System

Abstract

An object of a system according to an embodiment is to learn know-how of an excellent banker and to perform a loan determination fairly and efficiently.SOLUTION: A system according to an embodiment includes a know-how learning unit and a loan determination unit. The know-how learning unit learns know-how of an excellent banker. The loan determination unit makes a loan determination based on the know-how learned by the know-how learning unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology leaves room for improvement in terms of fairness and efficiency, as it leaves the lending decision-making process vulnerable to human error and corruption.

[0005] The system according to the embodiment aims to learn the know-how of excellent bankers and make loan decisions in a fair and efficient manner. [Means for solving the problem]

[0006] The system according to the embodiment includes a know-how learning unit and a loan decision unit. The know-how learning unit learns know-how of excellent bankers. The loan decision unit makes loan decisions based on the know-how learned by the know-how learning unit. [Effects of the Invention]

[0007] The system according to the embodiment can learn the know-how of excellent bankers and make loan decisions in a fair and efficient manner. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The loan decision-making system according to the embodiment of the present invention is a system in which AI learns the know-how of excellent bankers and makes loan decisions. As a result, the loan decision-making system can improve the efficiency of the loan decision-making process in banking operations and achieve fairness.

[0029] A loan decision-making system according to an embodiment includes a know-how learning unit and a loan decision-making unit. The know-how learning unit learns the know-how of excellent bankers. For example, the know-how learning unit collects data on bankers' past loan applications and decision-making criteria, and trains the generation AI on the data. The know-how learning unit can also learn the bankers' risk assessment methods and customer service techniques. For example, the generation AI uses a fine-tuned model to make advanced loan decisions based on the bankers' experience and knowledge. The loan decision-making unit makes loan decisions based on the know-how learned by the know-how learning unit. For example, the loan decision-making unit analyzes data such as a company's financial situation, business plan, and past transaction history to determine whether to grant a loan. The loan decision-making unit can also use the generation AI to make quick and accurate loan decisions. For example, the generation AI makes a loan decision based on input data and outputs the result. As a result, the loan decision-making system according to an embodiment can improve the efficiency and fairness of the loan decision-making process in banking operations. For example, banks can reduce labor costs and prevent errors. Furthermore, customers can receive quick and fair loan decisions.

[0030] The know-how learning unit can learn risk management methods from other industries in addition to banker know-how. For example, the know-how learning unit can learn risk management methods from the insurance and real estate industries in addition to banker know-how. This makes it possible to evaluate not only financial risks but also physical and market risks. In addition, to learn risk management methods from other industries, the know-how learning unit collects insurance contract data and real estate appraisal data and has the AI ​​learn them in an integrated manner. For example, it can learn risk assessment methods from the insurance industry and quality control methods from the manufacturing industry. This improves the accuracy of risk assessment. Furthermore, by incorporating risk management methods from other industries, the know-how learning unit enables the AI ​​to perform multifaceted risk assessments and more comprehensive lending decisions. For example, it can make lending decisions that take insurance risk and market risk into account. This enables multifaceted risk assessments.

[0031] The know-how learning unit can compare and analyze past success stories and failure stories to develop algorithms that increase the probability of success. For example, the know-how learning unit can create a database of bankers' past success stories and failure stories and have the AI ​​learn from them. This makes it possible to develop algorithms that increase the probability of success. The know-how learning unit can also compare and analyze success stories and failure stories to identify factors that led to success and failure. This allows the AI ​​to make loan decisions with a high probability of success. For example, it can suggest improvements to loan decisions based on success stories. Furthermore, the know-how learning unit provides feedback to the AI ​​to increase the probability of success based on past success stories and failure stories. For example, it can suggest improvements to loan decisions based on success stories. This makes it possible to make loan decisions with a high probability of success.

[0032] The know-how learning unit can also collect customer feedback and learn elements to improve customer satisfaction. For example, the know-how learning unit can collect customer feedback in addition to banker know-how and have the AI ​​learn from it. This allows the AI ​​to learn elements to improve customer satisfaction. The know-how learning unit also creates a database of customer feedback and has the AI ​​learn from it. For example, it can collect customer satisfaction surveys and complaint data and have the AI ​​learn from it. Furthermore, the know-how learning unit makes suggestions to improve customer satisfaction based on customer feedback. For example, it can suggest adjustments to loan terms in accordance with customer requests. This makes it possible to improve customer satisfaction.

[0033] The know-how learning unit can incorporate financial practices from different regions and cultures, enabling loan decisions to be made from a global perspective. For example, the know-how learning unit collects financial practices from different regions and cultures as data and has the AI ​​learn from it. This makes it possible to make loan decisions from a global perspective. The know-how learning unit also creates a database of financial practices and regulations from each region and has the AI ​​learn from them. For example, it can collect lending standards and risk assessment methods for each region and have the AI ​​learn from them. Furthermore, by incorporating financial practices from different cultures, the know-how learning unit can enable the AI ​​to make loan decisions from a variety of perspectives. For example, it can set loan conditions that take cultural backgrounds into account. This makes it possible to make loan decisions from a global perspective.

[0034] The loan decision-making unit can also add corporate social responsibility and environmental impact to the evaluation criteria. For example, when the AI ​​makes a loan decision, the loan decision-making unit adds corporate social responsibility (CSR) to the evaluation criteria. For example, it can collect data on a company's CSR activities and level of social contribution and have the AI ​​learn from it. In addition, to add environmental impact to the evaluation criteria, the loan decision-making unit can collect data on a company's environmental protection activities and eco-friendly initiatives and have the AI ​​learn from them. Furthermore, by adding CSR and environmental impact to the evaluation criteria, the loan decision-making unit can enable the AI ​​to make socially responsible loan decisions. For example, it can offer preferential terms to companies that engage in environmental protection activities. This makes it possible to make socially responsible loan decisions.

[0035] The loan decision-making unit can also be applied to other financial products, such as personal loans and home loans, to meet diverse needs. The loan decision-making unit applies AI-based loan decisions to personal loans and home loans. For example, the AI ​​can make loan decisions based on an individual's credit information and income data. In addition, the loan decision-making unit trains the AI ​​to learn the characteristics and risk assessment methods of each product in order to apply AI-based loan decisions to other financial products. This makes it possible to meet diverse needs. Furthermore, the loan decision-making unit uses AI to make quick and accurate loan decisions, even for personal loans and home loans. For example, it can present loan conditions based on an individual's financial situation and past transaction history. This makes it possible to make loan decisions that meet diverse needs.

[0036] The loan decision-making unit can be shared among different financial institutions to build a new financial model that jointly distributes risk. For example, the loan decision-making unit can share AI-based loan decisions among different financial institutions to build a new financial model that jointly distributes risk. For example, multiple financial institutions can use the same AI system. The loan decision-making unit also promotes data sharing among different financial institutions, and the AI ​​performs integrated analysis of the data from each financial institution. This makes it possible to distribute risk. Furthermore, the loan decision-making unit builds a data-sharing platform among financial institutions to jointly distribute risk, and the AI ​​makes loan decisions based on that data. This makes it possible to distribute risk.

[0037] The loan decision department can reduce the workload of bankers and create an environment where they can focus on more advanced tasks. For example, by introducing AI, the loan decision department can reduce the workload of bankers and create an environment where they can focus on more advanced tasks. For example, by automating loan decisions, bankers can focus on strategic tasks. In addition, to reduce the workload of bankers, the loan decision department uses AI to automate routine loan decision tasks. This allows bankers to focus on customer service and developing new business. Furthermore, by having AI make loan decisions, the loan decision department can allow bankers to devote their time to advanced tasks such as risk management and market analysis. For example, while AI handles routine tasks, bankers can develop new financial products. This creates an environment where bankers can focus on advanced tasks.

[0038] The loan assessment department can make the loan assessment process more transparent and improve the efficiency of internal audits. For example, by introducing AI, the loan assessment department can make the loan assessment process more transparent and improve the efficiency of internal audits. For example, AI can record the assessment process in detail, making it easy to check during audits. Furthermore, to make the loan assessment process more transparent, AI can record the assessment criteria and the results of data analysis in detail. This allows information to be provided quickly during internal audits. Furthermore, by using AI to make the loan assessment process more transparent, the loan assessment department can improve the efficiency of internal audits. For example, AI can automatically generate audit reports, allowing auditors to quickly check them. This can improve the efficiency of internal audits.

[0039] The loan decision-making department can also apply AI to other business processes to improve overall business efficiency. By introducing AI, for example, the loan decision-making department can apply AI to other business processes to improve overall business efficiency. For example, AI can provide automatic responses in customer service. The loan decision-making department can also apply AI to marketing operations, analyzing customer data and conducting targeted marketing. This can maximize marketing effectiveness. Furthermore, the loan decision-making department can use AI to automate customer service and marketing business processes, creating an environment where bankers can focus on more strategic tasks. This can improve overall business efficiency.

[0040] The loan decision-making unit can promote data sharing between different financial institutions, thereby improving efficiency across the industry. For example, by introducing AI, the loan decision-making unit can promote data sharing between different financial institutions, thereby improving efficiency across the industry. For example, a common data platform can be built. Furthermore, to promote data sharing between different financial institutions, AI standardizes and integrates data. This improves data consistency and reliability. Furthermore, the loan decision-making unit can use AI to share data between different financial institutions in real time, thereby improving efficiency across the industry. For example, loan decision data can be shared to diversify risk. This can improve efficiency across the industry.

[0041] The loan decision-making unit can provide individually optimized loan terms by analyzing a customer's past loan history and credit information in detail. For example, when AI makes a loan decision, the loan decision-making unit can provide individually optimized loan terms by analyzing a customer's past loan history and credit information in detail. For example, loan terms can be set based on the customer's credit score and repayment history. The loan decision-making unit also creates a database of the customer's past loan history and credit information and has the AI ​​learn from it. This makes it possible to provide individually optimized loan terms. Furthermore, the loan decision-making unit can provide individually optimized loan terms by using AI to analyze the customer's credit information in detail. For example, the loan terms can be adjusted based on the customer's income and spending patterns. This makes it possible to provide individually optimized loan terms.

[0042] The loan decision-making unit predicts future earnings and assesses risks for the customer, and can make loan proposals from a long-term perspective. For example, when AI makes a loan decision, the loan decision-making unit predicts future earnings and assesses risks for the customer, and makes loan proposals from a long-term perspective. For example, loan conditions can be set based on the customer's business plan and market forecasts. The loan decision-making unit also creates a database of the customer's future earnings forecasts and risk assessments, and has the AI ​​learn from them. This makes it possible to make loan proposals from a long-term perspective. Furthermore, the loan decision-making unit uses AI to predict future earnings and assess risks for the customer, and makes loan proposals from a long-term perspective. For example, the loan conditions can be adjusted based on the customer's business growth forecast. This makes it possible to make loan proposals from a long-term perspective.

[0043] The loan decision-making unit can also be applied to providing personalized financial advice and investment proposals, thereby supporting customer asset management. The loan decision-making unit, for example, applies AI-based loan decisions to providing personalized financial advice and investment proposals. For example, it can make optimal investment proposals based on a customer's financial situation and investment goals. In addition, the loan decision-making unit uses AI to analyze a customer's financial data and market data in order to provide personalized financial advice and investment proposals. This can support customer asset management. Furthermore, the loan decision-making unit uses AI to provide personalized financial advice and investment proposals in real time. For example, it can make proposals to optimize a customer's investment portfolio. This can support customer asset management.

[0044] The loan decision unit can share data between different financial institutions and propose optimal financial products to customers. The loan decision unit, for example, shares loan decisions made using AI between different financial institutions and proposes optimal financial products to customers. For example, it can integrate data from multiple financial institutions and present optimal loan terms. The loan decision unit also promotes data sharing between different financial institutions, and AI analyzes the data from each financial institution. This makes it possible to propose optimal financial products to customers. Furthermore, the loan decision unit uses AI to share data between different financial institutions in real time and propose optimal financial products to customers. For example, it can compare loan terms from multiple financial institutions and present the best options. This makes it possible to propose optimal financial products to customers.

[0045] The loan decision-making unit can learn past fraudulent patterns and develop algorithms that detect fraudulent activities in real time. For example, when the AI ​​makes loan decisions, the loan decision-making unit can learn past fraudulent patterns and develop algorithms that detect fraudulent activities in real time. For example, data can be collected to detect signs of fraudulent activities and have the AI ​​learn from it. The loan decision-making unit can also create a database of past fraudulent activity patterns and have the AI ​​learn from them. This allows the AI ​​to detect fraudulent activities in real time and take countermeasures in advance. Furthermore, the loan decision-making unit allows the AI, which has learned fraudulent activity patterns, to detect fraudulent activities in real time when making loan decisions. For example, it can detect fraudulent transactions and false information and issue warnings. This allows fraudulent activities to be detected in real time.

[0046] The loan decision-making unit can record the decision-making process in detail to increase transparency and facilitate audits by third parties. For example, when AI makes a loan decision, the loan decision-making unit records the decision-making process in detail to increase transparency. For example, the AI's decision-making criteria and the results of data analysis can be recorded in detail and provided at the time of audit. The loan decision-making unit also facilitates audits by third parties by recording the decision-making process in detail. For example, the AI ​​can automatically generate an audit report so that auditors can quickly check it. Furthermore, the loan decision-making unit facilitates audits by third parties by making the loan decision process transparent using AI. For example, detailed records of the decision-making process can be compiled into a database that can be accessed at the time of audit. This facilitates audits by third parties.

[0047] The loan decision-making unit can apply clean loan decisions to other financial products, thereby improving the transparency of the overall financial system. The loan decision-making unit, for example, applies clean loan decisions using AI to other financial products. For example, AI can be introduced into risk assessment of insurance and investment products to improve transparency. Furthermore, in order to apply clean loan decisions using AI to other financial products, the loan decision-making unit trains AI on the characteristics and risk assessment methods of each product. This improves the transparency of the overall financial system. Furthermore, the loan decision-making unit uses AI to perform risk assessment of insurance and investment products, thereby improving transparency. For example, AI can perform risk assessment of insurance contracts and performance assessment of investment products. This improves the transparency of the overall financial system.

[0048] The loan decision-making unit can share clean loan decisions between different financial institutions, thereby eradicating fraudulent activities throughout the industry. The loan decision-making unit can, for example, share clean loan decisions made using AI between different financial institutions, thereby eradicating fraudulent activities throughout the industry. For example, a common data platform can be built to share information on fraudulent activities. The loan decision-making unit also promotes data sharing between different financial institutions, and AI performs integrated analysis of data from each financial institution. This makes it possible to eradicate fraudulent activities. Furthermore, the loan decision-making unit can use AI to share data between different financial institutions in real time, thereby eradicating fraudulent activities throughout the industry. For example, it can detect signs of fraudulent activities and issue warnings. This makes it possible to eradicate fraudulent activities throughout the industry.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The loan decision-making unit can also add a company's social responsibility and environmental impact to its evaluation criteria. For example, it can collect data on a company's CSR activities and level of social contribution and have the AI ​​learn from it. In addition, to add environmental impact to the evaluation criteria, the loan decision-making unit can collect data on a company's environmental protection activities and eco-friendly initiatives and have the AI ​​learn from it. Furthermore, by adding CSR and environmental impact to the evaluation criteria, the loan decision-making unit can enable the AI ​​to make socially responsible loan decisions. For example, it can offer preferential terms to companies that engage in environmental protection activities. This makes it possible to make socially responsible loan decisions.

[0051] The loan decision-making unit can predict future revenues and assess risks for customers and make loan proposals from a long-term perspective. For example, it can set loan terms based on the customer's business plan and market forecasts. The loan decision-making unit also creates a database of customers' future revenue forecasts and risk assessments and has AI learn from them. This makes it possible to make loan proposals from a long-term perspective. Furthermore, the loan decision-making unit uses AI to predict future revenues and assess risks for customers and make loan proposals from a long-term perspective. For example, it can adjust loan terms based on the customer's business growth forecast. This makes it possible to make loan proposals from a long-term perspective.

[0052] The loan decision-making unit can be shared among different financial institutions to build a new financial model that jointly distributes risk. For example, AI loan decisions can be shared among different financial institutions to build a new financial model that jointly distributes risk. For example, multiple financial institutions can use the same AI system. The loan decision-making unit also promotes data sharing among different financial institutions, and the AI ​​performs integrated analysis of the data from each financial institution. This makes it possible to distribute risk. Furthermore, the loan decision-making unit builds a data sharing platform among financial institutions to jointly distribute risk, and the AI ​​makes loan decisions based on that data. This makes it possible to distribute risk.

[0053] The loan decision-making unit can also be applied to other financial products, such as personal loans and home loans, to meet diverse needs. For example, AI loan decisions can be applied to personal loans and home loans. For example, AI can make loan decisions based on an individual's credit information and income data. In addition, the loan decision-making unit trains the AI ​​to learn the characteristics and risk assessment methods of each product in order to apply AI loan decisions to other financial products. This makes it possible to meet diverse needs. Furthermore, the loan decision-making unit uses AI to make quick and accurate loan decisions, even for personal loans and home loans. For example, it can present loan conditions based on an individual's financial situation and past transaction history. This makes it possible to make loan decisions that meet diverse needs.

[0054] The loan decision-making unit can learn past fraudulent patterns and develop algorithms to detect fraudulent activity in real time. For example, when AI makes loan decisions, it can learn past fraudulent patterns and develop algorithms to detect fraudulent activity in real time. For example, data to detect signs of fraud can be collected and the AI ​​can learn from it. The loan decision-making unit can also create a database of past fraudulent activity patterns and have the AI ​​learn from them. This allows the AI ​​to detect fraudulent activity in real time and take countermeasures in advance. Furthermore, the loan decision-making unit uses AI that has learned fraudulent activity patterns to detect fraudulent activity in real time when making loan decisions. For example, it can detect fraudulent transactions and false information and issue warnings. This allows fraudulent activity to be detected in real time.

[0055] The loan decision-making unit can record the decision-making process in detail to increase transparency and facilitate audits by third parties. For example, when AI makes loan decisions, the decision-making process is recorded in detail to increase transparency. For example, the AI's decision-making criteria and the results of data analysis can be recorded in detail and provided during audits. The loan decision-making unit also facilitates audits by third parties by recording the decision-making process in detail. For example, the AI ​​can automatically generate audit reports so that auditors can quickly check them. Furthermore, the loan decision-making unit facilitates audits by third parties by making the loan decision process transparent using AI. For example, detailed records of the decision-making process can be compiled into a database that can be accessed during audits. This facilitates audits by third parties.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The know-how learning unit learns the know-how of excellent bankers. For example, the know-how learning unit collects data on bankers' past loan cases and decision-making criteria, and trains the generation AI to learn from this data. The know-how learning unit can also learn bankers' risk assessment methods and customer service techniques. The generation AI uses a fine-tuned model to make advanced loan decisions based on the bankers' experience and knowledge. Step 2: The loan decision unit makes a loan decision based on the know-how learned by the know-how learning unit. For example, the loan decision unit analyzes data such as the company's financial situation, business plan, and past transaction history to determine whether or not to grant a loan. The loan decision unit can also use a generation AI to make quick and accurate loan decisions. The generation AI makes a loan decision based on the input data and outputs the result.

[0058] (Example 2) The loan decision-making system according to the embodiment of the present invention is a system in which AI learns the know-how of excellent bankers and makes loan decisions. As a result, the loan decision-making system can improve the efficiency of the loan decision-making process in banking operations and achieve fairness.

[0059] A loan decision-making system according to an embodiment includes a know-how learning unit and a loan decision-making unit. The know-how learning unit learns the know-how of excellent bankers. For example, the know-how learning unit collects data on bankers' past loan applications and decision-making criteria, and trains the generation AI on the data. The know-how learning unit can also learn the bankers' risk assessment methods and customer service techniques. For example, the generation AI uses a fine-tuned model to make advanced loan decisions based on the bankers' experience and knowledge. The loan decision-making unit makes loan decisions based on the know-how learned by the know-how learning unit. For example, the loan decision-making unit analyzes data such as a company's financial situation, business plan, and past transaction history to determine whether to grant a loan. The loan decision-making unit can also use the generation AI to make quick and accurate loan decisions. For example, the generation AI makes a loan decision based on input data and outputs the result. As a result, the loan decision-making system according to an embodiment can improve the efficiency and fairness of the loan decision-making process in banking operations. For example, banks can reduce labor costs and prevent errors. Furthermore, customers can receive quick and fair loan decisions.

[0060] The know-how learning unit can learn risk management methods from other industries in addition to banker know-how. For example, the know-how learning unit can learn risk management methods from the insurance and real estate industries in addition to banker know-how. This makes it possible to evaluate not only financial risks but also physical and market risks. In addition, to learn risk management methods from other industries, the know-how learning unit collects insurance contract data and real estate appraisal data and has the AI ​​learn them in an integrated manner. For example, it can learn risk assessment methods from the insurance industry and quality control methods from the manufacturing industry. This improves the accuracy of risk assessment. Furthermore, by incorporating risk management methods from other industries, the know-how learning unit enables the AI ​​to perform multifaceted risk assessments and more comprehensive lending decisions. For example, it can make lending decisions that take insurance risk and market risk into account. This enables multifaceted risk assessments.

[0061] The know-how learning unit can also collect the banker's emotions and intuitive judgments as data and learn using the emotion estimation function. For example, the know-how learning unit collects data on the emotions and intuitive judgments of bankers when making loan decisions and has the AI ​​learn them. For example, it analyzes the banker's facial expressions and voice data and calculates an emotion score. The know-how learning unit also uses the emotion estimation function to have the AI ​​learn the banker's emotional data. This allows the AI ​​to make loan decisions that take emotional factors into account. For example, the emotion estimation function can analyze the banker's emotions using facial recognition technology and voice analysis technology. Furthermore, the know-how learning unit collects the banker's intuitive judgments as data and has the AI ​​learn them. For example, it can create a database of bankers' past intuitive decisions and their results and have the AI ​​learn them. This makes it possible to make loan decisions that take emotional factors into account.

[0062] The know-how learning unit can compare and analyze past success stories and failure stories to develop algorithms that increase the probability of success. For example, the know-how learning unit can create a database of bankers' past success stories and failure stories and have the AI ​​learn from them. This makes it possible to develop algorithms that increase the probability of success. The know-how learning unit can also compare and analyze success stories and failure stories to identify factors that led to success and failure. This allows the AI ​​to make loan decisions with a high probability of success. For example, it can suggest improvements to loan decisions based on success stories. Furthermore, the know-how learning unit provides feedback to the AI ​​to increase the probability of success based on past success stories and failure stories. For example, it can suggest improvements to loan decisions based on success stories. This makes it possible to make loan decisions with a high probability of success.

[0063] The know-how learning unit can also collect customer feedback and learn elements to improve customer satisfaction. For example, the know-how learning unit can collect customer feedback in addition to banker know-how and have the AI ​​learn from it. This allows the AI ​​to learn elements to improve customer satisfaction. The know-how learning unit also creates a database of customer feedback and has the AI ​​learn from it. For example, it can collect customer satisfaction surveys and complaint data and have the AI ​​learn from it. Furthermore, the know-how learning unit makes suggestions to improve customer satisfaction based on customer feedback. For example, it can suggest adjustments to loan terms in accordance with customer requests. This makes it possible to improve customer satisfaction.

[0064] The know-how learning unit can incorporate financial practices from different regions and cultures, enabling loan decisions to be made from a global perspective. For example, the know-how learning unit collects financial practices from different regions and cultures as data and has the AI ​​learn from it. This makes it possible to make loan decisions from a global perspective. The know-how learning unit also creates a database of financial practices and regulations from each region and has the AI ​​learn from them. For example, it can collect lending standards and risk assessment methods for each region and have the AI ​​learn from them. Furthermore, by incorporating financial practices from different cultures, the know-how learning unit can enable the AI ​​to make loan decisions from a variety of perspectives. For example, it can set loan conditions that take cultural backgrounds into account. This makes it possible to make loan decisions from a global perspective.

[0065] The know-how learning unit can use the emotion estimation function to evaluate the emotional impact that an AI's decision based on banker know-how has on a customer and adjust the system to elicit positive emotions. The know-how learning unit, for example, uses the emotion estimation function to evaluate the emotional impact that an AI's loan decision has on a customer. For example, it analyzes the customer's facial expressions and voice and calculates an emotion score. The know-how learning unit also evaluates the emotional impact that an AI's decision has on a customer and makes adjustments to elicit positive emotions. For example, it can improve the way loan terms are presented. Furthermore, the know-how learning unit makes suggestions based on the emotion estimation data to help the AI ​​elicit positive emotions from customers. For example, it can suggest communication methods that correspond to the customer's emotional state. This makes it possible to make loan decisions that elicit positive emotions from customers.

[0066] The loan decision-making unit can also add corporate social responsibility and environmental impact to the evaluation criteria. For example, when the AI ​​makes a loan decision, the loan decision-making unit adds corporate social responsibility (CSR) to the evaluation criteria. For example, it can collect data on a company's CSR activities and level of social contribution and have the AI ​​learn from it. In addition, to add environmental impact to the evaluation criteria, the loan decision-making unit can collect data on a company's environmental protection activities and eco-friendly initiatives and have the AI ​​learn from them. Furthermore, by adding CSR and environmental impact to the evaluation criteria, the loan decision-making unit can enable the AI ​​to make socially responsible loan decisions. For example, it can offer preferential terms to companies that engage in environmental protection activities. This makes it possible to make socially responsible loan decisions.

[0067] The loan decision-making unit can use the emotion estimation function to evaluate the emotional state of the customer and provide feedback to increase the customer's trust. The loan decision-making unit, for example, uses the emotion estimation function to evaluate the customer's emotional state when the AI ​​makes a loan decision. For example, it analyzes the customer's facial expressions and voice and calculates an emotion score. The loan decision-making unit also evaluates the customer's emotional state and provides feedback to increase trust. For example, it can suggest communication methods to elicit positive emotions. Furthermore, the loan decision-making unit provides feedback to the AI ​​to increase trust based on the emotion estimation data. For example, it can improve the method of presenting loan terms according to the customer's emotional state. This makes it possible to make loan decisions that increase customer trust.

[0068] The loan decision-making unit can also be applied to other financial products, such as personal loans and home loans, to meet diverse needs. The loan decision-making unit applies AI-based loan decisions to personal loans and home loans. For example, the AI ​​can make loan decisions based on an individual's credit information and income data. In addition, the loan decision-making unit trains the AI ​​to learn the characteristics and risk assessment methods of each product in order to apply AI-based loan decisions to other financial products. This makes it possible to meet diverse needs. Furthermore, the loan decision-making unit uses AI to make quick and accurate loan decisions, even for personal loans and home loans. For example, it can present loan conditions based on an individual's financial situation and past transaction history. This makes it possible to make loan decisions that meet diverse needs.

[0069] The loan decision-making unit can be shared among different financial institutions to build a new financial model that jointly distributes risk. For example, the loan decision-making unit can share AI-based loan decisions among different financial institutions to build a new financial model that jointly distributes risk. For example, multiple financial institutions can use the same AI system. The loan decision-making unit also promotes data sharing among different financial institutions, and the AI ​​performs integrated analysis of the data from each financial institution. This makes it possible to distribute risk. Furthermore, the loan decision-making unit builds a data-sharing platform among financial institutions to jointly distribute risk, and the AI ​​makes loan decisions based on that data. This makes it possible to distribute risk.

[0070] The loan decision-making unit can use the emotion estimation function to monitor the customer's emotional state in real time and propose the optimal communication method. For example, the loan decision-making unit uses the emotion estimation function to monitor the customer's emotional state in real time when the AI ​​makes a loan decision. For example, it analyzes the customer's facial expressions and voice and calculates an emotion score. The loan decision-making unit also monitors the customer's emotional state in real time and proposes the optimal communication method. For example, it can propose a communication method that elicits positive emotions. Furthermore, the loan decision-making unit uses the emotion estimation data to allow the AI ​​to propose the optimal communication method to the customer. For example, it can improve the way loan terms are presented according to the customer's emotional state. This makes it possible to propose the optimal communication method to the customer.

[0071] The loan decision department can reduce the workload of bankers and create an environment where they can focus on more advanced tasks. For example, by introducing AI, the loan decision department can reduce the workload of bankers and create an environment where they can focus on more advanced tasks. For example, by automating loan decisions, bankers can focus on strategic tasks. In addition, to reduce the workload of bankers, the loan decision department uses AI to automate routine loan decision tasks. This allows bankers to focus on customer service and developing new business. Furthermore, by having AI make loan decisions, the loan decision department can allow bankers to devote their time to advanced tasks such as risk management and market analysis. For example, while AI handles routine tasks, bankers can develop new financial products. This creates an environment where bankers can focus on advanced tasks.

[0072] The loan decision-making unit can use the emotion estimation function to monitor the banker's stress level and improve work efficiency. For example, the loan decision-making unit uses the emotion estimation function to monitor the banker's stress level when the AI ​​makes a loan decision. For example, it analyzes the banker's facial expressions and voice and calculates a stress score. The loan decision-making unit also monitors the banker's stress level and provides feedback to improve work efficiency. For example, it can suggest work adjustments if stress is high. Furthermore, the loan decision-making unit uses the emotion estimation data to enable the AI ​​to monitor the banker's stress level and provide support to improve work efficiency. For example, it can assign work to people with low stress. This can improve the banker's work efficiency.

[0073] The loan assessment department can make the loan assessment process more transparent and improve the efficiency of internal audits. For example, by introducing AI, the loan assessment department can make the loan assessment process more transparent and improve the efficiency of internal audits. For example, AI can record the assessment process in detail, making it easy to check during audits. Furthermore, to make the loan assessment process more transparent, AI can record the assessment criteria and the results of data analysis in detail. This allows information to be provided quickly during internal audits. Furthermore, by using AI to make the loan assessment process more transparent, the loan assessment department can improve the efficiency of internal audits. For example, AI can automatically generate audit reports, allowing auditors to quickly check them. This can improve the efficiency of internal audits.

[0074] The loan decision-making department can also apply AI to other business processes to improve overall business efficiency. By introducing AI, for example, the loan decision-making department can apply AI to other business processes to improve overall business efficiency. For example, AI can provide automatic responses in customer service. The loan decision-making department can also apply AI to marketing operations, analyzing customer data and conducting targeted marketing. This can maximize marketing effectiveness. Furthermore, the loan decision-making department can use AI to automate customer service and marketing business processes, creating an environment where bankers can focus on more strategic tasks. This can improve overall business efficiency.

[0075] The loan decision-making unit can promote data sharing between different financial institutions, thereby improving efficiency across the industry. For example, by introducing AI, the loan decision-making unit can promote data sharing between different financial institutions, thereby improving efficiency across the industry. For example, a common data platform can be built. Furthermore, to promote data sharing between different financial institutions, AI standardizes and integrates data. This improves data consistency and reliability. Furthermore, the loan decision-making unit can use AI to share data between different financial institutions in real time, thereby improving efficiency across the industry. For example, loan decision data can be shared to diversify risk. This can improve efficiency across the industry.

[0076] The loan decision-making unit can use the emotion estimation function to monitor the emotional state of the banker and improve the work environment and provide mental health care. The loan decision-making unit, for example, uses the emotion estimation function to monitor the emotional state of the banker and improve the work environment and provide mental health care. For example, it analyzes the banker's facial expressions and voice and calculates an emotion score. The loan decision-making unit also monitors the banker's emotional state and provides feedback for improving the work environment and providing mental health care. For example, if stress is high, it can suggest work adjustments. Furthermore, the loan decision-making unit monitors the banker's emotional state based on the emotion estimation data and improves the work environment and provides mental health care. For example, if the emotion score is low, it can suggest a break to refresh. This makes it possible to improve the banker's work environment and provide mental health care.

[0077] The loan decision-making unit can provide individually optimized loan terms by analyzing a customer's past loan history and credit information in detail. For example, when AI makes a loan decision, the loan decision-making unit can provide individually optimized loan terms by analyzing a customer's past loan history and credit information in detail. For example, loan terms can be set based on the customer's credit score and repayment history. The loan decision-making unit also creates a database of the customer's past loan history and credit information and has the AI ​​learn from it. This makes it possible to provide individually optimized loan terms. Furthermore, the loan decision-making unit can provide individually optimized loan terms by using AI to analyze the customer's credit information in detail. For example, the loan terms can be adjusted based on the customer's income and spending patterns. This makes it possible to provide individually optimized loan terms.

[0078] The loan decision-making unit predicts future earnings and assesses risks for the customer, and can make loan proposals from a long-term perspective. For example, when AI makes a loan decision, the loan decision-making unit predicts future earnings and assesses risks for the customer, and makes loan proposals from a long-term perspective. For example, loan conditions can be set based on the customer's business plan and market forecasts. The loan decision-making unit also creates a database of the customer's future earnings forecasts and risk assessments, and has the AI ​​learn from them. This makes it possible to make loan proposals from a long-term perspective. Furthermore, the loan decision-making unit uses AI to predict future earnings and assess risks for the customer, and makes loan proposals from a long-term perspective. For example, the loan conditions can be adjusted based on the customer's business growth forecast. This makes it possible to make loan proposals from a long-term perspective.

[0079] The loan decision-making unit can also be applied to providing personalized financial advice and investment proposals, thereby supporting customer asset management. The loan decision-making unit, for example, applies AI-based loan decisions to providing personalized financial advice and investment proposals. For example, it can make optimal investment proposals based on a customer's financial situation and investment goals. In addition, the loan decision-making unit uses AI to analyze a customer's financial data and market data in order to provide personalized financial advice and investment proposals. This can support customer asset management. Furthermore, the loan decision-making unit uses AI to provide personalized financial advice and investment proposals in real time. For example, it can make proposals to optimize a customer's investment portfolio. This can support customer asset management.

[0080] The loan decision unit can share data between different financial institutions and propose optimal financial products to customers. The loan decision unit, for example, shares loan decisions made using AI between different financial institutions and proposes optimal financial products to customers. For example, it can integrate data from multiple financial institutions and present optimal loan terms. The loan decision unit also promotes data sharing between different financial institutions, and AI analyzes the data from each financial institution. This makes it possible to propose optimal financial products to customers. Furthermore, the loan decision unit uses AI to share data between different financial institutions in real time and propose optimal financial products to customers. For example, it can compare loan terms from multiple financial institutions and present the best options. This makes it possible to propose optimal financial products to customers.

[0081] The loan decision-making unit can use the emotion estimation function to monitor the customer's emotional state in real time and propose the optimal communication method. The loan decision-making unit, for example, uses the emotion estimation function to monitor the customer's emotional state in real time. For example, it analyzes the customer's facial expressions and voice and calculates an emotion score. The loan decision-making unit also monitors the customer's emotional state in real time and proposes the optimal communication method. For example, it can propose a communication method that elicits positive emotions. Furthermore, the loan decision-making unit uses AI to propose the optimal communication method to the customer based on the emotion estimation data. For example, it can improve the way loan terms are presented according to the customer's emotional state. This makes it possible to propose the optimal communication method to the customer.

[0082] The loan decision-making unit can learn past fraudulent patterns and develop algorithms that detect fraudulent activities in real time. For example, when the AI ​​makes loan decisions, the loan decision-making unit can learn past fraudulent patterns and develop algorithms that detect fraudulent activities in real time. For example, data can be collected to detect signs of fraudulent activities and have the AI ​​learn from it. The loan decision-making unit can also create a database of past fraudulent activity patterns and have the AI ​​learn from them. This allows the AI ​​to detect fraudulent activities in real time and take countermeasures in advance. Furthermore, the loan decision-making unit allows the AI, which has learned fraudulent activity patterns, to detect fraudulent activities in real time when making loan decisions. For example, it can detect fraudulent transactions and false information and issue warnings. This allows fraudulent activities to be detected in real time.

[0083] The loan decision-making unit can use the emotion estimation function to detect signs of fraudulent activity and take countermeasures in advance. The loan decision-making unit, for example, uses the emotion estimation function to detect signs of fraudulent activity when the AI ​​makes a loan decision. For example, it analyzes a customer's facial expressions and voice to detect signs of fraudulent activity. The loan decision-making unit also trains the AI ​​with emotion estimation data to detect signs of fraudulent activity. This allows the AI ​​to detect signs of fraudulent activity in real time and take countermeasures in advance. Furthermore, the loan decision-making unit can use the emotion estimation function to detect signs of fraudulent activity and take countermeasures in advance. For example, it can assess the risk of fraudulent activity based on the customer's emotional state and issue a warning. This allows signs of fraudulent activity to be detected and countermeasures to be taken in advance.

[0084] The loan decision-making unit can record the decision-making process in detail to increase transparency and facilitate audits by third parties. For example, when AI makes a loan decision, the loan decision-making unit records the decision-making process in detail to increase transparency. For example, the AI's decision-making criteria and the results of data analysis can be recorded in detail and provided at the time of audit. The loan decision-making unit also facilitates audits by third parties by recording the decision-making process in detail. For example, the AI ​​can automatically generate an audit report so that auditors can quickly check it. Furthermore, the loan decision-making unit facilitates audits by third parties by making the loan decision process transparent using AI. For example, detailed records of the decision-making process can be compiled into a database that can be accessed at the time of audit. This facilitates audits by third parties.

[0085] The loan decision-making unit can apply clean loan decisions to other financial products, thereby improving the transparency of the overall financial system. The loan decision-making unit, for example, applies clean loan decisions using AI to other financial products. For example, AI can be introduced into risk assessment of insurance and investment products to improve transparency. Furthermore, in order to apply clean loan decisions using AI to other financial products, the loan decision-making unit trains AI on the characteristics and risk assessment methods of each product. This improves the transparency of the overall financial system. Furthermore, the loan decision-making unit uses AI to perform risk assessment of insurance and investment products, thereby improving transparency. For example, AI can perform risk assessment of insurance contracts and performance assessment of investment products. This improves the transparency of the overall financial system.

[0086] The loan decision-making unit can share clean loan decisions between different financial institutions, thereby eradicating fraudulent activities throughout the industry. The loan decision-making unit can, for example, share clean loan decisions made using AI between different financial institutions, thereby eradicating fraudulent activities throughout the industry. For example, a common data platform can be built to share information on fraudulent activities. The loan decision-making unit also promotes data sharing between different financial institutions, and AI performs integrated analysis of data from each financial institution. This makes it possible to eradicate fraudulent activities. Furthermore, the loan decision-making unit can use AI to share data between different financial institutions in real time, thereby eradicating fraudulent activities throughout the industry. For example, it can detect signs of fraudulent activities and issue warnings. This makes it possible to eradicate fraudulent activities throughout the industry.

[0087] The loan decision-making unit can use the emotion estimation function to monitor the emotional state of the customer in the loan decision-making process and provide feedback to enhance transparency and reliability. The loan decision-making unit, for example, uses the emotion estimation function to monitor the emotional state of the customer in the loan decision-making process. For example, it analyzes the customer's facial expressions and voice and calculates an emotion score. The loan decision-making unit also monitors the customer's emotional state and provides feedback to enhance transparency and reliability. For example, it can suggest communication methods to elicit positive emotions. Furthermore, the loan decision-making unit uses the emotion estimation data to provide feedback to the customer to enhance transparency and reliability. For example, it can improve the method of presenting loan terms according to the customer's emotional state. This makes it possible to provide feedback to enhance transparency and reliability.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The loan decision-making unit can also add a company's social responsibility and environmental impact to its evaluation criteria. For example, it can collect data on a company's CSR activities and level of social contribution and have the AI ​​learn from it. In addition, to add environmental impact to the evaluation criteria, the loan decision-making unit can collect data on a company's environmental protection activities and eco-friendly initiatives and have the AI ​​learn from it. Furthermore, by adding CSR and environmental impact to the evaluation criteria, the loan decision-making unit can enable the AI ​​to make socially responsible loan decisions. For example, it can offer preferential terms to companies that engage in environmental protection activities. This makes it possible to make socially responsible loan decisions.

[0090] The loan decision-making unit can predict future revenues and assess risks for customers and make loan proposals from a long-term perspective. For example, it can set loan terms based on the customer's business plan and market forecasts. The loan decision-making unit also creates a database of customers' future revenue forecasts and risk assessments and has AI learn from them. This makes it possible to make loan proposals from a long-term perspective. Furthermore, the loan decision-making unit uses AI to predict future revenues and assess risks for customers and make loan proposals from a long-term perspective. For example, it can adjust loan terms based on the customer's business growth forecast. This makes it possible to make loan proposals from a long-term perspective.

[0091] The loan decision-making unit can use the emotion estimation function to evaluate the emotional state of the customer and provide feedback to increase the customer's trustworthiness. For example, it can analyze the customer's facial expressions and voice and calculate an emotion score. The loan decision-making unit can also evaluate the customer's emotional state and provide feedback to increase the customer's trustworthiness. For example, it can suggest communication methods to elicit positive emotions. Furthermore, the loan decision-making unit can provide feedback to the customer based on the emotion estimation data to increase the customer's trustworthiness. For example, it can improve the method of presenting loan terms according to the customer's emotional state. This makes it possible to make loan decisions that increase the customer's trustworthiness.

[0092] The loan decision-making unit can be shared among different financial institutions to build a new financial model that jointly distributes risk. For example, AI loan decisions can be shared among different financial institutions to build a new financial model that jointly distributes risk. For example, multiple financial institutions can use the same AI system. The loan decision-making unit also promotes data sharing among different financial institutions, and the AI ​​performs integrated analysis of the data from each financial institution. This makes it possible to distribute risk. Furthermore, the loan decision-making unit builds a data sharing platform among financial institutions to jointly distribute risk, and the AI ​​makes loan decisions based on that data. This makes it possible to distribute risk.

[0093] The loan decision-making unit can use the emotion estimation function to monitor the banker's stress level and improve work efficiency. For example, using the emotion estimation function, the AI ​​monitors the banker's stress level when making loan decisions. For example, it analyzes the banker's facial expressions and voice and calculates a stress score. The loan decision-making unit also monitors the banker's stress level and provides feedback to improve work efficiency. For example, it can suggest work adjustments if stress is high. Furthermore, the loan decision-making unit uses the emotion estimation data to enable the AI ​​to monitor the banker's stress level and provide support to improve work efficiency. For example, it can assign work to people with low stress. This can improve the banker's work efficiency.

[0094] The loan decision-making unit can also be applied to other financial products, such as personal loans and home loans, to meet diverse needs. For example, AI loan decisions can be applied to personal loans and home loans. For example, AI can make loan decisions based on an individual's credit information and income data. In addition, the loan decision-making unit trains the AI ​​to learn the characteristics and risk assessment methods of each product in order to apply AI loan decisions to other financial products. This makes it possible to meet diverse needs. Furthermore, the loan decision-making unit uses AI to make quick and accurate loan decisions, even for personal loans and home loans. For example, it can present loan conditions based on an individual's financial situation and past transaction history. This makes it possible to make loan decisions that meet diverse needs.

[0095] The loan decision-making unit can use the emotion estimation function to monitor the emotional state of the banker and improve the work environment and provide mental health care. For example, the emotion estimation function can be used to monitor the emotional state of the banker and improve the work environment and provide mental health care. For example, the emotion estimation function can analyze the banker's facial expressions and voice and calculate an emotion score. The loan decision-making unit can also monitor the banker's emotional state and provide feedback for improving the work environment and providing mental health care. For example, if stress is high, it can suggest work adjustments. Furthermore, the loan decision-making unit can monitor the banker's emotional state based on the emotion estimation data and improve the work environment and provide mental health care. For example, if the emotion score is low, it can suggest taking a break to refresh. This makes it possible to improve the banker's work environment and provide mental health care.

[0096] The loan decision-making unit can learn past fraudulent patterns and develop algorithms to detect fraudulent activity in real time. For example, when AI makes loan decisions, it can learn past fraudulent patterns and develop algorithms to detect fraudulent activity in real time. For example, data to detect signs of fraud can be collected and the AI ​​can learn from it. The loan decision-making unit can also create a database of past fraudulent activity patterns and have the AI ​​learn from them. This allows the AI ​​to detect fraudulent activity in real time and take countermeasures in advance. Furthermore, the loan decision-making unit uses AI that has learned fraudulent activity patterns to detect fraudulent activity in real time when making loan decisions. For example, it can detect fraudulent transactions and false information and issue warnings. This allows fraudulent activity to be detected in real time.

[0097] The loan decision-making unit can use the emotion estimation function to detect signs of fraudulent activity and take countermeasures in advance. For example, the emotion estimation function is used to detect signs of fraudulent activity when the AI ​​makes a loan decision. For example, the emotion estimation function can analyze a customer's facial expressions and voice to detect signs of fraudulent activity. The loan decision-making unit also trains the AI ​​with emotion estimation data to detect signs of fraudulent activity. This allows the AI ​​to detect signs of fraudulent activity in real time and take countermeasures in advance. Furthermore, the loan decision-making unit can use the emotion estimation function to detect signs of fraudulent activity and take countermeasures in advance. For example, the AI ​​can assess the risk of fraudulent activity based on the customer's emotional state and issue a warning. This allows signs of fraudulent activity to be detected and countermeasures to be taken in advance.

[0098] The loan decision-making unit can record the decision-making process in detail to increase transparency and facilitate audits by third parties. For example, when AI makes loan decisions, the decision-making process is recorded in detail to increase transparency. For example, the AI's decision-making criteria and the results of data analysis can be recorded in detail and provided during audits. The loan decision-making unit also facilitates audits by third parties by recording the decision-making process in detail. For example, the AI ​​can automatically generate audit reports so that auditors can quickly check them. Furthermore, the loan decision-making unit facilitates audits by third parties by making the loan decision process transparent using AI. For example, detailed records of the decision-making process can be compiled into a database that can be accessed during audits. This facilitates audits by third parties.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The know-how learning unit learns the know-how of excellent bankers. For example, the know-how learning unit collects data on bankers' past loan cases and decision-making criteria, and trains the generation AI to learn from this data. The know-how learning unit can also learn bankers' risk assessment methods and customer service techniques. The generation AI uses a fine-tuned model to make advanced loan decisions based on the bankers' experience and knowledge. Step 2: The loan decision unit makes a loan decision based on the know-how learned by the know-how learning unit. For example, the loan decision unit analyzes data such as the company's financial situation, business plan, and past transaction history to determine whether or not to grant a loan. The loan decision unit can also use a generation AI to make quick and accurate loan decisions. The generation AI makes a loan decision based on the input data and outputs the result.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0107] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0108] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0109] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0110] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0111] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0112] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0113] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0114] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0115] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0122] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0123] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0125] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0126] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0129] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0130] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0136] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0141] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0142] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0151] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0152] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0153] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0154] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0155] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0156] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0157] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0158] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0159] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0160] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0161] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0162] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0163] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0164] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0165] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0166] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0167] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0168] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A know-how learning department that learns the know-how of excellent bankers, a loan decision unit that makes a loan decision based on the know-how learned by the know-how learning unit; A system characterized by:

2. The know-how learning unit In addition to banker know-how, learn risk management methods from other industries 2. The system of claim 1.

3. The know-how learning unit Collect and learn from the banker's emotions and intuitive judgments as data 2. The system of claim 1.

4. The know-how learning unit Comparing and analyzing past successes and failures to develop algorithms that increase the probability of success 2. The system of claim 1.

5. The know-how learning unit Collect customer feedback and learn what can improve customer satisfaction 2. The system of claim 1.

6. The know-how learning unit Incorporating financial practices from different regions and cultures to enable lending decisions from a global perspective 2. The system of claim 1.

Images