness determination program to which the present invention is applied is implemented. The lender credit rating system 1 includes an information acquisition unit 9, a search device 2 connected to the information acquisition unit 9, and a database 3 connected to the search device 2.

The information acquisition unit 9 is a device for a person who uses this system to input various commands and information, and specifically, is composed of a keyboard, buttons, a touch panel, a mouse, a switch, and the like. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an image pickup device capable of capturing an image of a camera or the like. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper-based document. Further, the information acquisition unit 9 may be integrated with the discrimination device 2 described later. The information acquisition unit 9 outputs the detected information to the determination device 2. Further, the information acquisition unit 9 may be configured by means for specifying the position information by scanning the map information. Further, the information acquisition unit 9 may be composed of an illuminance sensor for measuring a temperature sensor, a humidity sensor, and a wind direction sensor. Further, the information acquisition unit 9 may be composed of a communication interface for acquiring data on the weather from the Japan Meteorological Agency or a private weather forecast company. Further, the information acquisition unit 9 may be composed of a body sensor that is attached to the body to detect body data, and this body sensor detects, for example, body temperature, heart rate, blood pressure, number of steps, walking speed, and acceleration. It may be composed of a sensor for the purpose. Further, the body sensor may acquire biological data of animals as well as humans. Further, the information acquisition unit 9 may be configured as a device that acquires information such as drawings by scanning or reading it from a database. In addition to these, the information acquisition unit 9 may be configured by an odor sensor that detects an odor or scent.

The database 3 stores various information necessary for determining the creditworthiness of the lender. Information necessary for determining the creditworthiness of a stock lender includes reference financial information including the financial details of individuals and companies of past lenders, reference management plan information regarding management plans acquired from companies, and information held by companies. A data set of reference intellectual asset information about the intellectual assets that were used, reference market information about the market conditions at a certain point in the past, reference external environment information about the external environment at a certain time in the past, and creditworthiness determined in the past. Is remembered.

That is, in the database 3, in addition to such reference financial information, it is determined in the past that any one or more of reference management plan information, reference intellectual asset information, reference market condition information, and reference external environment information is determined. The creditworthiness given is memorized in association with each other. By the way, the credit rating determined in the past may be not limited to the individual actually determined in the past, but a fictitious persona may be set and the credit rating judged by the financial institution or the like may be included in the learning data.

The search device 2 is composed of, for example, an electronic device such as a personal computer (PC), but is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., in addition to the PC. It may be converted. The user can obtain a search solution by the search device 2.

FIG. 2 shows a specific configuration example of the search device 2. The search device 2 performs wired communication or wireless communication with a control unit 24 for controlling the entire search device 2 and an operation unit 25 for inputting various control commands via operation buttons, a keyboard, or the like. A communication unit 26 for the purpose, an estimation unit 27 for making various judgments, and a storage unit 28 for storing a program for performing a search to be executed represented by a hard disk or the like are connected to the internal bus 21, respectively. .. Further, a display unit 23 as a monitor that actually displays information is connected to the internal bus 21.

The control unit 24 is a so-called central control unit for controlling each component mounted in the search device 2 by transmitting a control signal via the internal bus 21. Further, the control unit 24 transmits various control commands via the internal bus 21 in response to the operation via the operation unit 25.

The operation unit 25 is embodied by a keyboard or a touch panel, and an execution command for executing a program is input from the user. When the execution command is input by the user, the operation unit 25 notifies the control unit 24 of the execution command. Upon receiving this notification, the control unit 24, including the estimation unit 27, executes a desired processing operation in cooperation with each component. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The estimation unit 27 estimates the search solution. The estimation unit 27 reads out various information stored in the storage unit 28 and various information stored in the database 3 as necessary information when executing the estimation operation. The estimation unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any well-known artificial intelligence technique.

The display unit 23 is composed of a graphic controller that creates a display image based on the control by the control unit 24. The display unit 23 is realized by, for example, a liquid crystal display (LCD) or the like.

When the storage unit 28 is composed of a hard disk, predetermined information is written to each address based on the control by the control unit 24, and is read out as needed. Further, the storage unit 28 stores a program for executing the present invention. This program is read and executed by the control unit 24.

The operation of the lender creditworthiness determination system 1 having the above-described configuration will be described.

In the lender credit rating system 1, for example, as shown in FIG. 3, it is premised that the reference financial information and the credit rating have three or more levels of association with each other in advance and acquired. If it is a company, the reference financial information reflects the financial results of the company examined in the past. In other words, the reference financial information reflects the past financial results of the companies that have been examined before this when there is a time when the creditworthiness of the lender is to be determined. An example of this reference financial information is data related to all financial statements including the financial statements of the company that provided the financial statements, for example, the numerical values of the book information and financial information described in the financial statements. Main, current ratio, liquid debt, equity ratio shareholders' equity, total capital, gearing ratio, interest-bearing debt, equity capital, ordinary income margin, ordinary income, sales, total capital ordinary income ratio, ordinary income, Total capital, net income, ordinary income growth rate, ordinary income, ordinary income for the previous term, sales, repayment ability, years of debt repayment, interest-bearing debt, operating funds, cash flow, operating income, depreciation expenses, etc. In addition to the figures in these financial statements, the reference financial information may include whether or not the debt is insolvent, and how much borrowing from officers and inventories (inventory) are. These reference financial information may be for one year or several years.

Further, the reference financial information may be composed of the financial information of the company examined in the past, which reflects the financial results of the company, even when the loanee is a private store. Further, the reference financial information may be obtained from data such as a salary statement and a withholding slip when the lender is an individual.

The reference financial information includes all information indicating the financial status of the corporation or individual, the information described in the final tax return of the self-employed person, the information described in the financial information of the corporation, and the personal withholding slip (annual income). ), Information indicating the current assets, information on the real estate owned, the number of years of living in the real estate owned, etc. are also included. In addition to this, the amount of cash currently held, the amount of financial assets, the type of receivables, etc. may be included in this reference financial information. These reference financial information includes the status of collateral properties and other borrowing status. For reference financial information, for example, image analysis of the description of withholding slip, salary statement, final tax return, residence tax decision notice, taxation certificate, etc., and if necessary, deep learning technology is used to analyze the analysis image. It may be automatically determined based on the feature amount and converted into data. In addition, the financial information may be represented by the actual desired amount of borrowing based on the actual financial condition of the prospective real estate purchaser.

The credit rating may be ranked as "normal", "caution required", "possible bankruptcy", "substantial bankruptcy", "bankruptcy", etc., or displayed as a score, with 1000 points being the highest credit rating. High and 0 points may be the one with the lowest credit rating. The most credible score may be any score other than 1000 points. This credit rating is pre-collected as a dataset with reference financial information. For this credit rating, for example, if there is a record of a previous judgment made by a financial institution, it may be used as it is. Further, the credit rating may be calculated from the number of cases where the loan was approved and the number of cases where the loan was not obtained with the same or similar reference financial information. By the way, this credit rating is given to the company that provided the financial information for reference. Therefore, in the past examination, these data sets can be obtained by acquiring the company that provided the financial information for reference and the credit rating attached to the company. I will collect many such cases. Since the financial information does not have exactly the same financial information between companies, the financial information itself may be categorized. That is, the reference financial information P01 to P03 in FIG. 3 may be financial information classified by type, and may be classified by dividing by the rate of return, the amount of profit, or the like. Further, it may be categorized by a pattern (for example, a large amount of accounts receivable, a large amount of entertainment expenses, and no inventory because of the service industry).

In other words, through this reference financial information and the credit rating data set, it is possible to understand how the data related to various settlements generated in the reference financial information was judged in the loan examination. In other words, the settlement data described in the reference financial information and the creditworthiness are the data set. Therefore, by collecting the reference financial information and the credit rating data set, it is possible to know how the credit rating was judged in the examination after what kind of financial results have been obtained in the past.

In the example of FIG. 3, it is assumed that the input data is, for example, reference financial information P01 to P03. The reference financial information as such input data is linked to the output. In this output, the credit rating as the output solution is displayed.

The reference financial information is associated with each other through three or more levels of association with the creditworthiness of this output solution. The reference financial information is arranged on the left side through this degree of association, and the creditworthiness is arranged on the right side through this degree of association. The degree of association indicates the degree of creditworthiness and the degree of relevance to the reference financial information arranged on the left side. In other words, this degree of association is an indicator of what credit rating each reference financial information is likely to be associated with, and the accuracy with which the most probable credit rating is selected from the reference financial information. Is shown. In the example of FIG. 3, w13 to w19 are shown as the degree of association. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the creditworthiness as an output. On the contrary, the closer to one point, the lower the degree of relevance of each combination as an intermediate node to the creditworthiness as an output.

The search device 2 acquires in advance the degree of association w13 to w19 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to whether the reference financial information or the credit rating in that case is adopted in determining the actual search solution, and analyzes and analyzes these. The degree of association shown in FIG. 3 is created in.

For example, suppose that some reference financial information is determined to be "possible for bankruptcy". Suppose that In such a situation, it is assumed that there are many similar patterns of reference financial information that are judged to be “possible for bankruptcy”. In such a case, the degree of association of "possible bankruptcy" becomes stronger. On the other hand, in the exact same pattern (classification) of financial information for reference, it is assumed that many were judged to be "substantial bankruptcy" and few were judged to be "possible bankruptcy". In such a case, the degree of association of "substantial bankruptcy" becomes stronger, and the degree of association of "possible bankruptcy" becomes lower.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of reference financial information P01, analysis is performed from the data of the past creditworthiness determination result. This may be extracted from, for example, the data of the credit rating determination result in the past loan examination stored in the financial institution. In the case of reference financial information P01, if there are many cases of "possible bankruptcy", the degree of association leading to this "possible bankruptcy" is set higher, and there are many cases of "substantial bankruptcy". Is set to a higher degree of association that leads to this "substantial bankruptcy". For example, in the example of financial information P01 for reference, it is linked to "possible bankruptcy" and "substantial bankruptcy". The degree of association of w14 that leads to "substantial bankruptcy" is set to 2 points.

Further, the degree of association shown in FIG. 3 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In such a case, as shown in FIG. 4, reference financial information is input as input data, each credit rating is output as output data, and at least one or more hidden layers are provided between the input node and the output node. Machine learning may be performed. On the contrary, the credit rating may be input and the reference financial information may be output.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, the credit rating will be predicted using the above-mentioned trained data in actually determining the credit rating from now on. In such a case, the latest financial information of the lender company that actually determines the creditworthiness is newly acquired. This financial information may be for the last year or years. This financial information is composed of the same type of data as the reference financial information described above.

The newly acquired financial information is input by the information acquisition unit 9 described above. The information acquisition unit 9 may acquire such financial information as electronic data.

Based on the newly acquired financial information in this way, the credit rating that is likely to be judged is actually searched for the financial information. In such a case, the degree of association shown in FIG. 3 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02, "normal" is associated with w15 and "substantial bankruptcy" is associated with the association degree w16 through the association degree. In such a case, "normal" with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the “substantial failure” in which the degree of association is low but the association itself is recognized may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In this way, it is possible to search for the creditworthiness to be judged from the newly acquired financial information and display it to the user (consultant, bank clerk, customer). By looking at the search result, the user can grasp the degree of credit of the loanee candidate based on the searched credit rating. By the way, in the process of outputting this credit rating, in addition to simply displaying the searched credit rating, even if the advice is configured by displaying the specific amount of financing based on this credit rating. good.

In the example of FIG. 5, it is assumed that the input data is, for example, reference financial information P01 to P03 and reference management plan information P14 to 17. The intermediate node shown in FIG. 5 is a combination of the reference financial information and the reference management plan information as such input data. Each intermediate node is further linked to the output. In this output, each credit rating as an output solution is displayed.

In the example of FIG. 5, it is premised that a combination of reference financial information and reference management plan information is formed. The reference management plan information relates to the contents of the management plan. Examples of the contents of the management plan include vision, action guidelines, management policy, goals, analysis of opportunities / threats and strengths (internal / external environment analysis), gap analysis with goals, and medium-term management plan (necessity and formulation procedure). ), Single-year management plan, sales target, etc., which consists of information described in general management plans. As the reference management plan information, the information obtained from the company that has previously been examined may be used. From the company that conducted the examination, the reference financial information, the reference management plan information, and the judgment result of the creditworthiness of the reference management plan information will be obtained.

Since the reference management plan information does not have exactly the same management plan between companies, the management plan itself may be categorized. That is, the reference management plan information P14 to P17 in FIG. 5 may be information classified by type, and may be classified by, for example, being divided according to a sales target, a management policy, or the like. Further, it may be categorized by a pattern (for example, a pattern of a single-year management plan or a pattern of a vision).

In the example of FIG. 5, it is assumed that the input data is, for example, reference financial information P01 to P03 and reference management plan information P14 to 17. The intermediate node shown in FIG. 5 is a combination of the reference financial information and the reference management plan information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference financial information and the reference management plan information is associated with each other through three or more levels of association with the credit rating as the output solution. The reference financial information and the reference business plan information are arranged on the left side through this degree of association, and the creditworthiness is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to each credit level with respect to the reference financial information and the reference management plan information arranged on the left side. In other words, this degree of association is an index showing what kind of credit rating each reference financial information and reference business plan information is likely to be associated with, and from the reference financial information and the reference business plan information. It shows the accuracy in selecting each credit rating that is most likely. In addition to financial information, it is possible to make a judgment based on the actual success rate of the business after that according to the management plan, and the possibility of collecting funds will be different. Therefore, the optimum credit rating will be searched for by combining these reference financial information and reference management plan information.

In the example of FIG. 5, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference financial information, the reference management plan information, and the creditworthiness in that case was suitable for determining the actual search solution, and stores these. By analyzing and analyzing, the degree of association shown in FIG. 5 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference financial information P01 and the reference management plan information P16, the creditworthiness is analyzed from the past data. When there are many cases where the credit rating is "possible bankruptcy", the degree of association leading to this "possible bankruptcy" is set higher, and there are many cases of "normal" and cases of "possible bankruptcy". If the number is low, the degree of association that leads to "normal" is set high, and the degree of association that leads to "possible failure" is set low. For example, in the example of the intermediate node 61a, it is linked to the output of "possible failure" and "normal", but from the previous case, the degree of association of w13 leading to "possible failure" is set to 7 points, and "normal". The degree of association of w14 that leads to "" is set to 2 points.

Further, the degree of association shown in FIG. 5 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 5, the node 61b is a node in which the reference financial information P01 is combined with the reference management plan information P14, the degree of association of "substantial bankruptcy" is w15, and "management required". The degree of association is w16. The node 61c is a node that is a combination of the reference management plan information P15 and P17 with respect to the reference financial information P02, and has a credit rating of w17 and a credit rating of w18.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually performing a search for determining the credit rating from now on, the above-mentioned learned data will be used. In such a case, management plan information is acquired in addition to financial information from the company that newly determines the creditworthiness. This management plan information corresponds to the above-mentioned reference management plan information, and data such as gap analysis with the target of the company to be judged, medium-term management plan, etc. is taken in or directly input. May be good.

Based on the newly acquired financial information and management plan information in this way, the optimum credit rating is searched for. In such a case, the degree of association shown in FIG. 5 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02 and the management plan information is the same as or similar to P17, the node 61d is associated via the degree of association. In this node 61d, "substantial failure" is associated with w19, and "need attention" is associated with the degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In addition, Table 2 below shows examples of the degrees of association w1 to w12 extending from the input.

The intermediate node 61 may be selected based on the degree of association w1 to w12 extending from this input. That is, the larger the degree of association w1 to w12, the heavier the weighting in the selection of the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weights in the selection of the intermediate node 61 may all be the same.

FIG. 6 shows an example in which the combination of the above-mentioned reference financial information, the reference market future information, and the creditworthiness of the combination are set to three or more levels of association.

Reference market future information is any data about the future of the market in which the company intends to provide a product or service. This reference market potential information includes various data based on blogs, analyst reports, securities reports, advertisements, press releases, news articles, etc. in any market. The reference market future information may be categorized as the market future itself. That is, the reference market future information P18 to P21 in FIG. 6 may be information classified by type. For example, the information may be classified by an analyst according to whether or not the market growth rate is 0% or more per year. It may be. Further, it may be categorized by a pattern (for example, a pattern of whether the market growth rate increases rapidly or gradually) or the like.

In the example of FIG. 6, it is assumed that the input data is, for example, reference financial information P01 to P03 and reference market future information P18 to 21. The intermediate node shown in FIG. 6 is a combination of the reference financial information and the reference market future information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference financial information and the reference market future information is related to each other through three or more levels of association with the credit rating as this output solution. The reference financial information and the reference market future information are arranged on the left side through this degree of association, and the creditworthiness is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to the creditworthiness of the reference financial information and the reference market future information arranged on the left side. In other words, this degree of association is an indicator of what credit quality each reference financial information and reference market future information are likely to be associated with, and is a reference financial information and reference market future information. It shows the accuracy in selecting each credit rating that is most probable from. In addition to financial information, the likelihood of cash recovery varies depending on the actual market potential. Therefore, the optimum credit rating will be searched for by combining these reference financial information and reference market future information.

In the example of FIG. 6, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference financial information, the reference market future information, and the credit rating in that case was more suitable for determining the actual search solution. By analyzing and analyzing these, the degree of association shown in FIG. 6 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference financial information P01 and the reference market future information P20, the creditworthiness is analyzed from the past data. For example, in the example of the intermediate node 61a, it is linked to the output of "possible failure" and "normal", but from the previous case, the degree of association of w13 leading to "possible failure" is set to 7 points, and "normal". The degree of association of w14 that leads to "" is set to 2 points.

Further, the degree of association shown in FIG. 6 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 6, the node 61b is a node in which the reference market future information P18 is combined with the reference financial information P01, and the “substantial bankruptcy” association degree is w15, “management required”. The degree of association of "destination" is w16. Node 61c is a node that is a combination of reference market future information P19 and P21 with respect to reference financial information P02, and the degree of association of "normal" is w17 and the degree of association of "need attention" is w18. ing.

Such a degree of association is what is called learned data in artificial intelligence. After creating such trained data, when actually giving advice from now on, the above-mentioned trained data will be used. In such a case, in addition to the above-mentioned financial information, market future information regarding the future of the market in which the lender company that newly determines the creditworthiness develops the business is acquired. The market future information corresponds to the reference market future information, and the analyst report or the securities report may be directly imported. If it is other statistical data, the data may be acquired directly.

The credit rating is searched based on the newly acquired financial information and market potential information in this way. In such a case, the degree of association shown in FIG. 6 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02 and the market future information is P21, the node 61d is associated through the degree of association. The node 61d is associated with "substantial failure" by w19 and "need attention" by the degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

FIG. 7 shows an example in which the combination of the above-mentioned reference financial information, the reference intellectual property information, and the creditworthiness of the combination are set to three or more levels of association.

The reference intellectual property information is information on intellectual property held by the company, and is mainly information such as patent rights, utility model rights, design rights, trademark rights, and copyrights. In addition to these, the intellectual property information for reference includes all kinds of intellectual property such as patents, designs, trademarks, know-how accumulated in the company, sales information, customer information, knowledge about manufacturing processes, etc. The reference intellectual property information to be used may be categorized as the intellectual property itself. That is, the reference intellectual property information P22 to P25 in FIG. 7 may be information classified by type, and may be classified by, for example, the number of patents. Further, it may be categorized by a pattern (pattern such as patent, design, trademark ratio, etc.).

In the example of FIG. 7, it is assumed that the input data is, for example, reference financial information P01 to P03 and reference intellectual property information P22 to 25. The intermediate node shown in FIG. 7 is a combination of the reference financial information and the reference intellectual property information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference financial information and the reference intellectual property information is related to each other through three or more levels of association with the credit rating as this output solution. The reference financial information and the reference intellectual property information are arranged on the left side through this degree of association, and the creditworthiness is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to the creditworthiness of the reference financial information and the reference intellectual property information arranged on the left side. In other words, this degree of association is an indicator of what credit quality each reference financial information and reference intellectual property information is likely to be associated with, and is a reference financial information and reference intellectual property. It shows the accuracy in selecting each credit rating that is most likely from the information. In addition to financial information, the likelihood of cash recovery varies depending on the state of actual intellectual property. Therefore, the optimum credit rating will be searched for by combining these reference financial information and reference intellectual property information.

In the example of FIG. 7, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. 7. That is, the search device 2 accumulates past data as to which of the reference financial information, the reference intellectual property information, and the credit rating in that case was more suitable for determining the actual search solution. By analyzing and analyzing these, the degree of association shown in FIG. 7 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference financial information P01 and the reference intellectual property information P24, the creditworthiness is analyzed from the past data. For example, in the example of the intermediate node 61a, it is linked to the output of "possible failure" and "normal", but from the previous case, the degree of association of w13 leading to "possible failure" is set to 7 points, and "normal". The degree of association of w14 that leads to "" is set to 2 points.

Further, the degree of association shown in FIG. 7 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 7, the node 61b is a node in which the reference intellectual property information P22 is combined with the reference financial information P01, the association degree of "substantial bankruptcy" is w15, and "management required". The degree of association of "destination" is w16. The node 61c is a node that is a combination of the reference intellectual property information P23 and P25 with respect to the reference financial information P02, and the "normal" association degree is w17 and the "attention required" association degree is w18. ing.

Such a degree of association is what is called learned data in artificial intelligence. After creating such trained data, when actually giving advice from now on, the above-mentioned trained data will be used. In such a case, in addition to the above-mentioned financial information, the intellectual property information related to the intellectual property held by the lender company whose creditworthiness is newly determined is acquired. The intellectual property information corresponds to the reference intellectual property information, and is information such as patent rights held, and these may be directly taken in. If it is other statistical data, the data may be acquired directly.

The credit rating is searched based on the newly acquired financial information and intellectual property information in this way. In such a case, the degree of association shown in FIG. 7 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02 and the intellectual property information is P21, the node 61d is associated through the degree of association. The node 61d is associated with "substantial failure" by w19 and "need attention" by the degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

FIG. 8 shows an example in which the combination of the above-mentioned reference financial information, the reference market information, and the credit rating for the combination are set to three or more levels of association.

Reference market information is various information related to market conditions. The market conditions referred to here may target any range including one company, the entire industry including the company, the entire Japan, and the entire world. Examples of this reference market information include interest rates, exchange rates, stock prices of each stock, crude oil, futures, precious metals, and price movements of Bitcoin. This reference market information may be displayed as a time-series chart, a line graph, or the like for these targets. Further, information such as Bollinger band, MACD, moving average line and the like may be attached. In addition, this market information may include fundamental indicators of each brand's company, and in addition to annual sales, profits, and costs, PER (price-earnings ratio), PBR (price-to-book value ratio), ROE ( Indicators such as return on equity) may be included. For foreign exchange, information such as a chart showing price movements between currencies, Bollinger Bands, MACD, and moving average lines may be attached. The reference market information may categorize the market potential itself. That is, the reference market information P26 to P29 in FIG. 8 may be information classified by type, and may be classified by dividing according to whether or not the growth rate of the stock price is 0% or more per year. Further, it may be categorized by a pattern (for example, a pattern of whether the growth rate of the stock price increases rapidly or gradually) or the like.

In the example of FIG. 8, it is assumed that the input data is, for example, reference financial information P01 to P03 and reference market information P26 to 29. The intermediate node shown in FIG. 8 is a combination of reference financial information and reference market information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference financial information and the reference market information is related to each other through three or more levels of association with the credit rating as this output solution. The reference financial information and the reference market information are arranged on the left side through this degree of association, and the credit rating is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to the creditworthiness of the reference financial information and the reference market condition information arranged on the left side. In other words, this degree of association is an indicator of what credit rating each reference financial information and reference market information is likely to be associated with, and is most certain from the reference financial information and the reference market information. It shows the accuracy in selecting each unique credit rating. In addition to financial information, the likelihood of cash recovery varies depending on the actual market conditions. Therefore, the optimum credit rating will be searched for by combining these reference financial information and reference market information.

In the example of FIG. 8, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data on which of the reference financial information, the reference market condition information, and the credit rating in that case is more suitable for determining the actual search solution, and stores these. By analyzing and analyzing, the degree of association shown in FIG. 8 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of reference financial information P01 and reference market information P28, the creditworthiness is analyzed from past data. For example, in the example of the intermediate node 61a, it is linked to the output of "possible failure" and "normal", but from the previous case, the degree of association of w13 leading to "possible failure" is set to 7 points, and "normal". The degree of association of w14 that leads to "" is set to 2 points.

Further, the degree of association shown in FIG. 8 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 8, the node 61b is a node in which the reference financial information P01 is combined with the reference market information P26, the degree of association of "substantial bankruptcy" is w15, and "management required". The degree of association is w16. The node 61c is a node that is a combination of the reference market information P27 and P29 with respect to the reference financial information P02, and the "normal" association degree is w17 and the "attention required" association degree is w18. ..

Such a degree of association is what is called learned data in artificial intelligence. After creating such trained data, when actually giving advice from now on, the above-mentioned trained data will be used. In such a case, in addition to the above-mentioned financial information, the market conditions of the market in which the lender company that newly determines the creditworthiness develops the business, and the market conditions information that reflects the market conditions of Japan as a whole and the world as a whole are acquired. The market information corresponds to the market future potential information for reference, and the stock price and exchange chart information may be directly taken in. If it is other statistical data, the data may be acquired directly.

The credit rating is searched based on the newly acquired financial information and market condition information in this way. In such a case, the degree of association shown in FIG. 8 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02 and the market information is P29, the node 61d is associated through the degree of association, and this node In 61d, "substantial bankruptcy" is associated with w19, and "need attention" is associated with a degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

FIG. 9 shows an example in which the combination of the above-mentioned reference financial information, the reference external environment information, and the credit rating for the combination are set to three or more levels of association.

The reference external environment information is various information related to the external environment information. The external environmental information here is economic data (GDP, employment statistics, mining and industry production index, capital investment, labor force survey, etc.), household data (household consumption situation survey, household data, average working hours per week, savings amount). Statistical data, annual income statistical data, etc.), real estate data (office vacancy rate, unit price per tsubo, rent market, land price, vacant house data, etc.), natural environment data (disaster data, temperature data, precipitation data, wind direction data, humidity data, etc.) Etc.). The external environment information includes all information outside the company to be examined, in addition to the information that reflects a part or all of these data. The external environment information for reference may be categorized as the external environment itself. That is, the reference market information P30 to P33 in FIG. 9 may be information classified by type, and may be classified by separating them by data in the employment statistics, for example. Further, it may be categorized by a pattern (for example, a pattern of whether the growth rate of GDP increases rapidly or gradually) or the like.

In the example of FIG. 9, it is assumed that the input data is, for example, reference financial information P01 to P03 and reference external environment information P30 to 33. The intermediate node shown in FIG. 9 is a combination of the reference financial information and the reference external environment information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference financial information and the reference external environment information is related to each other through three or more levels of association with the credit rating as this output solution. The reference financial information and the reference external environment information are arranged on the left side through this degree of association, and the credit rating is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to the creditworthiness of the reference financial information and the reference external environment information arranged on the left side. In other words, this degree of association is an index showing what kind of credit rating each reference financial information and reference external environment information are likely to be associated with, and from the reference financial information and the reference external environment information. It shows the accuracy in selecting each credit rating that is most likely. In addition to financial information, the likelihood of cash recovery varies depending on the actual external environment. Therefore, the optimum credit rating will be searched for by combining these reference financial information and reference external environment information.

In the example of FIG. 9, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference financial information, the reference external environment information, and the credit rating in that case was more suitable for determining the actual search solution, and these By analyzing and analyzing the above, the degree of association shown in FIG. 9 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference financial information P01 and the reference external environment information P28, the creditworthiness is analyzed from the past data. For example, in the example of the intermediate node 61a, it is linked to the output of "possible failure" and "normal", but from the previous case, the degree of association of w13 leading to "possible failure" is set to 7 points, and "normal". The degree of association of w14 that leads to "" is set to 2 points.

Further, the degree of association shown in FIG. 9 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 9, the node 61b is a node in which the reference external environment information P30 is combined with the reference financial information P01, the association degree of "substantial bankruptcy" is w15, and the "management required destination". The degree of association is w16. The node 61c is a node that is a combination of the reference external environment information P31 and P33 with respect to the reference financial information P02, and the "normal" association degree is w17 and the "attention required" association degree is w18. There is.

Such a degree of association is what is called learned data in artificial intelligence. After creating such trained data, when actually giving advice from now on, the above-mentioned trained data will be used. In such a case, in addition to the above-mentioned financial information, external environmental information outside the lender company whose creditworthiness is newly determined is acquired. The external environment information corresponds to the reference market external environment information, and these data may be directly captured. If it is other statistical data, the data may be acquired directly.

The credit rating is searched based on the newly acquired financial information and external environmental information in this way. In such a case, the degree of association shown in FIG. 9 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02 and the external environment information is P33, the node 61d is associated via the degree of association. The node 61d is associated with "substantial failure" by w19 and "need attention" by the degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In FIG. 10, in addition to the above-mentioned reference financial information and reference management plan information, a combination of reference market future information and creditworthiness for the combination are set to three or more levels of association. An example is shown.

In such a case, as shown in FIG. 10, the degree of association is such that the set of combinations of the reference financial information, the reference business plan information, and the reference market future information is the same as described above, and the nodes 61a of the intermediate node to It will be expressed as 61e.

For example, in FIG. 10, in the node 61c, the reference financial information P02 is associated with the reference degree w3, the reference management plan information P15 is associated with the association degree w7, and the reference market future information P19 is associated with the association degree w11. Similarly, in the node 61e, the reference financial information P03 is associated with the reference degree w5, the reference management plan information P15 is associated with the association degree w8, and the reference market future information P18 is associated with the association degree w10.

Similarly, when such a degree of association is set, the search solution is determined based on the newly acquired financial information, the management plan information, and the management plan information.

In determining the search solution, the degree of association shown in FIG. 10 acquired in advance is referred to. For example, the acquired financial information corresponds to or similar to the reference financial information P02, the acquired management plan information corresponds to the reference management plan information P15, and the acquired management plan information corresponds to the reference management plan information P19. In this case, the combination is associated with the node 61c, in which "normal" is associated with the degree of association w17 and "need attention" is associated with the degree of association w18. As a result of such a degree of association, a search solution is actually obtained based on w17 and w18.

When combining three or more types of such input parameters, in addition to the reference financial information, the reference management plan information, the reference management plan information, the reference intellectual asset information, the reference market condition information, and the reference external It is applicable even if the combination is composed of any two or more of the environmental information.

Second Embodiment Hereinafter, the second embodiment will be described. In executing this second embodiment, the loanee creditworthiness determination system 1, the information acquisition unit 9, the search device 2, and the database 3 used in the first embodiment are similarly used. The description of each of these configurations will be omitted below by quoting the description of the first embodiment.

In the second embodiment, for example, as shown in FIG. 11, three or more levels of association between the combination of the reference financial information and the reference market condition information and the creditworthiness of the individual of the lender to the combination are set. An example is shown. In creating a trained model from these datasets, this credit rating sets a fictitious persona as well as the individual actually judged in the past, and includes the credit rating judged by financial institutions etc. in the training data. You may.

In this second embodiment, an example is shown in which a combination of the reference financial information, the reference information shown below, and the credit rating for the combination are set to three or more levels of association.

The reference information referred to here is composed of any of the following.

First, when the lender is an individual, the reference information includes consumption behavior information for reference, transaction information for reference, credit history information for reference, personal network information for reference, first impression information for reference, personality information for reference, and future for reference. It is composed of any one or more of sexual information, reference taste information, reference attribute information, reference area information, and reference reputation information. Each of these reference information was obtained from an individual of a past lender. The details of these reference information when the lender is an individual will be described below.

The reference consumption behavior information is all information about the consumption behavior of the individual of the past lender. The individuals of the past lenders mentioned here are not limited to the individuals who actually made the loan, but each fictitious individual is set, and the data obtained by setting the creditworthiness of the financial institution is utilized. You may.

Specifically, this reference consumption behavior information is information indicating what kind of goods and services the individual of the past lender has purchased so far. In other words, the consumption behavior here includes all the products and services purchased so far. If you are a sole proprietor, you may want to extract these purchase information from the books. In addition, these purchase information may be noted from a receipt or the like. This reference consumption behavior information may also include sales on an EC (electronic commerce) site, purchase history, and purchase history imported from cloud accounting information. In addition, the consumption behavior information for reference may statistically indicate what is actually purchased and at what ratio in the purchases that have been made so far. For example, one individual spends a quarter of the annual money on housing rent, one quarter for food, another quarter for hobby golf, and a quarter. The breakdown of purchase targets, such as buying clothing and miscellaneous goods, may be shown as a ratio. When this reference consumption behavior information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 was the most purchased last month, with 15% for clothes and 13 for food expenses. %, Entertainment expenses are 10%, and so on. For reference information P35, the most common purchases made last month were rent 25%, food expenses 20%, automobiles 14%, and so on.・ Etc.

Reference transaction information is all information about past transactions with an individual of a past lender. While the reference consumption behavior information is information that shows what the money has actually been spent on, this reference transaction information shows how fair the actual buying and selling and transactions were, and sincerity. It shows whether you have made a good trade, and the integrity and safety of your trading partner. The reference transaction information also includes the transaction amount and the sense of scale. This reference transaction information can be obtained from deposits and withdrawals to and from bank accounts and settlement data at financial institutions. Deposit and withdrawal information can be obtained from these. Further, the reference transaction information can be obtained from the quotation, the delivery note, and the invoice. For example, if the product is sold or purchased on an EC (electronic commerce) site, it can be obtained from the EC site. In addition, the reference transaction information may also reflect the evaluation contents by the evaluator for the products and services actually bought and sold through the EC site. The higher the evaluation content, the more legitimate and fair the consumption behavior and purchase can be considered. Reference transaction information may be extracted from information such as the quality of the delivered item, compliance with the delivery date, and the politeness of the message before the transaction. Further, if there is a defect in the delivered product in the transaction conducted through the EC site, the evaluation content may be lowered by extracting the defect through writing on the EC site. The reference transaction information may reflect the presence or absence of fraudulent transactions determined from past order data. To determine fraudulent transactions here, purchase a lot of cheap products that can only be purchased once a day by changing the name or changing the address so that the same person cannot be identified. If so, it may be extracted through surveillance technology on the Internet. The integrity and security of a trading partner may be extracted from account deposit / withdrawal details, accounting data, WEB sites, financial statements, and book information. At the time of this extraction, a higher risk trading partner is acquired and learned in advance, and it is determined from these account deposit / withdrawal details, accounting data, WEB site, financial statements, etc. through machine learning. May be good. In addition, if negotiations have been conducted with a trading partner in the past and the transaction history holds a paper document or electronic data of the document, reference transaction information may be extracted from this transaction history document. Further, if the individual is a self-employed person, reference transaction information may be extracted from the main business partner information described in the site, SNS, etc. launched for the self-employed person. When this reference consumption behavior information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 has a business partner of 〇 × Co., Ltd., sells 10 books for 23,000 yen, and is an EC site. The evaluation by is 4 points out of 5 grades, the reference information P35 is the customer is △ ◆ Co., Ltd., the PC is purchased for 55,000 yen, the evaluation by the EC site is 2 points out of 5 grades, And so on.

The reference credit history information is all information about the credit history of the individual of the past lender. Examples of reference credit history information include neglect of repayment of credit loans, presence / absence and degree of delinquency in communication charges for mobile phones, etc., payment status of pensions and health insurance, history of delinquency, tax delinquency, etc. , Your own insurance documents, whether you have a history of debt consolidation or bankruptcy in the past, etc. This reference credit history information may be obtained from the bank's deposit / withdrawal history. When this reference credit history information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 has no delinquency history of mobile phones and credit loans in the past, and the reference information P35 has credit in the past. The loan delinquency history is 3 times, the reference information P36 has a mobile phone call charge delinquency history of 1 time, and so on.

Reference network information is all information about the personal friendships and connections of past lenders. This reference personal connection information may be extracted from, for example, information on authors and inventors described in papers and patent gazettes. When co-authors and inventors are lined up under a joint name in one treatise or patent gazette, those co-authors and inventors have usually worked together to issue the treatise or patent. It can be said that the connections are deep and the connections are formed with each other. In addition, when events and various announcements are jointly planned from the Internet site, the co-participants are often posted on the site under joint names, so a network of contacts is formed between the co-participants. In many cases. In addition, even when the names are listed among the officers of a company, it can be considered that a personal connection is formed between these officers. The reference network information extracts such a network. The reference personal connection information includes a score and evaluation information to that effect when a person requiring attention, a dangerous person, a person who has left various achievements, a famous person, or the like is included in the personal connection. When this reference personal connection information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 includes a person XX who has won the XX award as a personal connection. The person who committed the crime in the past ▲ ◆ is included.

The reference first impression information is any information about the individual first impression of the past lender. The first impression information for reference can be obtained through the face image of the individual of the past lender, the voice uttered, or the like. The face image is composed of a face photograph or a digital image taken through a camera, and may be either a still image or a moving image. A voice is a voice recorded through a microphone. Such face images and sounds are analyzed respectively. The face image may be automatically discriminated based on the feature amount of the analyzed image and converted into data by using image analysis and, if necessary, deep learning technology. For example, it is possible to extract features that affect the credit aspect, such as a part that seems to be unconfident by lying and a part that contains malicious intent through a face image. For voice, we extract characteristics that affect credit, such as lying, unconfident words and actions, and repeating words and actions that are different from the past. For voice, features that affect credit may be extracted by extracting characteristic intonations and accents using existing analysis techniques and machine learning. The reference first impression information may consist of both the face image and the sound, or either the face image or the sound.

Reference personality information is any information about the personality of a past lender. This personality is, for example, impatient, long-suffering, merciless, stubborn, mild, bullish, bearish, often false, caring, polite to superiors, always keeping promises, frequent promises. And so on. For this personality, for example, writing on the SNS or various information sites, the contents of resumes heard by financial institutions, or data acquired from a personality diagnosis test, a temperament analysis test, or the like may be utilized. When this reference personality information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 is weak and merciless, the reference information P35 is bullish but compassionate, and so on.

Reference future information is any information about the future potential of an individual of a past lender. This reference future information may be scored based on educational background and current place of employment, or the position, years of service, annual income, etc. at the current place of employment may be included in the score. In addition, if there is a career change history so far, the history information and the career information that has been cultivated may be acquired as well. Such reference future information may be extracted from, for example, an application submitted to a financial institution if there is a column to be described in such a resume or resume. In addition, the presence or absence of qualifications, the speed of promotion to a position, the experience of studying abroad, the experience of being seconded, etc. may also be used as explanatory variables for this reference future information. Furthermore, if the name is listed as the inventor of the patent or the author of the treatise, this may also be added as an explanatory variable of the future potential information for reference. When applying this reference future information to the above-mentioned reference information P34 to P36, for example, the reference information P34 is 〇 × university graduate ◆◆ 15 years of service at a company, the position is a section chief, 5 years ago 〇 △ Seconded to the company, reference information P35 is ◇ 〇 University graduate, after working for 〇 〇 company for 5 years, runs 〇 □ × business independently, currently has annual sales of 50 million yen and has 2 employees.

The reference hobby information is all the information about the personal hobbies and special skills of the past lenders. Hobbies include, for example, golf, fishing, mahjong, running, billiards, bowling, reading, watching sports, driving, marine sports, etc. , Tea ceremony (high school, tea ceremony manager), etc. The reference taste information does not necessarily require both hobbies and special skills, and may be composed of only one of them. When this reference information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 has a hobby: fishing, a special skill: a tea ceremony, and the reference information P35 has a hobby: marine sports. Special skill: Tea ceremony (high school, tea ceremony manager), etc.

Reference attribute information is all information about the personal attributes of past lenders. Reference attribute information includes the individual's age and health status, annual income, date of birth, birthplace, and family environment (whether the wife is pregnant, the family is pursuing a disability or illness, whether or not they live with their grandparents, etc. Whether or not the caregiver is at home, whether or not the child is affected, whether or not there is DV or abuse, whether or not the child is divorced, whether or not the household income, whether or not there is livelihood protection, whether or not there is a wife and child, and their age structure, etc. If the child is in school, the school expenses and the expected school expenses in the future, whether the individual is currently in employment or working, etc. are also included. Regarding the state of health, whether or not the individual is in perfect health or has some kind of congenital disorder and the degree of the disorder, and whether or not there is an acquired disorder after birth and the degree of the disorder. Also, whether or not you have some kind of illness after birth, whether or not the illness continues at present and its degree, allergic condition, inflammatory condition, injured condition, chronic condition, medication status, etc. , Contains all information that indicates health status. The health condition included in the reference attribute information may be derived from medical data itself such as heart rate, pulse rate, blood data, electrocardiogram data, and X-ray image. All of these may be obtained through declarations and documents submitted by each household, medical certificates of doctors, and the like. When applying this reference attribute information to the above-mentioned reference information P34 to P36, for example, the reference information P34 is age 46 years old, birthplace: Shizuoka, annual income of ¥ 100,000, working at a company, family environment: Wife and eldest son, eldest daughter family of four, eldest son high school, eldest daughter junior high school student, health condition: have had surgery for gastric ulcer in the past, reference information P35 is age 38 years old, birthplace: Tokyo, annual income 100,000 Yen, ▲ 〇 Worked at a company, family environment: family of three, wife and eldest daughter, eldest daughter is elementary school student, health condition: good, etc.

The reference area information is information about the area to which the individual of the past loan recipient belongs. The area to which an individual belongs here includes not only the area of the current address, but also the area of work, the area of the previous address, and the place of origin. This reference area information may be grouped into the Kanto region, Tokyo, etc., but may be subdivided at the city / ward / town / village, town name, and street address level. While there are areas grouped and subdivided in this way, business sentiment, events, accidents, incidents, disasters, infectious diseases, etc. in each segmented area are reflected as this reference area information. Since this reference industry information includes elements governed by the reference external environment information in the first embodiment, it may be configured by quoting this reference external environment information. When applying this reference area information to the above-mentioned reference information P34 to P36, for example, the reference information P34 has a XX incident in Chiyoda-ku, Tokyo, and the reference information P35 is a business sentiment in Nara prefecture. The index is 〇〇 mag.

Reference reputation information is information about the personal reputation of a past lender. This reputation is, for example, a reputation on a bulletin board on SNS or the Internet, a reputation on a product sold by the individual or an event operated by the individual, an evaluation or reputation on a blog operated by the individual, or the like. Reputation information for reference is mainly obtained from SNS, blogs, information sites, bulletin boards, etc. on the Internet. When this reference reputation information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 causes a problem related to rights such as copyright and portrait right on the information site operated by the company. In some cases, the reference information P35 has been slandered or the like by name through the SNS.

When the lender is a corporation, the reference information includes expert opinion information for reference, transaction information for reference, credit history information for reference, corporate ethics information for reference, future information for reference, attribute information for reference, and industry for reference. It is composed of any one or more of information, reference management information, reference area information, and reference reputation information. Each of these reference information was obtained from an individual of a past lender. The details of these reference information when the lender is an individual will be described below.

The reference expert opinion information is information that reflects the expert opinion published for the reference financial information. The corporations to which the loans have been made in the past are not limited to the corporations that actually provided the loans, but each corporation is set up as a fictitious corporation, and the data obtained by the financial institution setting the credit rating is utilized. You may.

Reference expert opinion information means any information that has been expressed by an expert on reference financial information, and is related to the reasons for the increase or decrease in the shares of each company listed in analyst reports, newspaper articles, etc. Expert comments, future sales and profit outlooks, forecasts, views, etc. In addition, the reference expert opinion information may simply be the prediction itself as to whether the stock of each company will rise, fall, or remain unchanged. This reference expert opinion information includes opinions on the entire Nikkei Average Futures, opinions on specific segments and industries, and opinions on individual stocks. In addition, the reference expert opinion information may include an analyst report by an expert (analyst) posted on the Internet and a forecast of increase or decrease.

Reference transaction information is all information regarding past transactions in the corporation of the past lender. The reference transaction information indicates how fair the actual trading or transaction has been, whether the transaction has been conducted in good faith, and the integrity and security of the trading partner. The reference transaction information also includes the transaction amount and the sense of scale. This reference transaction information can be obtained from deposits and withdrawals to and from bank accounts and settlement data at financial institutions. Deposit and withdrawal information can be obtained from these. Further, the reference transaction information can be obtained from the quotation, the delivery note, and the invoice. For example, if the product is sold or purchased on an EC (electronic commerce) site, it can be obtained from the EC site. In addition, the reference transaction information may also reflect the evaluation contents by the evaluator for the products and services actually bought and sold through the EC site. The higher the evaluation content, the more legitimate and fair the consumption behavior and purchase can be considered. Reference transaction information may be extracted from information such as the quality of the delivered item, compliance with the delivery date, and the politeness of the message before the transaction. Further, if there is a defect in the delivered product in the transaction conducted through the EC site, the evaluation content may be lowered by extracting the defect through writing on the EC site. The reference transaction information may reflect the presence or absence of fraudulent transactions determined from past order data. To determine fraudulent transactions here, purchase a lot of cheap products that can only be purchased once a day by changing the name or changing the address so that the same person cannot be identified. If so, it may be extracted through surveillance technology on the Internet. The integrity and security of a trading partner may be extracted from account deposit / withdrawal details, accounting data, WEB sites, financial statements, and book information. At the time of this extraction, a higher risk trading partner is acquired and learned in advance, and it is determined from these account deposit / withdrawal details, accounting data, WEB site, financial statements, etc. through machine learning. May be good. In addition, if negotiations have been conducted with a trading partner in the past and the transaction history holds a paper document or electronic data of the document, reference transaction information may be extracted from this transaction history document. In addition, reference transaction information may be extracted from the main customer information described on the site launched by the corporation, SNS, or the like. When this reference consumption behavior information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 is sold by a business partner of 〇 × Co., Ltd. and 10,000 LED bulbs as a product for 〇 〇 yen. The evaluation by the EC site is 4 points out of 5 grades, the reference information P35 is sold by 40 PCs with a business partner of △ ◆ Co., Ltd. for 55,000 yen, and the evaluation by the EC site is out of 5 grades. 5 points, etc.

The reference credit history information is all information regarding the credit history of the corporation to which the loan has been made in the past. Examples of reference credit history information include whether or not there is a history of non-payment of communication charges for mobile phones, etc., and the degree of delinquency, the payment status of pensions and health insurance that companies should pay, and the history of delinquency. Documents of insurance that you have taken out, such as tax delinquency, whether or not you have a history of debt consolidation or self-bankruptcy in the past. This reference credit history information may be obtained from the bank's deposit / withdrawal history. When this reference credit history information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 has no delinquency history of mobile phones and credit loans in the past, and the reference information P35 has credit in the past. The loan delinquency history is 3 times, the reference information P36 has a mobile phone call charge delinquency history of 1 time, and so on.

Reference corporate ethics information is all information related to corporate ethics up to that point in the corporation of the past lender. Corporate ethics here refers to whether the waste is properly treated, whether the factory does not generate pollution, but whether consideration is given to neighboring residents, etc., but it is not limited to this. , Infringement of patent rights, violation of law, misconduct and troubles such as leakage of technology and leakage of personal information, tax exemption, and various crimes may be reflected in this reference corporate ethics information. For example, when news comes from unfair dismissal, power harassment, death from overtime due to overtime work, suicide, etc., the news information is taken in from various information sites on the Internet to form this reference corporate ethics information. You may do so. When this reference corporate ethics information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 is the leakage of defense confidential information 〇〇, and the reference information P35 is power harassment and an employee commits suicide. ..

The reference future information is all information about the future of the corporation to which the loan is made in the past. This reference future information is set to be high credit if the company is likely to grow significantly in the future, and low credit if the company is likely to stagnate in the future. It is an explanatory variable to do. The reference future information may be extracted from the company's R & D efforts, for example, from the text data of patent gazettes, articles, and technical reports issued by the company, to meet future market needs. The number of patent applications, etc. that include the keywords to be used may be scored based on the ratio to the total number of patent applications in the industry. Sexual information may be scored. Similarly, the future potential information for reference may be scored from news articles that have a dark future potential. Further, as for the future of a corporation, if the future of the industry is high, the future of the corporation belonging to the corporation tends to be high as well. Therefore, the market future information in the first embodiment may be cited. ..

The reference attribute information is all information regarding the attributes of the corporation of the past lender. The attributes here include, but are not limited to, the type of business, technical field, history, history, capital, scale, number of employees, years of establishment, etc. of the corporation, but are not limited to this, such as corporate culture and employee morale. The number of hires is also included.

Reference industry information is all information about the industry to which the corporation of the past lender belongs. Reference industry information includes information on the history of the industry, the position of the industry in the global environment, growth potential as an industry, business practices, supply and demand relationships, KSF, KBF, business models of the industry, flow of money and goods, etc. Is. Since this reference industry information includes elements governed by the reference market information and the reference external environment information in the first embodiment, the reference market information and the reference external environment information can be cited. It may be configured.

The reference management information is all information about the management of the corporation to which the loan is made in the past. The management here includes not only the president but also the officers who participate in the management. This reference management information includes the management's career and achievements, as well as the management's age and health status, annual income, date of birth, birthplace, and family environment. In addition, fame as a manager, punishment, scandal, etc. may be scored in addition to the explanatory variables. In addition to this, any information regarding the first impression of management may be included in this reference management information. In such a case, it can be obtained through the face image of the manager, the voice uttered, or the like, as in the case of the above-mentioned first impression information for reference. The acquired face image and voice of the manager are analyzed respectively. The face image may be automatically discriminated based on the feature amount of the analyzed image and converted into data by using image analysis and, if necessary, deep learning technology. For example, it is possible to extract features that affect the credit aspect, such as a part that seems to be unconfident by lying and a part that contains malicious intent through a face image. For voice, we extract characteristics that affect credit, such as lying, unconfident words and actions, and repeating words and actions that are different from the past. For voice, features that affect credit may be extracted by extracting characteristic intonations and accents using existing analysis techniques and machine learning. It may consist of both a face image and a voice, or one of a face image and a voice.

The reference area information is information about the area to which the corporation of the past loan recipient belongs. The area to which the corporation belongs is the area of the address where the corporation is located. This reference area information may be grouped into the Kanto region, Tokyo, etc., but may be subdivided at the city / ward / town / village, town name, and street address level. While there are areas grouped and subdivided in this way, business sentiment, events, accidents, incidents, disasters, infectious diseases, etc. in each segmented area are reflected as this reference area information. Since this reference industry information includes elements governed by the reference external environment information in the first embodiment, it may be configured by quoting this reference external environment information. When applying this reference area information to the above-mentioned reference information P34 to P36, for example, the reference information P34 has a XX incident in Chiyoda-ku, Tokyo, and the reference information P35 is a business sentiment in Nara prefecture. The index is 〇〇 mag.

The reference reputation information is information on the reputation of the corporation to which the loan is made in the past. This reputation is, for example, a reputation on a bulletin board on SNS or the Internet, a reputation on a product or service sold by the corporation, a reputation on an event operated by the corporation, an evaluation or reputation on a blog operated by the corporation, or the like. Reputation information for reference is mainly obtained from SNS, blogs, information sites, bulletin boards, etc. on the Internet. When this reference reputation information is applied to the above-mentioned reference information P34 to P36, for example, the reference information P34 causes a problem related to rights such as copyright and portrait right on an information site operated by a corporation. In some cases, reference information P35 indicates that the corporation has been protested by a charity through SNS.

Next, in this second embodiment, the solution of the creditworthiness will be searched, but since the details of the method are the same as those in the first embodiment, by quoting the explanation of the first embodiment, the following The explanation in is omitted.

For example, in the case of personal loans, in addition to financial information, consumer behavior information, transaction information, credit history information, personal network information, first impression information, personality information, future information, taste information, attribute information, region Obtain either information or reputation information. The combination of the reference information according to the acquired information, the above-mentioned reference financial information, and the credit rating for the combination are set in advance at three or more levels of association. Here, the consumption behavior information corresponds to the reference consumption behavior information, the transaction information corresponds to the reference transaction information, the credit history information corresponds to the reference credit history information, and the personal network information corresponds to the reference personal network. Corresponding to information, first impression information corresponds to reference first impression information, personality information corresponds to reference personality information, future information corresponds to reference future information, and preference information corresponds to , Corresponds to reference preference information, attribute information corresponds to reference attribute information, regional information corresponds to reference regional information, and reputation information corresponds to reference reputation information. The acquisition methods of consumption behavior information, transaction information, credit history information, personal network information, first impression information, personality information, future information, taste information, attribute information, regional information, and reputation information are for reference according to each. Similar to information.

For example, when acquiring consumption behavior information, the combination of the reference financial information and the reference consumption behavior information as the reference information shown in FIG. 11 and the credit rating for the combination are associated with each other in three or more stages. Create learning data consisting of degrees.

In the example of FIG. 11, for example, reference financial information P01 to P03 and reference information P34 to 37 contain reference consumption behavior information P34 to 37 as input data. The intermediate node shown in FIG. 11 is a combination of reference consumption behavior information and reference financial information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference financial information and the reference consumption behavior information is associated with each other through three or more levels of association with the credit rating as the output solution. The reference financial information and the reference consumption behavior information are arranged on the left side through this degree of association, and the credit rating is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to each credit level with respect to the reference financial information and the reference consumption behavior information arranged on the left side. In other words, this degree of association is an index showing what kind of credit is likely to be associated with each reference financial information and reference consumption behavior information, and is based on the reference financial information and reference consumption behavior information. It shows the accuracy in selecting each credit rating that is most likely. In addition to financial information, it can be judged according to the actual consumption behavior, and the possibility of collecting funds will be different. Therefore, the optimum credit rating will be searched for by combining these reference financial information and reference consumption behavior information.

In the example of FIG. 11, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference financial information, the reference consumption behavior information, and the credit rating in that case is suitable for determining the actual search solution, and stores these. By analyzing and analyzing, the degree of association shown in FIG. 11 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of reference financial information P01 and reference information (reference consumption behavior information) P36, the creditworthiness is analyzed from past data. When there are many cases where the credit rating is "possible bankruptcy", the degree of association leading to this "possible bankruptcy" is set higher, and there are many cases of "normal" and cases of "possible bankruptcy". If the number is low, the degree of association that leads to "normal" is set high, and the degree of association that leads to "possible failure" is set low. For example, in the example of the intermediate node 61a, it is linked to the output of "possible failure" and "normal", but from the previous case, the degree of association of w13 leading to "possible failure" is set to 7 points, and "normal". The degree of association of w14 that leads to "" is set to 2 points.

Further, the degree of association shown in FIG. 11 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 11, the node 61b is a node in which the reference information (reference consumption behavior information) P34 is combined with the reference financial information P01, and the association degree of “substantial failure” is w15. , The degree of association of "very high" is w16. The node 61c is a node that is a combination of reference information (reference consumption behavior information) P35 and P37 with respect to reference financial information P02, and has a credit rating of w17 and a credit rating of w18. ..

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually performing a search for determining the credit rating from now on, the above-mentioned learned data will be used. In such a case, consumption behavior information is acquired in addition to financial information from the company that newly determines the creditworthiness. This consumption behavior information corresponds to the above-mentioned reference consumption behavior information.

Based on the newly acquired financial information and consumption behavior information in this way, the optimum credit rating is searched for. In such a case, the degree of association shown in FIG. 11 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02 and the consumption behavior information is the same as or similar to P37, the node 61d is associated via the degree of association. In this node 61d, "substantial failure" is associated with w19, and "need attention" is associated with the degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

The intermediate node 61 may be selected based on the degree of association w1 to w12 extending from this input. That is, the larger the degree of association w1 to w12, the heavier the weighting in the selection of the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weights in the selection of the intermediate node 61 may all be the same.

When acquiring other transaction information, credit history information, personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information, reference information corresponding to these is shown in FIG. As shown in, create training data in the same way in combination with financial information for reference. Then, the actually acquired transaction information, credit history information, personal network information, first impression information, personality information, future information, taste information, attribute information, regional information, reputation information, and the financial information of the individual are acquired. The credit rating can be obtained in the same manner by referring to the degree of association acquired in advance.

In addition to financial information, any two or more of consumption behavior information, transaction information, credit history information, personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information For learning, which consists of three or more levels of association between the combination of two or more reference information according to the two or more information to be acquired with the reference financial information and the creditworthiness of the combination. By creating the data, it is possible to search for a solution of creditworthiness in the same way. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.

In addition to financial information, one or more of consumption behavior information, transaction information, credit history information, personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information. In addition, when acquiring the management plan information, intellectual asset information, market condition information, and external environment information in the first embodiment, similarly, the reference management plan information and the reference intellectual according to the acquired information. By creating learning data consisting of three or more levels of association between asset information, market information for reference, and external environment information for reference, and the creditworthiness of the combination, a solution search for creditworthiness is performed in the same manner. be able to. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.

In the case of corporate loans, in addition to financial information, expert opinion information, transaction information, credit history information, corporate ethics information, future potential information, attribute information, industry information, management information, regional information, etc. Get any of the reputation information. The combination of the reference information according to the acquired information, the above-mentioned reference financial information, and the credit rating for the combination are set in advance at three or more levels of association. Here, the expert opinion information corresponds to the reference expert opinion information, the transaction information corresponds to the reference transaction information, the credit history information corresponds to the reference credit history information, and the corporate ethics information corresponds to. Corresponds to corporate ethics information for reference, future information corresponds to future information for reference, attribute information corresponds to attribute information for reference, industry information corresponds to industry information for reference, management information Corresponds to the reference management information, the regional information corresponds to the reference regional information, and the reputation information corresponds to the reference reputation information.

For example, when acquiring expert opinion information, there are three or more levels of a combination of reference financial information, reference expert opinion information as reference information shown in FIG. 11, and creditworthiness for the combination. Create learning data consisting of the degree of association.

In the example of FIG. 11, for example, reference financial information P01 to P03 and reference information P34 to 37 contain reference expert opinion information P34 to 37 as input data. The intermediate node shown in FIG. 11 is a combination of reference financial information and reference expert opinion information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference financial information and the reference expert opinion information is associated with each other through three or more levels of association with the credit rating as the output solution. The reference financial information and the reference expert opinion information are arranged on the left side through this degree of association, and the credit rating is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to each credit level with respect to the reference financial information and the reference expert opinion information arranged on the left side. In other words, this degree of association is an indicator of what credit rating each reference financial information and reference expert opinion information is likely to be associated with, and is a reference financial information and reference expert opinion. It shows the accuracy in selecting each credit rating that is most likely from the information. In addition to financial information, it can be judged according to the opinions of the experts, and the possibility of collecting funds will be different. Therefore, the optimum credit rating will be searched for by combining these reference financial information and reference expert opinion information.

In the example of the degree of association shown in FIG. 11, the node 61b is a node in which the reference information (reference expert opinion information) P34 is combined with the reference financial information P01, and the association degree of "substantial failure" is The degree of association between w15 and "very high" is w16. The node 61c is a node that is a combination of reference information (reference expert opinion information) P35 and P37 with respect to reference financial information P02, and has a credit rating of w17 and a credit rating of w18. There is.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually performing a search for determining the credit rating from now on, the above-mentioned learned data will be used. In such a case, in addition to financial information, expert opinion information will be obtained from the company that newly determines the creditworthiness. This expert opinion information corresponds to the above-mentioned reference expert opinion information.

Based on the newly acquired financial information and expert opinion information in this way, the optimum credit rating is searched for. In such a case, the degree of association shown in FIG. 11 (Table 1) acquired in advance is referred to. For example, when the newly acquired financial information is the same as or similar to P02, and the expert opinion information is the same as or similar to P37, the node 61d is determined via the degree of association. The node 61d is associated with a "substantial failure" w19 and a "need attention" with a degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In addition to other financial information, when acquiring transaction information, credit history information, corporate ethics information, future potential information, attribute information, industry information, management information, regional information, reputation information, reference information corresponding to these As shown in FIG. 11, training data is similarly created in combination with the reference financial information. Then, the actually acquired transaction information, credit history information, corporate ethics information, future potential information, attribute information, industry information, management information, regional information, reputation information, and financial information of the corporation were acquired and acquired in advance. The credit rating can be obtained in the same way by referring to the degree of association.

In addition to financial information, obtain any two or more of expert opinion information, transaction information, credit history information, corporate ethics information, future potential information, attribute information, industry information, management information, regional information, and reputation information. In this case, learning data consisting of three or more levels of association between the combination of two or more reference information with the reference financial information and the creditworthiness of the combination according to the two or more information to be acquired is used. By making it, it is possible to search for a solution of credit rating in the same way. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.

In addition to financial information, one or more of consumption behavior information, transaction information, credit history information, personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information. In addition, when acquiring the management plan information, intellectual asset information, market condition information, and external environment information in the first embodiment, similarly, the reference management plan information and the reference intellectual according to the acquired information. By creating learning data consisting of three or more levels of association between asset information, market information for reference, and external environment information for reference, and the creditworthiness of the combination, a solution search for creditworthiness is performed in the same manner. be able to. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.

Third Embodiment Hereinafter, the third embodiment will be described. In executing this third embodiment, the loanee creditworthiness determination system 1, the information acquisition unit 9, the search device 2, and the database 3 used in the second embodiment are similarly used. The description of each of these configurations will be omitted below by quoting the description of the first embodiment. Further, in the third embodiment, reference consumption behavior information, reference transaction information, reference credit history information, reference personal network information, reference first impression information, as reference information when the lender is an individual, Since the details of the reference personality information, the reference future information, the reference preference information, the reference attribute information, the reference area information, and the reference reputation information are the same as those in the second embodiment, the description of the second embodiment will be described. The explanation below is omitted by quoting. Similarly, in the third embodiment, when the lender is a corporation, reference expert opinion information, reference transaction information, reference credit history information, reference corporate ethics information, and reference future potential as reference information. Since the details of the information, the reference attribute information, the reference industry information, the reference management information, the reference area information, and the reference reputation information are the same as those in the second embodiment, the explanation of the second embodiment should be cited. The explanation below is omitted.

In the third embodiment, for example, as shown in FIG. 12, an example is shown in which the degree of association between the reference credit history information and the individual credit rating is set to three or more levels. In creating a trained model from these datasets, this credit rating sets a fictitious persona as well as the individual actually judged in the past, and includes the credit rating judged by financial institutions etc. in the training data. You may.

In the example of FIG. 12, it is assumed that the input data is, for example, reference credit history information P01 to P03. The reference credit history information as such input data is linked to the output. In this output, the credit rating as the output solution is displayed. The reference credit history information is associated with each other through three or more levels of association with the credit as the output solution. The reference credit history information is arranged on the left side via this degree of association, and the credit degree is arranged on the right side via this degree of association. The degree of association indicates which credit degree is highly relevant to the reference credit history information arranged on the left side. In other words, this degree of association is an index showing what kind of credit history each reference credit history information is likely to be associated with, and is used to select the most probable credit rating from the reference credit history information. It shows the accuracy.

In the example of FIG. 12, w13 to w19 are shown as the degree of association. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the creditworthiness as an output. On the contrary, the closer to one point, the lower the degree of relevance of each combination as an intermediate node to the creditworthiness as an output.

The search device 2 acquires in advance the degree of association w13 to w19 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference credit history information and the credit rating in that case is adopted in determining the actual search solution, and analyzes and analyzes these. By doing so, the degree of association shown in FIG. 12 is created. Since the solution search method using this degree of association is the same as the description in FIG. 3 of the first embodiment, the description below will be omitted by quoting the description.

Further, the degree of association shown in FIG. 12 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In such a case, as shown in FIG. 13, reference credit history information is input as input data, each credit rating is output as output data, and at least one or more hidden layers are provided between the input node and the output node. , Machine learning may be made. On the contrary, the credit rating may be input and the reference credit history information may be output.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, the credit rating will be predicted using the above-mentioned trained data in actually determining the credit rating from now on. In such a case, the latest credit history information of the individual of the lender who actually determines the creditworthiness is newly acquired. This credit history information is composed of the same type of data as the above-mentioned reference credit history information.

The newly acquired financial information is input by the information acquisition unit 9 described above. The information acquisition unit 9 may acquire such financial information as electronic data.

Based on the credit history information newly acquired in this way, the credit rating that is likely to be determined is actually searched for the credit history information. In such a case, the degree of association shown in FIG. 12 (Table 1) acquired in advance is referred to. For example, when the newly acquired credit history information is the same as or similar to P02, "normal" is associated with w15 and "substantial failure" is associated with the association degree w16 through the association degree. In such a case, "normal" with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the “substantial failure” in which the degree of association is low but the association itself is recognized may be selected as the optimum solution. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In this way, it is possible to search for the credit rating to be determined from the newly acquired credit history information and display it to the user (consultant, bank clerk, customer). By looking at the search result, the user can grasp the degree of credit of the loanee candidate based on the searched credit rating. By the way, in the process of outputting this credit rating, in addition to simply displaying the searched credit rating, even if the advice is configured by displaying the specific amount of financing based on this credit rating. good.

Further, in the third embodiment, as shown in FIG. 14, three or more levels of association between the reference credit history information, the combination of the reference information shown below, and the credit rating for the combination are set. In the same case, the search solution can be derived in the same way.

In the case of a loan for an individual assumed in the third embodiment, in addition to the credit history information, personal connection information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information Get one. The combination of the reference information according to the acquired information, the above-mentioned reference credit history information, and the credit rating for the combination are set in advance at three or more levels of association. Here, the credit history information corresponds to the reference credit history information, the personal network information corresponds to the reference personal network information, the first impression information corresponds to the reference first impression information, and the personality information corresponds to the personality information. Corresponds to personality information, future potential information corresponds to reference future potential information, preference information corresponds to reference preference information, attribute information corresponds to reference attribute information, regional information corresponds to reference Corresponds to regional information, and reputation information corresponds to reference reputation information. The method of acquiring these credit history information, personal connection information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information is the same as the reference information corresponding to each.

For example, when acquiring personal connection information, the combination of the reference credit history information and the reference personal connection information as the reference information shown in FIG. 14 and the credit rating for the combination have three or more levels of association. Create learning data consisting of.

In the example of FIG. 14, for example, reference credit history information P01 to P03 and reference information P34 to 37 contain reference personal connection information P34 to 37 as input data. The intermediate node shown in FIG. 14 is a combination of reference credit history information and reference personal connection information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference credit history information and the reference personal connection information is associated with each other through three or more levels of association with the credit as the output solution. The reference credit history information and the reference personal connection information are arranged on the left side via this degree of association, and the credit degree is arranged on the right side via this degree of association. The degree of association indicates the degree of relevance to each credit degree with respect to the reference credit history information and the reference personal connection information arranged on the left side. In other words, this degree of association is an index indicating what kind of credit is likely to be associated with each reference credit history information and reference personal connection information, and is based on the reference credit history information and reference personal connection information. It shows the accuracy in selecting each credit rating that is most likely. In addition to the credit history information, it is possible to make a judgment according to the personal network information, and the possibility of collecting funds will be different. Therefore, the optimum credit rating is searched for by combining the reference credit history information and the reference personal connection information.

In the example of FIG. 14, w13 to w22 are shown as the degree of association. As shown in Table 1, these w13 to w22 are shown in 10 stages, and the closer to 10 points, the higher the degree of relevance of each combination as an intermediate node to the output, and conversely, 1 point. The closer they are, the less relevant each combination as an intermediate node is to the output.

The search device 2 acquires in advance the degree of association w13 to w22 of three or more stages shown in FIG. That is, the search device 2 accumulates past data as to which of the reference credit history information, the reference personal connection information, and the credit rating in that case is suitable for determining the actual search solution, and stores these. By analyzing and analyzing, the degree of association shown in FIG. 14 is created.

This analysis and analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference credit history information P01 and the reference information (reference personal connection information) P36, the credit rating is analyzed from the past data. When there are many cases where the credit rating is "possible bankruptcy", the degree of association leading to this "possible bankruptcy" is set higher, and there are many cases of "normal" and cases of "possible bankruptcy". If the number is low, the degree of association that leads to "normal" is set high, and the degree of association that leads to "possible failure" is set low. For example, in the example of the intermediate node 61a, it is linked to the output of "possible failure" and "normal", but from the previous case, the degree of association of w13 leading to "possible failure" is set to 7 points, and "normal". The degree of association of w14 that leads to "" is set to 2 points.

Further, the degree of association shown in FIG. 14 may be composed of the nodes of the neural network in artificial intelligence. That is, the weighting coefficient for the output of the node of this neural network corresponds to the above-mentioned degree of association. Further, the network is not limited to a neural network, and may be composed of all decision-making factors constituting artificial intelligence.

In the example of the degree of association shown in FIG. 14, the node 61b is a node in which the reference information (reference personal connection information) P34 is combined with the reference credit history information P01, and the association degree of "substantial failure" is w15. , The degree of association of "very high" is w16. The node 61c is a node that is a combination of reference information (reference personal connection information) P35 and P37 with respect to reference credit history information P02, and has a credit degree association of w17 and a credit degree association degree of w18. ..

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually performing a search for determining the credit rating from now on, the above-mentioned learned data will be used. In such a case, personal network information is acquired in addition to the credit history information from the company that newly determines the creditworthiness. This personal connection information corresponds to the above-mentioned reference personal connection information.

Based on the newly acquired credit history information and personal connection information in this way, the optimum credit rating is searched for. In such a case, the degree of association shown in FIG. 14 (Table 1) acquired in advance is referred to. For example, when the newly acquired credit history information is the same as or similar to P02 and the personal connection information is the same as or similar to P37, the node 61d is associated via the degree of association. In this node 61d, "substantial failure" is associated with w19, and "need attention" is associated with the degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

The intermediate node 61 may be selected based on the degree of association w1 to w12 extending from this input. That is, the larger the degree of association w1 to w12, the heavier the weighting in the selection of the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weights in the selection of the intermediate node 61 may all be the same.

When acquiring other personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information, reference information corresponding to these is shown in FIG. Create learning data in the same way by combining with historical information. Then, the actually acquired personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, reputation information, and the credit history information of the individual are acquired, and the degree of association acquired in advance is obtained. The credit rating can be calculated in the same way by referring to it.

In addition to credit history information, if any two or more of personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information are acquired, they are acquired. The same is true by creating learning data consisting of a combination of two or more reference information corresponding to two or more pieces of information with reference credit history information and three or more levels of association with the creditworthiness of the combination. It is possible to search for a solution of creditworthiness. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.

Further, in addition to the credit history information, in addition to any one or more of personal network information, first impression information, personality information, future potential information, taste information, attribute information, regional information, and reputation information, further, in the first embodiment. Similarly, when acquiring management plan information, intellectual asset information, market condition information, and external environment information, reference management plan information, reference intellectual asset information, reference market condition information, and reference according to the acquired information. By creating learning data consisting of a combination with external environment information and a degree of association between the combination and the degree of credibility of the combination, it is possible to search for a solution of the degree of credibility in the same manner. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.
Further, in the case of acquiring any one or more of the management plan information, the intellectual asset information, the market condition information, and the external environment information in the first embodiment in addition to the credit history information, the reference credit history information and its reference are also obtained. Three or more levels of association between the combination of reference management plan information, reference intellectual asset information, reference market information, and reference external environment information according to the information of the first embodiment to be acquired, and the creditworthiness of the combination. By creating learning data consisting of degrees, it is possible to search for a solution of credit rating in the same way.

In the case of corporate loans, in addition to credit history information, any of expert opinion information, corporate ethics information, future potential information, attribute information, industry information, management information, regional information, and reputation information is provided. get. The combination of the reference information according to the acquired information, the above-mentioned reference credit history information, and the credit rating for the combination are set in advance at three or more levels of association. Here, the expert opinion information corresponds to the reference expert opinion information, the corporate ethics information corresponds to the reference corporate ethics information, the future information corresponds to the reference future information, and the attribute information corresponds to the reference information. , Corresponding to reference attribute information, industry information corresponds to reference industry information, management information corresponds to reference management information, regional information corresponds to reference regional information, reputation information , Corresponds to reputation information for reference.

For example, when acquiring corporate ethics information, there are three or more levels of a combination of reference credit history information, reference corporate ethics information as reference information shown in FIG. 14, and creditworthiness for the combination. Create learning data consisting of the degree of association.

In the example of FIG. 14, for example, reference credit history information P01 to P03 and reference information P34 to 37 contain reference corporate ethics information P34 to 37 as input data. The intermediate node shown in FIG. 14 is a combination of the reference credit history information and the reference corporate ethics information as such input data. Each intermediate node is further linked to the output. In this output, the credit rating as the output solution is displayed.

Each combination (intermediate node) of the reference credit history information and the reference corporate ethics information is associated with each other through three or more levels of association with the credit as the output solution. The reference credit history information and the reference corporate ethics information are arranged on the left side through this degree of association, and the credit degree is arranged on the right side through this degree of association. The degree of association indicates the degree of relevance to each credit degree with respect to the reference credit history information and the reference corporate ethics information arranged on the left side. In other words, this degree of association is an index showing what kind of credit is likely to be associated with each reference credit history information and reference corporate ethics information, and the reference credit history information and reference corporate ethics. It shows the accuracy in selecting each credit rating that is most likely from the information. In addition to credit history information, it can be judged according to the actual corporate ethics, and the possibility of collecting funds will be different. Therefore, the optimum credit rating will be searched for by combining the reference credit history information and the reference corporate ethics information.

In the example of the degree of association shown in FIG. 14, the node 61b is a node in which the reference information (reference corporate ethics information) P34 is combined with the reference credit history information P01, and the association degree of "substantial bankruptcy" is The degree of association between w15 and "very high" is w16. The node 61c is a node that is a combination of reference information (reference corporate ethics information) P35 and P37 with respect to reference credit history information P02, and has a credit rating of w17 and a credit rating of w18. There is.

Such a degree of association is what is called learned data in artificial intelligence. After creating such learned data, when actually performing a search for determining the credit rating from now on, the above-mentioned learned data will be used. In such a case, corporate ethics information is obtained in addition to credit history information from the company that newly determines the creditworthiness. This credit history information corresponds to the above-mentioned reference corporate ethics information.

Based on the newly acquired credit history information and corporate ethics information in this way, the optimum credit rating is searched for. In such a case, the degree of association shown in FIG. 11 (Table 1) acquired in advance is referred to. For example, when the newly acquired credit history information is the same as or similar to P02, and the corporate ethics information is the same as or similar to P37, the node 61d is determined via the degree of association. The node 61d is associated with a "substantial failure" w19 and a "need attention" with a degree of association w20. In such a case, the “substantial bankruptcy” with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and it is also possible to select the “point of caution” as the optimum solution, which has the lowest degree of association but the association itself is recognized. In addition to this, it goes without saying that an output solution to which the arrows are not connected may be selected, and as long as it is based on the degree of association, it may be selected in any other priority.

In addition to other credit history information, when acquiring corporate ethics information, future potential information, attribute information, industry information, management information, regional information, and reputation information, reference information corresponding to these is shown in FIG. Similarly, create learning data in combination with reference credit history information. Then, the actually acquired corporate ethics information, future potential information, attribute information, industry information, management information, regional information, reputation information, and the credit history information of the corporation are acquired, and the degree of association acquired in advance is referred to. Similarly, the creditworthiness can be calculated.

In addition to credit history information, if any two or more of corporate ethics information, future potential information, attribute information, industry information, management information, regional information, and reputation information are to be acquired, the two or more to be acquired. By creating learning data consisting of a combination of two or more reference information according to the information with the reference credit history information and three or more levels of association with the credit rating for the combination, the credit rating can be similarly improved. You can search for a solution. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.

In addition to credit history information, in addition to any one or more of corporate ethics information, future potential information, attribute information, industry information, and management information, further, management plan information and intellectual asset information in the first embodiment, Similarly, when acquiring market condition information and external environment information, the combination with reference management plan information, reference intellectual asset information, reference market condition information, and reference external environment information according to the acquired information, and the relevant By creating learning data consisting of three or more levels of association with the creditworthiness of the combination, it is possible to search for a solution of the creditworthiness in the same manner. Since the specific method in such a case is the same as the description of FIG. 10 of the first embodiment, the description below will be omitted by quoting the description.

Further, in the case of acquiring any one or more of the management plan information, the intellectual asset information, the market condition information, and the external environment information in the first embodiment in addition to the credit history information, the reference credit history information and its reference are also obtained. Three or more levels of association between the combination of reference management plan information, reference intellectual asset information, reference market information, and reference external environment information according to the information of the first embodiment to be acquired, and the creditworthiness of the combination. By creating learning data consisting of degrees, it is possible to search for a solution of credit rating in the same way.

Further, as shown in FIG. 15, the present invention determines each credit rating based on the degree of association between two or more types of information, the reference information U and the reference information V. It is assumed that the reference information U is the reference credit history information, and the reference information V is the reference information P34 to 37 shown in FIG. Alternatively, it is assumed that the reference information U is the reference information P34 to 37 shown in FIG. 14, and the reference information V is the reference credit history information.

At this time, as shown in FIG. 15, the output obtained for the reference information U may be used as the input data as it is, and may be associated with the output via the intermediate node 61 in combination with the reference information V. For example, for the reference information U, after the output solution is output, this may be used as an input as it is, and the output may be searched by using the degree of association with other reference information V.

In the above-mentioned degree of association, the degree of association is expressed by a 10-step evaluation, but it is not limited to this, and it may be expressed by a degree of association of 3 or more levels, and conversely, it may be expressed by 3 or more levels. For example, 100 steps or 1000 steps may be used. On the other hand, this degree of association does not include those expressed in two stages, that is, whether or not they are related to each other, either 1 or 0.

According to the present invention having the above-described configuration, anyone can easily search for the creditworthiness of a company considering financing without any special skill or experience. Further, according to the present invention, it is possible to determine the search solution with higher accuracy than that performed by a human being. Further, by configuring the above-mentioned degree of association with artificial intelligence (neural network or the like), it is possible to further improve the discrimination accuracy by learning this.

Since there are many cases where the input data and the output data described above do not exist exactly the same in the process of learning, the input data and the output data may be classified by type. That is, the information P01, P02, ... P15, 16, ... That constitute the input data are classified according to the criteria classified in advance on the system side or the user side according to the content of the information, and the classified inputs. A data set may be created between the data and the output data and trained.

Further, according to the present invention, there is a feature that an optimum solution search is performed through the degree of association set in three or more stages. The degree of association can be described by, for example, a numerical value from 0 to 100% in addition to the above-mentioned 10 steps, but the degree of association is not limited to this, and any step can be described as long as it can be described by a numerical value of 3 or more steps. It may be configured.

In a situation where there are multiple possible candidates for a search solution by determining the creditworthiness with higher credibility and less misunderstanding based on the degree of association expressed by such numerical values of three or more levels. It is also possible to search and display in descending order of the degree of association.

In addition to this, according to the present invention, it is possible to judge without overlooking the discrimination result of the output having an extremely low degree of association such as 1%. It warns the user that even a judgment result with an extremely low degree of association is connected as a slight sign and may be useful as the judgment result once every tens or hundreds of times. be able to.

Further, according to the present invention, there is an advantage that the search policy can be determined by the method of setting the threshold value by performing the search based on the degree of association of three or more stages. If the threshold value is lowered, even if the above-mentioned degree of association is 1%, it can be picked up without omission, but it is unlikely that a more appropriate discrimination result can be detected favorably, and a lot of noise may be picked up. be. On the other hand, if the threshold value is raised, there is a high possibility that the optimum search solution can be detected with a high probability. Sometimes the solution is overlooked. It is possible to decide which one to prioritize based on the ideas of the user side and the system side, but it is possible to increase the degree of freedom in selecting the points to be emphasized.

Further, in the present invention, the above-mentioned degree of association may be updated. This update may reflect information provided via a public communication network such as the Internet. In addition to market information, when event information, external environmental information, household information, real estate information, expert opinion information, and natural environment information knowledge, information, and data are acquired, the degree of association is increased or decreased accordingly. Let me.

In other words, this update corresponds to learning in the sense of artificial intelligence. It can be said that it is a learning act because it acquires new data and reflects it in the learned data.

In addition, this update of the degree of association is done by the system side or the user side based on the contents of research data, treatises, conference presentations, newspaper articles, books, etc. by experts, except when it is based on information that can be obtained from the public communication network. It may be updated artificially or automatically. Artificial intelligence may be utilized in these update processes.

Further, the process of first creating the trained model and the above-mentioned update may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of reading and learning the data set of input data and output data, information corresponding to the input data is read and trained, and the degree of association related to the output data is self-formed from there. You may let it.

1 Lender credit judgment system 2 Search device 21 Internal bus 23 Display unit 24 Control unit 25 Operation unit 26 Communication unit 27 Estimate unit 28 Storage unit 61 node

Claims (17)

In the lender credit judgment program that determines the creditworthiness of the individual of the lender
Information acquisition step to acquire credit history information about the credit history of the individual of the lender who newly determines the creditworthiness,
Refer to the reference credit history information regarding the credit history of the individual of the past lender acquired in advance and the degree of association with the credit rating of three or more levels, and based on the credit history information acquired in the above information acquisition step, the individual of the lender A creditworthiness determination program for a lender, which comprises having a computer perform a determination step for determining the creditworthiness of a loan. In the above information acquisition step, personal network information regarding the personal network of the loan recipient who newly determines the creditworthiness is acquired, and the personal network information is acquired.
In the determination step, the credit history acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference personal connection information related to the individual's personal connection, and the degree of association with the credit rating in three or more stages. The creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the loanee is determined based on the information and the personal connection information. In the above information acquisition step, first impression information consisting of a face image and / or voice of a loanee's individual whose creditworthiness is newly determined is acquired.
In the determination step, the combination of the reference credit history information, the reference first impression information consisting of the face image and / or voice of the individual, and the degree of association with the credit rating in three or more stages are referred to, and the above The creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the loanee is determined based on the credit history information acquired in the information acquisition step and the first impression information. In the above information acquisition step, personality information regarding the personality of the lender who newly determines the creditworthiness is acquired, and the personality information is acquired.
In the determination step, the credit history acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference personality information relating to the personality of the individual, and the degree of association with the credit rating in three or more stages. The creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the borrower is determined based on the information and the personality information. In the above information acquisition step, the future potential information regarding the future potential of the individual of the lender who newly determines the creditworthiness is acquired.
In the determination step, the combination of the reference credit history information, the reference future information regarding the future potential of the individual, and the degree of association with the credit rating in three or more stages are referred to, and the information is acquired in the information acquisition step. The creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the borrower is determined based on the credit history information and the future potential information. In the above information acquisition step, information on the personal hobbies or special skills of the lender who newly determines the creditworthiness is acquired.
In the determination step, the combination of the reference credit history information, the reference preference information related to the individual's hobby or special skill, and the degree of association with the credit rating in three or more stages are referred to, and the information is acquired in the information acquisition step. The creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the borrower is determined based on the credit history information and the hobby information. In the above information acquisition step, attribute information regarding the attributes of the individual of the lender who newly determines the creditworthiness is acquired.
In the determination step, the credit history acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference attribute information relating to the attribute of the individual, and the degree of association with the credit rating in three or more stages. The lender creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the lender is determined based on the information and the attribute information. In the above information acquisition step, the area information regarding the area to which the individual of the lender who newly determines the creditworthiness belongs is acquired, and the area information is acquired.
In the determination step, the credit acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference area information about the area to which the individual belongs, and the degree of association with the credit rating in three or more stages. The creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the borrower is determined based on the history information and the regional information. In the above information acquisition step, reputation information regarding the personal reputation of the lender who newly determines the creditworthiness is acquired.
In the determination step, the credit history acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference reputation information relating to the personal reputation, and the degree of association with the credit rating in three or more stages. The creditworthiness determination program according to claim 1, wherein the creditworthiness of the individual of the borrower is determined based on the information and the reputation information. In the lender credit judgment program that determines the creditworthiness of the lender corporation
Information acquisition step to acquire credit history information about the credit history of the corporation of the lender that newly determines the creditworthiness,
Refer to the reference credit history information regarding the credit history of the past lender's corporation acquired in advance and the degree of association with the credit rating of three or more levels, and based on the credit history information acquired in the above information acquisition step, the lender's corporation A creditworthiness determination program for a lender, which comprises having a computer perform a determination step for determining the creditworthiness of a loan. In the above information acquisition step, corporate ethics information on the ethics of the lender's corporation that newly determines the creditworthiness is acquired.
In the determination step, the combination of the reference credit history information and the reference corporate ethics information regarding the ethics of the corporation and the degree of association with the credit rating of three or more levels are referred to, and the information is acquired in the information acquisition step. The creditworthiness determination program according to claim 10, wherein the creditworthiness of the corporation of the borrower is determined based on the credit history information and the corporate ethics information. In the above information acquisition step, the future information regarding the future potential of the lender's corporation for which the creditworthiness is newly determined is acquired.
In the determination step, the combination of the reference credit history information, the reference future information regarding the future of the corporation, and the degree of association with the credit rating of three or more levels are referred to, and the information is acquired in the information acquisition step. The creditworthiness determination program according to claim 10, wherein the creditworthiness of the corporation of the borrower is determined based on the credit history information and the future potential information. In the above information acquisition step, attribute information regarding the attributes of the corporation of the lender that newly determines the creditworthiness is acquired.
In the determination step, the credit history acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference attribute information related to the attribute of the corporation, and the degree of association with the credit rating in three or more stages. The lender creditworthiness determination program according to claim 10, wherein the creditworthiness of the lender corporation is determined based on the information and the attribute information. In the above information acquisition step, industry information about the industry to which the lender's corporation to which the creditworthiness is newly determined belongs is acquired.
In the determination step, the credit acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference industry information about the industry to which the corporation belongs, and the degree of association with the credit rating in three or more stages. The lender creditworthiness determination program according to claim 10, wherein the creditworthiness of the lender's corporation is determined based on history information and industry information. In the above information acquisition step, management information regarding the management of the corporation to which the loan is to be newly determined to determine the creditworthiness is acquired.
In the determination step, the combination of the reference credit history information and the reference management information about the management of the corporation and the degree of association with the credit rating in three or more stages are referred to, and the information is acquired in the information acquisition step. The lender creditworthiness determination program according to claim 10, wherein the creditworthiness of the lender corporation is determined based on the credit history information and the management information. In the above information acquisition step, the area information regarding the area to which the corporation of the lender for which the creditworthiness is newly determined belongs is acquired.
In the determination step, the credit acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information, the reference area information about the area to which the corporation belongs, and the degree of association with the credit rating in three or more stages. The lender creditworthiness determination program according to claim 10, wherein the creditworthiness of the lender's corporation is determined based on historical information and regional information. In the above information acquisition step, reputation information regarding the reputation of the corporation of the lender that newly determines the creditworthiness is acquired.
In the determination step, the credit history acquired in the information acquisition step is referred to by referring to the combination of the reference credit history information and the reference reputation information regarding the reputation of the corporation and the degree of association with the credit rating in three or more stages. The lender creditworthiness determination program according to claim 10, wherein the creditworthiness of the lender's corporation is determined based on information and reputation information.

Images