system

Abstract

We provide the system. [Solution] Means for collecting transaction information of financial institution customers, Means for integrating and preprocessing collected transaction information, A method for extracting features from transaction information, A means of applying a generative algorithm that performs credit evaluation based on extracted features, A means of delivering credit evaluation results to the customer's information terminal, A means of implementing a feedback loop to improve the model based on credit evaluation results, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional credit scoring systems mainly rely on past credit histories to evaluate credit risks, making it difficult to accurately evaluate the credit risks of young people and new customers with insufficient credit histories. As a result, there is a problem that their access to financial services may be restricted. Also, the current credit scoring model has a problem in that it is difficult to perform real-time credit evaluation because information updates cannot keep up.

Means for Solving the Problems

[0005] The present invention provides a system that can perform credit risk assessment in real time by means of a system equipped with means for collecting transaction information of financial institution customers and further having means for integrating and preprocessing the transaction information. Specifically, data is integrated and preprocessed from various information sources including purchase history, location information, and life event information, and credit evaluation is performed based on feature quantities extracted by applying a generation algorithm. By using a feedback loop that distributes the result to the customer's information terminal and improves the model based on the evaluation result, the evaluation accuracy is improved. With this system, it is possible to realize a more accurate and comprehensive credit evaluation and widen the scope of access to financial services.

[0006] "Financial institution customer" refers to an individual or a corporation that conducts transactions with financial institutions such as banks and credit unions.

[0007] "Transaction information" refers to all data related to transactions conducted by financial institution customers, and specifically includes deposit and withdrawal history, credit card usage history, loan repayment history, etc.

[0008] "Integrate and preprocess" refers to the process of organizing data collected from different formats and information sources and converting it into an analyzable form.

[0009] "Feature quantity" refers to data points or indicators used to analyze the credit risk of customers in a credit scoring algorithm.

[0010] "Generation algorithm" refers to a calculation method for evaluating credit risk using machine learning technology, and particularly includes the process of learning a model based on new data and performing credit evaluation.

[0011] "Credit evaluation result" refers to data indicating the credit score of a customer and evaluation indicators of credit risk calculated by an algorithm.

[0012] An "information terminal" is a device used by a user to check information, specifically referring to smartphones, tablets, computers, etc.

[0013] A "feedback loop" refers to a process of continuously improving a model based on credit evaluation results, including a mechanism for improving the accuracy of the model by comparing the evaluation results with actual customer behavior.

Brief Explanation of Drawings

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), etc.

[0018] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention provides a system for more accurate and efficient credit assessment of customers of various financial institutions. This system is implemented in the following form.

[0036] First, the server collects customer transaction information provided by financial institutions. This transaction information includes detailed data about the customer's economic activities, such as deposit and withdrawal history, purchase history, and account transfer details. The server also obtains location information, purchasing trends, and life event data from other sources.

[0037] Next, this data is integrated and preprocessed to transform it into a format suitable for analysis. Data preprocessing includes supplementing incomplete data, identifying and handling outliers, and standardizing data formats. At this stage, the server extracts features from each customer to create a foundation for assessing credit risk.

[0038] The server then applies a generation algorithm to perform a real-time credit assessment for each customer. The algorithm utilizes machine learning techniques to calculate individual credit scores based on transaction patterns and purchasing behavior. For example, customers with a stable income are given high credit scores, while customers who frequently delay credit card payments are given low scores.

[0039] The credit assessment results are sent to the device and can be reviewed by the user as needed. The results may include not only the credit score but also advice on how to improve the score and a breakdown of how specific financial actions have affected the assessment.

[0040] Furthermore, the system incorporates a feedback loop to continuously improve the model. Specifically, it incorporates actual customer behavior and repayment history into the evaluation to improve the accuracy of the algorithm. Through this process, the system evolves over time, enabling it to provide more accurate credit ratings to a wider range of customers.

[0041] Thus, the present invention makes it possible to provide financial institutions with the latest credit assessments of their customers in real time by utilizing transaction information and location information.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server retrieves customer transaction information from financial institutions and partners. This includes deposit and withdrawal history, credit card usage, loan repayment history, and purchase history, and the information is securely collected using Secure File Transfer Protocol (SFTP) and Application Programming Interface (API).

[0045] Step 2:

[0046] The server integrates the collected transaction information and converts information from different data sources into a consistent format. Furthermore, it cleans the data by processing noise and missing values. This results in a clean, analyzable dataset.

[0047] Step 3:

[0048] The server extracts specific features from the pre-processed data. For example, it calculates features that encompass the average monthly credit card spending, purchase frequency, income stability, and the number of payment delays. This information is then used in the subsequent scoring model.

[0049] Step 4:

[0050] The server applies a generative algorithm based on the features to calculate the customer's credit score. This algorithm uses machine learning techniques such as neural networks and decision tree models to simultaneously analyze many features and assess credit risk.

[0051] Step 5:

[0052] The server sends the calculated credit score to the user's device, which the user can then view directly. The data is displayed in a user-friendly interface, providing detailed feedback on the credit rating and areas for improvement.

[0053] Step 6:

[0054] The server collects feedback on actual customer credit performance, incorporates it into the algorithm, and continuously improves the model. This lays the foundation for improving the accuracy of future credit scoring.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] Financial institutions are required to effectively collect and process diverse data in order to properly assess the creditworthiness of their customers. However, conventional methods are insufficient in terms of credit risk assessment due to data incompleteness and inaccuracies in analysis. Therefore, the development of new systems that enable more accurate and efficient credit assessment is necessary.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for collecting activity information of users of financial institutions, means for integrating and pre-processing the collected activity information, and means for extracting indicators from the activity information. This makes it possible to perform more accurate credit risk assessments in real time.

[0060] A "financial institution" refers to an organization that provides services such as money management, lending, and remittance to its users.

[0061] "User" refers to an individual or group that utilizes the services of a financial institution and engages in transactions or purchasing activities.

[0062] "Activity information" refers to records of transactions conducted by users through financial institutions, purchasing behavior, location data, and information related to lifestyle events.

[0063] A "server" refers to a computing device that collects, processes, and analyzes data, and exchanges information with users and other systems.

[0064] "Integration" refers to the process of combining data collected from multiple sources into a single, unified format.

[0065] "Preprocessing" refers to processes that prepare data for analysis, such as imputing missing values, removing outliers, and standardizing the format.

[0066] An "indicator" refers to a numerical representation of characteristics or features extracted from data to assess a user's credit risk.

[0067] An "estimation algorithm" refers to a set of methods and procedures for evaluating indicators using data analysis techniques and calculating credit scores.

[0068] "Information device" refers to a device or terminal used by users to receive and confirm credit evaluation results.

[0069] A "return loop" refers to a system improvement process in which the model is readjusted based on evaluation results to improve the accuracy of subsequent processing.

[0070] This invention provides a system for efficiently and accurately evaluating the creditworthiness of financial institution users. The server first collects user activity information from financial institutions and external data sources. This activity information includes deposit and withdrawal history, purchasing behavior, location data, and information on lifestyle events. This data is integrated and pre-processed, during which incomplete data is supplemented and outliers are removed. From the information, which is then formatted into a standardized format, the server extracts indicators and executes an estimation algorithm based on these indicators.

[0071] Specifically, the server uses machine learning techniques and leverages generative AI models such as Random Forest and XGBoost to calculate a credit score for each user in real time. This allows for a quantitative evaluation of the user's trustworthiness. For example, users with a stable income and no delays in credit card payments are assigned a high score.

[0072] The credit assessment results are delivered to the terminal, and users can check the assessment results through their information devices. The assessment results include the user's credit score as well as specific advice on how to improve it. For example, it might be presented as, "Your score will increase if you improve your recent credit card payments."

[0073] Furthermore, the server has a feedback loop that compares evaluation results with actual actions to improve the accuracy of the estimation algorithm. This continuous improvement further enhances the reliability of the credit rating.

[0074] An example of a prompt message is, "Calculate this user's credit score and assess the likelihood of loan approval," which utilizes a generative AI model. This prompt allows the system to perform the necessary data processing and provide a specific credit assessment.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server collects user activity information from financial institutions and external sources. The input data includes deposit and withdrawal history, purchasing behavior, location data, and lifestyle event information. This data is stored in a local database. The output is a raw dataset linked to each user.

[0078] Step 2:

[0079] The server preprocesses the collected raw dataset. It uses medians and means to fill in any incomplete parts of the input data. It also identifies, removes, or corrects outliers. It standardizes the data format and converts it into a format suitable for analysis. The output is a standardized dataset.

[0080] Step 3:

[0081] The server extracts metrics from pre-processed data. Based on the input data, it quantifies specific metrics such as the stability of the user's income and their spending trends. At this stage, a feature selection algorithm is used to extract important metrics. The output is a list of metrics for each user.

[0082] Step 4:

[0083] The server performs credit assessments using a generative AI model. The input is a list of metrics for each user. Machine learning algorithms (e.g., Random Forest or XGBoost) are used to calculate a credit score based on these metrics. The output is an individual credit score for each user.

[0084] Step 5:

[0085] The server delivers the calculated credit score to the terminal. The terminal displays the received credit score to the user. The input is the credit score and its breakdown, and the output is an evaluation interface that the user can review. The user can receive detailed information about their credit score and suggestions for improvement.

[0086] Step 6:

[0087] The server executes a feedback loop, improving the model's accuracy using actual user repayment history and behavioral data. The input consists of historical data and the latest evaluation results. Based on this, the model is retrained and parameters are adjusted. The output is the improved machine learning model.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In electronic payment services, it is difficult to assess a user's credit risk in real time and individually propose the optimal payment method or credit option. Furthermore, conventional credit rating systems cannot effectively combine large amounts of individual purchase history and location data, making them unable to provide specific and useful advice to users. Therefore, it is necessary to conduct credit assessments tailored to users' economic activities and optimize their daily spending.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes means for collecting transaction data of financial institution users, means for integrating and pre-processing the collected transaction data, and means for extracting characteristics from the transaction data. This makes it possible to perform credit assessments in real time based on the user's purchase history and location information, and to propose the optimal electronic payment method or credit option.

[0093] "Financial institution user" refers to an individual or legal entity that generates transaction data, and that data is generated through a financial institution.

[0094] "Transaction data" is a general term for information related to economic activities, such as deposit and withdrawal history through financial institutions, purchase history, and account transfer details.

[0095] "Means of collection" refers to the processes and functions for collecting and storing data, and this includes various sensors and database technologies.

[0096] "Means of integration and preprocessing" refers to the process of centralizing collected data and converting it into a format suitable for analysis. This includes supplementing incomplete data and removing outliers.

[0097] "Means of extracting characteristics" refers to the process of identifying characteristic elements from data and extracting them in a format usable for analysis.

[0098] A "generative algorithm for credit evaluation" is a computational method or procedure for quantitatively evaluating a user's creditworthiness based on characteristics calculated from transaction data.

[0099] "Means of distribution to information devices" refers to communication processes and functions for providing the generated credit evaluation results in a format accessible to users.

[0100] "Feedback cycle" refers to the process of continuously using data to improve algorithms and enhance the accuracy of evaluations.

[0101] The system for implementing this invention consists of three elements: a server, a terminal, and a user.

[0102] The server first collects transaction data from financial institution users. This transaction data includes users' purchase history and location data. The server integrates and preprocesses this data. Preprocessing includes imputing incomplete data and removing outliers. Next, the server extracts characteristics from the transaction data and applies a generation algorithm to perform credit assessment based on those characteristics. Credit assessment is performed using machine learning techniques to evaluate credit risk in real time.

[0103] The evaluation results are delivered to the user's information device, a terminal, allowing the user to check their credit score. The terminal displays advice and credit suggestions for improving the score through a user interface. Furthermore, through a feedback cycle, the user's actual behavioral data is sent back to the server and used to improve the accuracy of the algorithm.

[0104] As a concrete example, when a user reviews their purchase history, the server displays the user's latest credit score and offers low-interest loans based on that score. These offers also include advice on what purchasing behaviors can contribute to improving the score.

[0105] The generative AI model performs credit assessment using prompts like the following:

[0106] "To perform a credit assessment, please use the following data: Purchase history: [Date, Item, Price], Location information: [Latitude, Longitude], Past credit score: [Date, Score]. Generate advice for the user to improve their future credit score."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects user transaction data from financial institutions and related data sources. This data includes purchase history and location information. The input is raw data, and the output is a well-organized dataset. The server efficiently retrieves data using API calls and stores it in a database.

[0110] Step 2:

[0111] The server integrates and preprocesses the collected data. The input is raw data stored in the database, and the output is clean, preprocessed data. Specifically, it supplements incomplete data, identifies and removes outliers, and standardizes the data format.

[0112] Step 3:

[0113] The server extracts characteristics from pre-processed data. The input is a clean dataset, and the output is a list of extracted characteristics. A machine learning model identifies important characteristics as features, preparing for the next step.

[0114] Step 4:

[0115] The server applies a generative algorithm to perform a credit assessment based on the extracted characteristics. The input is a list of characteristics, and the output is a credit score. Machine learning techniques are used to assess the user's credit risk. The model generates results in real time.

[0116] Step 5:

[0117] The server delivers the generated credit score to the user's device. The input is the generated credit score, and the output is the score displayed on the device. Users can check their own credit information on their device and receive feedback.

[0118] Step 6:

[0119] User behavior data is sent back to the server over time, forming a feedback loop. The input is the user's actual purchasing behavior and payment history, and the output is an improved generation algorithm. This improves the accuracy of credit assessment and ensures that the user's credit score is properly reflected.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention provides a credit rating system that takes into account the user's emotional state. This system integrates not only transaction information from financial institutions but also user emotional data to achieve a more accurate and personalized credit rating.

[0122] First, the server collects customer transaction information from financial institutions. This transaction information includes account deposit and withdrawal history, card usage records, and purchase history. Simultaneously, the server also collects additional data related to the user's emotional state, such as voice data, behavioral data, and location information.

[0123] Next, this data is integrated and preprocessed. The server analyzes the collected data and uses an emotion engine to determine the user's emotional state. For example, it extracts emotions such as stress and a sense of security from voice data to evaluate the user's everyday psychological state.

[0124] The server then applies a generation algorithm based on a comprehensive set of features, including emotional state, to calculate the user's credit score. This algorithm considers the relationship between the user's economic behavior and emotional state to determine credit risk. For example, a user who is consistently experiencing high stress levels may be considered high-risk because a decrease in their willingness to pay is predicted.

[0125] The calculated credit rating results are delivered to the device for the user to review. The device provides the user with details of their credit score, its breakdown, and how emotional data influenced the rating. For example, it can explain how a large expenditure during a period of high stress affected the credit score.

[0126] Furthermore, the server establishes a feedback loop to continuously improve the accuracy of the algorithm. It monitors the user's actual behavior and emotional changes, and revises the evaluation criteria based on this information. In this way, the system evolves in response to changing times, enabling more accurate user credit assessments.

[0127] This invention incorporates emotion recognition technology into credit evaluation, thereby providing a multifaceted credit scoring system that surpasses conventional evaluations based on financial information, and improving the quality of financial services.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server securely collects transaction information provided by financial institutions. This data includes transaction history, credit card statements, and loan repayment information, and is retrieved using APIs and secure data transfer protocols.

[0131] Step 2:

[0132] Users record voice and behavioral data on their devices through an emotion recognition application to collect their own emotional data. This includes the tone of voice during conversations and the frequency of specific activities.

[0133] Step 3:

[0134] The server integrates the collected transaction information and sentiment data and preprocesses it into a consistent data format. It then cleans the data, imputing missing information and removing outliers.

[0135] Step 4:

[0136] The server uses an emotion engine to analyze the user's emotional state. It identifies emotions such as stress levels and joy from voice tone and tags the emotional state.

[0137] Step 5:

[0138] The server extracts features based on pre-processed data and sentiment tags. Specifically, features include monthly spending, credit card usage frequency, and the frequency of sentiment tags.

[0139] Step 6:

[0140] The server applies machine learning algorithms to calculate the user's credit score in real time. The algorithms analyze both financial information and sentiment data to assess credit risk.

[0141] Step 7:

[0142] The device displays the evaluation results, including the calculated credit score, in a user interface. Users can check their own score, the impact of their emotional state on their credit rating, and suggestions for improvement.

[0143] Step 8:

[0144] The server tracks users' financial behavior and emotional changes, and runs a feedback loop to improve the model's accuracy. This ensures continuous improvement in evaluation accuracy.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] Traditional credit rating systems primarily rely on economic activity information from financial institutions and do not take into account the emotional state of users, making it impossible to comprehensively assess credit risk. Furthermore, they are unable to perform personalized assessments that utilize the relationship between emotional state and economic behavior, resulting in insufficient accuracy in assessing user creditworthiness.

[0148] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0149] In this invention, the server includes means for collecting economic activity information of financial institution users, means for collecting additional information related to emotional state from users, and means for analyzing emotional state using an emotion engine. This enables a multifaceted and personalized credit assessment that takes emotional state into account.

[0150] A "financial institution" is an organization that provides financial products and services to users, and includes banks, credit unions, securities companies, and others.

[0151] "Users" refers to individuals or corporations that utilize the services of a financial institution.

[0152] "Economic activity information" refers to data such as transaction history, records of expenses and income, and purchasing behavior related to the user's asset management.

[0153] "Emotional state" refers to data that indicates the user's psychological state and mental condition, and is obtained from voice analysis and behavioral patterns.

[0154] "Additional information" refers to non-financial information such as audio data, behavioral data, and location information related to understanding emotional states.

[0155] An "emotion engine" refers to software or technology that analyzes emotions from a user's voice and behavioral patterns and evaluates their psychological impact on economic behavior.

[0156] "Credit rating" refers to the results of an analysis used to determine a user's financial soundness and ability to pay, and is calculated based on integrated data of economic activity and emotional state.

[0157] A "feedback loop" refers to a series of processes that adjust data and algorithms based on evaluation results to improve the accuracy of the generation method.

[0158] The following system is constructed as an embodiment of this invention. The system consists of three main components: a server, a terminal, and a user.

[0159] The server is primarily designed to retrieve users' financial activity information from financial institutions. This information includes account deposit and withdrawal history, credit card usage records, and purchase history. The server also collects additional information related to the user's emotional state. This additional information includes voice data, behavioral data, and location information, obtained from smartphones and wearable devices.

[0160] The server uses an emotion engine to analyze emotional states. This emotion engine incorporates speech analysis and natural language processing technologies to determine emotions such as stress and feelings of security from voice data. This makes it possible to analyze the psychological impact on users' economic behavior.

[0161] The analyzed data is input into a generative AI model to calculate the user's credit score. This model takes into account both economic activity and emotional state to provide a multifaceted and personalized credit assessment. The credit score aims for real-time optimization, and the generative AI model can provide a highly accurate assessment.

[0162] The calculated credit rating results are delivered to the user via the device. The device provides the user with detailed information such as their credit score, its breakdown, and how sentiment data influenced the rating. This allows the user to clearly understand their own credit situation.

[0163] As a concrete example, it is possible to explain how a large expenditure made while under high stress affects a credit score. An example of a prompt would be, "How would a credit score be affected if a user in their 40s indicated stress in recent voice data?"

[0164] This system aims to improve the quality of financial services by providing a new perspective on credit assessment that takes user emotions into account.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The server collects information on users' economic activities from financial institutions.

[0168] Specifically, the system uses APIs to retrieve account deposit and withdrawal history and credit card usage records from financial institutions. The input is financial data received via APIs, which is then filtered and converted into a useful format on the server. The output is analyzable economic activity data.

[0169] Step 2:

[0170] The server collects additional information related to the user's emotional state.

[0171] Specifically, the system acquires voice data, behavioral data, and location information through smartphones and wearable devices. The input consists of various sensor data transmitted from the devices, which are then integrated centrally. The output provides additional information necessary for emotional state analysis.

[0172] Step 3:

[0173] The server integrates and preprocesses the collected economic activity information and additional information.

[0174] This involves data cleansing and format conversion, removing inconsistent data and standardizing it. The input is integrated data from various data sources, and the output is a clean dataset that serves as the basis for analysis.

[0175] Step 4:

[0176] The server uses an emotion engine to analyze the emotional state.

[0177] In concrete terms, an algorithm for analyzing audio data assigns emotional labels such as stress and reassurance. The input is pre-processed audio data, and the output is emotional labels indicating the user's psychological state.

[0178] Step 5:

[0179] The server inputs the analysis data into the generating AI model and calculates the user's credit score.

[0180] The algorithm considers the correlation between economic activity and emotional state to assess credit risk. The input is integrated feature data, and the output is each user's credit score.

[0181] Step 6:

[0182] The server delivers the calculated credit rating results to the terminal.

[0183] Specifically, push notifications or emails are used to inform the user of the credit evaluation results on their device. The input is the credit score and its details, and the output is evaluation information formatted for the user.

[0184] Step 7:

[0185] The device visually displays the user's credit score and its breakdown.

[0186] The dashboard uses graphs and charts to intuitively display information, making it easier for users to understand the results. The input is formalized evaluation data, and the output is user-viewable visualized credit rating data.

[0187] Step 8:

[0188] The server executes a feedback loop to improve the generated AI model based on user feedback.

[0189] Specifically, this involves collecting user behavior data and feedback on evaluations to improve the accuracy of the model. The input is feedback data, and the output is the improved generative AI model.

[0190] (Application Example 2)

[0191] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0192] Traditional credit rating systems rely solely on transaction information from financial institutions and cannot accurately reflect the emotions and psychological state of individual users, potentially resulting in insufficient credit assessments. Furthermore, they lack the ability to provide flexible payment advice based on the user's real-time situation.

[0193] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0194] In this invention, the server includes means for collecting transaction information of financial institution customers, means for integrating and preprocessing the collected transaction information and user sentiment data, and means for extracting features from the transaction information and sentiment data. This enables dynamic and accurate credit assessment and real-time payment option suggestions that take into account the user's sentiment state.

[0195] "Means for collecting transaction information of financial institution customers" refers to technologies that obtain customer account activity and purchase history at financial institutions.

[0196] "Means for integrating and preprocessing emotional state data" refers to a process for collecting data related to emotional state, such as user voice data and location information, and converting it into a format suitable for analysis.

[0197] "Methods for extracting features" refer to techniques for identifying meaningful data points that indicate user behavior and psychological state from transaction information and sentiment data.

[0198] "Means of applying a generation algorithm" refers to computational methods that generate user credit ratings and payment options based on collected data.

[0199] "Means of distribution to information terminals" refers to technologies that transmit credit evaluation results and payment proposals to users' devices such as smartphones.

[0200] A "means of implementing a feedback loop" is a process for continuously improving algorithms based on user responses and actions.

[0201] This invention utilizes specific hardware and software to realize a system that provides credit assessment and payment suggestions while taking into account the user's emotional state. A server collects customer transaction information from financial institutions, including data on the user's economic activities. Furthermore, it collects emotional state-related data, such as voice data and location information, using the user's smartphone or wearable device. This involves using an emotion analysis engine, such as Google® Cloud Speech API, to supplement the voice data.

[0202] The server integrates and preprocesses this data to transform it into an analyzable state. Next, it extracts significant features from the data, calculates a credit score using a generative AI model, and generates payment options based on emotional states. This credit score and payment suggestion are delivered to the user's information terminal in real time, allowing the user to view this information and select a payment method on their smartphone.

[0203] Furthermore, the server monitors user behavior and feedback, and uses this information to improve the algorithm. This enables continuously evolving, dynamic credit assessment and payment management. For example, if a user is paying at a cafe they frequent and their voice is low-energy and they seem stressed, the system might suggest a smaller payment.

[0204] An example of a prompt message would be: "Emotional data indicating the user is experiencing stress has been detected from the voice. This user is currently slightly over budget. Please suggest a recommended payment method to provide appropriate financial advice."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server retrieves user transaction information from financial institutions. This information includes account deposit and withdrawal history and card usage records. The input is transaction information from the financial institution's database, and the output is transaction information in a parseable format. The server imports this data into its internal database and formats it so that it can be used in subsequent processing.

[0208] Step 2:

[0209] The server collects emotional state-related data, such as voice data and location information, from the user's smartphone or wearable device. The input is sensor data from the user's device, and the output is data converted into a format suitable for emotion analysis. The server processes the voice data using an emotion analysis engine such as the Google Cloud Speech API to determine the emotional state.

[0210] Step 3:

[0211] The server integrates and preprocesses the collected transaction information and sentiment data. The inputs are transaction information and sentiment data, and the outputs are features extracted from each of these pieces of information. The server applies a feature extraction algorithm to identify meaningful patterns from the data.

[0212] Step 4:

[0213] The server calculates a user's credit score using a generative AI model based on the extracted features. It also generates payment options based on the user's emotional state. The input is the extracted features, and the output is the credit score and proposed payment options. The server selects the optimal payment method based on the calculated score.

[0214] Step 5:

[0215] The server delivers the calculated credit score and proposed payment options to the user's information terminal. Inputs are the credit score and payment options, and output is a notification to the user's terminal. The user then reviews this information on their smartphone screen.

[0216] Step 6:

[0217] The user reviews the proposed payment options and selects the appropriate method. Input is notification information from the server, and output is the user's selection information. User feedback is sent to the server and used to improve the accuracy of future suggestions.

[0218] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0219] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0220] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0224] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0225] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0226] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0227] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0228] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0229] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0230] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0231] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0232] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0233] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0234] This invention provides a system for more accurate and efficient credit assessment of customers of various financial institutions. This system is implemented in the following manner.

[0235] First, the server collects customer transaction information provided by financial institutions. This transaction information includes detailed data about the customer's economic activities, such as deposit and withdrawal history, purchase history, and account transfer details. The server also obtains location information, purchasing trends, and life event data from other sources.

[0236] Next, this data is integrated and preprocessed to transform it into a format suitable for analysis. Data preprocessing includes supplementing incomplete data, identifying and handling outliers, and standardizing data formats. At this stage, the server extracts features from each customer to create a foundation for assessing credit risk.

[0237] The server then applies a generation algorithm to perform a real-time credit assessment for each customer. The algorithm utilizes machine learning techniques to calculate individual credit scores based on transaction patterns and purchasing behavior. For example, customers with a stable income are given high credit scores, while customers who frequently delay credit card payments are given low scores.

[0238] The credit assessment results are sent to the device and can be reviewed by the user as needed. The results may include not only the credit score but also advice on how to improve the score and a breakdown of how specific financial actions have affected the assessment.

[0239] Furthermore, the system incorporates a feedback loop to continuously improve the model. Specifically, it incorporates actual customer behavior and repayment history into the evaluation to improve the accuracy of the algorithm. Through this process, the system evolves over time, enabling it to provide more accurate credit ratings to a wider range of customers.

[0240] Thus, the present invention makes it possible to provide financial institutions with the latest credit assessments of their customers in real time by utilizing transaction information and location information.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The server retrieves customer transaction information from financial institutions and partners. This includes deposit and withdrawal history, credit card usage, loan repayment history, and purchase history, and the information is securely collected using Secure File Transfer Protocol (SFTP) and Application Programming Interface (API).

[0244] Step 2:

[0245] The server integrates the collected transaction information and converts information from different data sources into a consistent format. Furthermore, it cleans the data by processing noise and missing values. This results in a clean, analyzable dataset.

[0246] Step 3:

[0247] The server extracts specific features from the pre-processed data. For example, it calculates features that encompass the average monthly credit card spending, purchase frequency, income stability, and the number of payment delays. This information is then used in the subsequent scoring model.

[0248] Step 4:

[0249] The server applies a generative algorithm based on the features to calculate the customer's credit score. This algorithm uses machine learning techniques such as neural networks and decision tree models to simultaneously analyze many features and assess credit risk.

[0250] Step 5:

[0251] The server sends the calculated credit score to the user's device, which the user can then view directly. The data is displayed in a user-friendly interface, providing detailed feedback on the credit rating and areas for improvement.

[0252] Step 6:

[0253] The server collects feedback on actual customer credit performance, incorporates it into the algorithm, and continuously improves the model. This lays the foundation for improving the accuracy of future credit scoring.

[0254] (Example 1)

[0255] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0256] Financial institutions are required to effectively collect and process diverse data in order to properly assess the creditworthiness of their customers. However, conventional methods are insufficient in terms of credit risk assessment due to data incompleteness and inaccuracies in analysis. Therefore, the development of new systems that enable more accurate and efficient credit assessment is necessary.

[0257] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0258] In this invention, the server includes means for collecting activity information of users of financial institutions, means for integrating and pre-processing the collected activity information, and means for extracting indicators from the activity information. This makes it possible to perform more accurate credit risk assessments in real time.

[0259] A "financial institution" refers to an organization that provides services such as money management, lending, and remittance to its users.

[0260] "User" refers to an individual or group that utilizes the services of a financial institution and engages in transactions or purchasing activities.

[0261] "Activity information" refers to records of transactions conducted by users through financial institutions, purchasing behavior, location data, and information related to lifestyle events.

[0262] A "server" refers to a computing device that collects, processes, and analyzes data, and exchanges information with users and other systems.

[0263] "Integration" refers to the process of combining data collected from multiple sources into a single, unified format.

[0264] "Preprocessing" refers to processes that prepare data for analysis, such as imputing missing values, removing outliers, and standardizing the format.

[0265] An "indicator" refers to a numerical representation of characteristics or features extracted from data to assess a user's credit risk.

[0266] An "estimation algorithm" refers to a set of methods and procedures for evaluating indicators using data analysis techniques and calculating credit scores.

[0267] "Information device" refers to a device or terminal used by users to receive and confirm credit evaluation results.

[0268] A "return loop" refers to a system improvement process that involves readjusting the model based on evaluation results to improve the accuracy of subsequent processing.

[0269] This invention provides a system for efficiently and accurately evaluating the creditworthiness of financial institution users. The server first collects user activity information from financial institutions and external data sources. This activity information includes deposit and withdrawal history, purchasing behavior, location data, and information on lifestyle events. This data is integrated and pre-processed, during which incomplete data is supplemented and outliers are removed. From the information, which is then formatted into a standardized format, the server extracts indicators and executes an estimation algorithm based on these indicators.

[0270] Specifically, the server uses machine learning techniques and leverages generative AI models such as Random Forest and XGBoost to calculate a credit score for each user in real time. This allows for a quantitative evaluation of the user's trustworthiness. For example, users with a stable income and no delays in credit card payments are assigned a high score.

[0271] The credit assessment results are delivered to the terminal, and users can check the assessment results through their information devices. The assessment results include the user's credit score as well as specific advice on how to improve it. For example, it might be presented as, "Your score will increase if you improve your recent credit card payments."

[0272] Furthermore, the server has a feedback loop that compares evaluation results with actual actions to improve the accuracy of the estimation algorithm. This continuous improvement further enhances the reliability of the credit rating.

[0273] An example of a prompt message is, "Calculate this user's credit score and assess the likelihood of loan approval," which utilizes a generative AI model. This prompt allows the system to perform the necessary data processing and provide a specific credit assessment.

[0274] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0275] Step 1:

[0276] The server collects user activity information from financial institutions and external sources. The input data includes deposit and withdrawal history, purchasing behavior, location data, and lifestyle event information. This data is stored in a local database. The output is a raw dataset linked to each user.

[0277] Step 2:

[0278] The server preprocesses the collected raw dataset. To complement incomplete parts of the input data, median or average values are used. Also, outliers are identified and removed or corrected. The data format is standardized and converted into a format suitable for analysis. The output is a standardized dataset.

[0279] Step 3:

[0280] The server extracts metrics from the preprocessed data. Based on the input data, specific metrics such as the stability of the user's income and expenditure trends are quantified. At this stage, a feature selection algorithm is used to extract important metrics. The output is a list of metrics for each user.

[0281] Step 4:

[0282] The server conducts credit evaluations using a generated AI model. What is input is the list of metrics for each user. Machine learning algorithms (e.g., Random Forest, XGBoost) are utilized to calculate a credit score based on the metrics. The output is an individual credit score for each user.

[0283] Step 5:

[0284] The server distributes the calculated credit score to the terminal. The terminal displays the received credit score to the user. The input is the credit score and its breakdown information, and an evaluation interface that can be confirmed by the user is provided as the output. The user can receive details of the credit score and improvement suggestions.

[0285] Step 6:

[0286] The server executes a feedback loop. Using the user's actual repayment history and behavioral data, the accuracy of the model is improved. The input is the historical data and the latest evaluation results. Based on this, the model is retrained and its parameters are adjusted. The output is a machine learning model with improved accuracy.

[0287] (Application Example 1)

[0288] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0289] In electronic payment services, it is difficult to assess a user's credit risk in real time and individually propose the optimal payment method or credit option. Furthermore, conventional credit rating systems cannot effectively combine large amounts of individual purchase history and location data, making them unable to provide specific and useful advice to users. Therefore, it is necessary to conduct credit assessments tailored to users' economic activities and optimize their daily spending.

[0290] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0291] In this invention, the server includes means for collecting transaction data of financial institution users, means for integrating and pre-processing the collected transaction data, and means for extracting characteristics from the transaction data. This makes it possible to perform credit assessments in real time based on the user's purchase history and location information, and to propose the optimal electronic payment method or credit option.

[0292] "Financial institution user" refers to an individual or legal entity that generates transaction data, and that data is generated through a financial institution.

[0293] "Transaction data" is a general term for information related to economic activities, such as deposit and withdrawal history through financial institutions, purchase history, and account transfer details.

[0294] "Means of collection" refers to the processes and functions for collecting and storing data, and this includes various sensors and database technologies.

[0295] "Means of integration and preprocessing" refers to the process of centralizing collected data and converting it into a format suitable for analysis. This includes supplementing incomplete data and removing outliers.

[0296] "Means of extracting characteristics" refers to the process of identifying characteristic elements from data and extracting them in a format usable for analysis.

[0297] A "generative algorithm for credit evaluation" is a computational method or procedure for quantitatively evaluating a user's creditworthiness based on characteristics calculated from transaction data.

[0298] "Means of distribution to information devices" refers to communication processes and functions for providing the generated credit evaluation results in a format accessible to users.

[0299] "Feedback cycle" refers to the process of continuously using data to improve algorithms and enhance the accuracy of evaluations.

[0300] The system for implementing this invention consists of three elements: a server, a terminal, and a user.

[0301] The server first collects transaction data from financial institution users. This transaction data includes users' purchase history and location data. The server integrates and preprocesses this data. Preprocessing includes imputing incomplete data and removing outliers. Next, the server extracts characteristics from the transaction data and applies a generation algorithm to perform credit assessment based on those characteristics. Credit assessment is performed using machine learning techniques to evaluate credit risk in real time.

[0302] The evaluation results are delivered to the user's information device, a terminal, allowing the user to check their credit score. The terminal displays advice and credit suggestions for improving the score through a user interface. Furthermore, through a feedback cycle, the user's actual behavioral data is sent back to the server and used to improve the accuracy of the algorithm.

[0303] As a specific example, when a user checks their purchase history, the server displays the user's latest credit score and a proposal for a low-interest loan based on it. This proposal is accompanied by advice on what purchase behaviors contribute to score improvement.

[0304] The generative AI model performs credit evaluation using prompt texts as follows.

[0305] "To perform a credit evaluation, please use the following data. Purchase history: [date, item, price], location information: [latitude, longitude], past credit score: [date, score]. Please generate advice for the user to improve their future credit score."

[0306] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0307] Step 1:

[0308] The server collects the user's transaction data from data sources related to financial institutions. This data includes purchase history and location information. The input is raw data, and the output is a well-organized dataset. The server efficiently obtains data using API calls and stores it in a database.

[0309] Step 2:

[0310] The server integrates the collected data and performs preprocessing. The input is the raw data stored in the database, and the output is preprocessed clean data. Specifically, incomplete data is complemented, outliers are identified and removed. Also, the standardization of the data format is performed.

[0311] Step 3:

[0312] The server extracts characteristics from pre-processed data. The input is a clean dataset, and the output is a list of extracted characteristics. A machine learning model identifies important characteristics as features, preparing for the next step.

[0313] Step 4:

[0314] The server applies a generative algorithm to perform a credit assessment based on the extracted characteristics. The input is a list of characteristics, and the output is a credit score. Machine learning techniques are used to assess the user's credit risk. The model generates results in real time.

[0315] Step 5:

[0316] The server delivers the generated credit score to the user's device. The input is the generated credit score, and the output is the score displayed on the device. Users can check their own credit information on their device and receive feedback.

[0317] Step 6:

[0318] User behavior data is sent back to the server over time, forming a feedback loop. The input is the user's actual purchasing behavior and payment history, and the output is an improved generation algorithm. This improves the accuracy of credit assessment and ensures that the user's credit score is properly reflected.

[0319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0320] This invention provides a credit rating system that takes into account the user's emotional state. This system integrates not only transaction information from financial institutions but also user emotional data to achieve a more accurate and personalized credit rating.

[0321] First, the server collects customer transaction information from financial institutions. This transaction information includes account deposit and withdrawal history, card usage records, and purchase history. Simultaneously, the server also collects additional data related to the user's emotional state, such as voice data, behavioral data, and location information.

[0322] Next, this data is integrated and preprocessed. The server analyzes the collected data and uses an emotion engine to determine the user's emotional state. For example, it extracts emotions such as stress and a sense of security from voice data to evaluate the user's everyday psychological state.

[0323] The server then applies a generation algorithm based on a comprehensive set of features, including emotional state, to calculate the user's credit score. This algorithm considers the relationship between the user's economic behavior and emotional state to determine credit risk. For example, a user who is consistently experiencing high stress levels may be considered high-risk because a decrease in their willingness to pay is predicted.

[0324] The calculated credit rating results are delivered to the device for the user to review. The device provides the user with details of their credit score, its breakdown, and how emotional data influenced the rating. For example, it can explain how a large expenditure during a period of high stress affected the credit score.

[0325] Furthermore, the server establishes a feedback loop to continuously improve the accuracy of the algorithm. It monitors the user's actual behavior and emotional changes, and revises the evaluation criteria based on this information. In this way, the system evolves in response to changing times, enabling more accurate user credit assessments.

[0326] This invention incorporates emotion recognition technology into credit evaluation, thereby providing a multifaceted credit scoring system that goes beyond conventional evaluations based on financial information, and improving the quality of financial services.

[0327] The following describes the processing flow.

[0328] Step 1:

[0329] The server securely collects transaction information provided by financial institutions. This data includes transaction history, credit card statements, and loan repayment information, and is retrieved using APIs and secure data transfer protocols.

[0330] Step 2:

[0331] Users record voice and behavioral data on their devices through an emotion recognition application to collect their own emotional data. This includes the tone of voice during conversations and the frequency of specific activities.

[0332] Step 3:

[0333] The server integrates the collected transaction information and sentiment data and preprocesses it into a consistent data format. It then cleans the data, imputing missing information and removing outliers.

[0334] Step 4:

[0335] The server uses an emotion engine to analyze the user's emotional state. It identifies emotions such as stress levels and joy from voice tone and tags the emotional state.

[0336] Step 5:

[0337] The server extracts features based on pre-processed data and sentiment tags. Specifically, features include monthly spending, credit card usage frequency, and the frequency of sentiment tags.

[0338] Step 6:

[0339] The server applies machine learning algorithms to calculate the user's credit score in real time. The algorithms analyze both financial information and sentiment data to assess credit risk.

[0340] Step 7:

[0341] The device displays the evaluation results, including the calculated credit score, in a user interface. Users can check their own score, the impact of their emotional state on their credit rating, and suggestions for improvement.

[0342] Step 8:

[0343] The server tracks users' financial behavior and emotional changes, and runs a feedback loop to improve the model's accuracy. This ensures continuous improvement in evaluation accuracy.

[0344] (Example 2)

[0345] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0346] Traditional credit rating systems primarily rely on economic activity information from financial institutions and do not take into account the emotional state of users, making it impossible to comprehensively assess credit risk. Furthermore, they are unable to perform personalized assessments that utilize the relationship between emotional state and economic behavior, resulting in insufficient accuracy in assessing user creditworthiness.

[0347] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0348] In this invention, the server includes means for collecting economic activity information of financial institution users, means for collecting additional information related to emotional state from users, and means for analyzing emotional state using an emotion engine. This enables a multifaceted and personalized credit assessment that takes emotional state into account.

[0349] A "financial institution" is an organization that provides financial products and services to users, and includes banks, credit unions, securities companies, and others.

[0350] "Users" refers to individuals or corporations that utilize the services of a financial institution.

[0351] "Economic activity information" refers to data such as transaction history, records of expenses and income, and purchasing behavior related to the user's asset management.

[0352] "Emotional state" refers to data that indicates the user's psychological state and mental condition, and is obtained from voice analysis and behavioral patterns.

[0353] "Additional information" refers to non-financial information such as audio data, behavioral data, and location information related to understanding emotional states.

[0354] An "emotion engine" refers to software or technology that analyzes emotions from a user's voice and behavioral patterns and evaluates their psychological impact on economic behavior.

[0355] "Credit rating" refers to the results of an analysis used to determine a user's financial soundness and ability to pay, and is calculated based on integrated data of economic activity and emotional state.

[0356] A "feedback loop" refers to a series of processes that adjust data and algorithms based on evaluation results to improve the accuracy of the generation method.

[0357] The following system is constructed as an embodiment of this invention. The system consists of three main components: a server, a terminal, and a user.

[0358] The server is primarily designed to retrieve users' financial activity information from financial institutions. This information includes account deposit and withdrawal history, credit card usage records, and purchase history. The server also collects additional information related to the user's emotional state. This additional information includes voice data, behavioral data, and location information, obtained from smartphones and wearable devices.

[0359] The server uses an emotion engine to analyze emotional states. This emotion engine incorporates speech analysis and natural language processing technologies to determine emotions such as stress and feelings of security from voice data. This makes it possible to analyze the psychological impact on users' economic behavior.

[0360] The analyzed data is input into a generative AI model to calculate the user's credit score. This model takes into account both economic activity and emotional state to provide a multifaceted and personalized credit assessment. The credit score aims for real-time optimization, and the generative AI model can provide a highly accurate assessment.

[0361] The calculated credit rating results are delivered to the user via the device. The device provides the user with detailed information such as their credit score, its breakdown, and how sentiment data influenced the rating. This allows the user to clearly understand their own credit situation.

[0362] As a concrete example, it is possible to explain how a large expenditure made while under high stress affects a credit score. An example of a prompt would be, "How would a credit score be affected if a user in their 40s indicated stress in recent voice data?"

[0363] This system aims to improve the quality of financial services by providing a new perspective on credit assessment that takes user emotions into account.

[0364] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0365] Step 1:

[0366] The server collects information on users' economic activities from financial institutions.

[0367] Specifically, the system uses APIs to retrieve account deposit and withdrawal history and credit card usage records from financial institutions. The input is financial data received via the API, which is then filtered and converted into a useful format on the server. The output is analyzable economic activity data.

[0368] Step 2:

[0369] The server collects additional information related to the user's emotional state.

[0370] Specifically, the system acquires voice data, behavioral data, and location information through smartphones and wearable devices. The input consists of various sensor data transmitted from the devices, which are then integrated centrally. The output provides additional information necessary for emotional state analysis.

[0371] Step 3:

[0372] The server integrates and preprocesses the collected economic activity information and additional information.

[0373] This includes data cleansing and format conversion, removing inconsistent data and standardizing it. The input is integrated data from various data sources, and the output is a clean dataset that serves as the basis for analysis.

[0374] Step 4:

[0375] The server uses an emotion engine to analyze the emotional state.

[0376] In concrete terms, an algorithm for analyzing audio data assigns emotional labels such as stress and reassurance. The input is pre-processed audio data, and the output is emotional labels indicating the user's psychological state.

[0377] Step 5:

[0378] The server inputs the analysis data into the generating AI model and calculates the user's credit score.

[0379] The algorithm considers the correlation between economic activity and emotional state to assess credit risk. The input is integrated feature data, and the output is each user's credit score.

[0380] Step 6:

[0381] The server delivers the calculated credit rating results to the terminal.

[0382] Specifically, push notifications or emails are used to inform the user of the credit evaluation results on their device. The input is the credit score and its details, and the output is evaluation information formatted for the user.

[0383] Step 7:

[0384] The device visually displays the user's credit score and its breakdown.

[0385] The dashboard uses graphs and charts to intuitively display information, making it easier for users to understand the results. The input is formalized evaluation data, and the output is user-viewable visualized credit rating data.

[0386] Step 8:

[0387] The server executes a feedback loop to improve the generated AI model based on user feedback.

[0388] Specifically, this involves collecting user behavior data and feedback on evaluations to improve the accuracy of the model. The input is feedback data, and the output is the improved generative AI model.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0391] Traditional credit rating systems rely solely on transaction information from financial institutions and cannot accurately reflect the emotions and psychological state of individual users, potentially resulting in insufficient credit assessments. Furthermore, they lack the ability to provide flexible payment advice based on the user's real-time situation.

[0392] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0393] In this invention, the server includes means for collecting transaction information of financial institution customers, means for integrating and preprocessing the collected transaction information and user sentiment data, and means for extracting features from the transaction information and sentiment data. This enables dynamic and accurate credit assessment and real-time payment option suggestions that take into account the user's sentiment state.

[0394] "Means for collecting transaction information of financial institution customers" refers to technologies that obtain customer account activity and purchase history at financial institutions.

[0395] "Means for integrating and preprocessing emotional state data" refers to a process for collecting data related to emotional state, such as user voice data and location information, and converting it into a format suitable for analysis.

[0396] "Methods for extracting features" refer to techniques for identifying meaningful data points that indicate user behavior and psychological state from transaction information and sentiment data.

[0397] "Means of applying a generation algorithm" refers to computational methods that generate user credit ratings and payment options based on collected data.

[0398] "Means of distribution to information terminals" refers to technologies that transmit credit evaluation results and payment proposals to users' devices such as smartphones.

[0399] A "means of implementing a feedback loop" is a process for continuously improving algorithms based on user responses and actions.

[0400] This invention utilizes specific hardware and software to realize a system that provides credit assessment and payment suggestions while taking into account the user's emotional state. A server collects customer transaction information from financial institutions, including data on the user's economic activities. Furthermore, it collects emotional state-related data, such as voice data and location information, using the user's smartphone or wearable device. This involves using an emotion analysis engine, such as the Google Cloud Speech API, to supplement the voice data.

[0401] The server integrates and preprocesses this data to transform it into an analyzable state. Next, it extracts significant features from the data, calculates a credit score using a generative AI model, and generates payment options based on emotional states. This credit score and payment suggestion are delivered to the user's information terminal in real time, allowing the user to view this information and select a payment method on their smartphone.

[0402] Furthermore, the server monitors user behavior and feedback, and uses this information to improve the algorithm. This enables continuously evolving, dynamic credit assessment and payment management. For example, if a user is paying at a cafe they frequent and their voice is low-energy and they seem stressed, the system might suggest a smaller payment.

[0403] An example of a prompt message would be: "Emotional data indicating the user is experiencing stress has been detected from the voice. This user is currently slightly over budget. Please suggest a recommended payment method to provide appropriate financial advice."

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The server retrieves user transaction information from financial institutions. This information includes account deposit and withdrawal history and card usage records. The input is transaction information from the financial institution's database, and the output is transaction information in a parseable format. The server imports this data into its internal database and formats it so that it can be used in subsequent processing.

[0407] Step 2:

[0408] The server collects emotional state-related data, such as voice data and location information, from the user's smartphone or wearable device. The input is sensor data from the user's device, and the output is data converted into a format suitable for emotion analysis. The server processes the voice data using an emotion analysis engine such as the Google Cloud Speech API to determine the emotional state.

[0409] Step 3:

[0410] The server integrates and preprocesses the collected transaction information and sentiment data. The inputs are transaction information and sentiment data, and the outputs are features extracted from each of these pieces of information. The server applies a feature extraction algorithm to identify meaningful patterns from the data.

[0411] Step 4:

[0412] The server calculates a user's credit score using a generative AI model based on the extracted features. It also generates payment options based on the user's emotional state. The input is the extracted features, and the output is the credit score and proposed payment options. The server selects the optimal payment method based on the calculated score.

[0413] Step 5:

[0414] The server delivers the calculated credit score and proposed payment options to the user's information terminal. Inputs are the credit score and payment options, and output is a notification to the user's terminal. The user then reviews this information on their smartphone screen.

[0415] Step 6:

[0416] The user reviews the proposed payment options and selects the appropriate method. Input is notification information from the server, and output is the user's selection information. User feedback is sent to the server and used to improve the accuracy of future suggestions.

[0417] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0418] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0423] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0425] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0427] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0428] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0429] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0430] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0432] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0433] This invention provides a system for more accurate and efficient credit assessment of customers of various financial institutions. This system is implemented in the following manner.

[0434] First, the server collects customer transaction information provided by financial institutions. This transaction information includes detailed data about the customer's economic activities, such as deposit and withdrawal history, purchase history, and account transfer details. The server also obtains location information, purchasing trends, and life event data from other sources.

[0435] Next, this data is integrated and preprocessed to transform it into a format suitable for analysis. Data preprocessing includes supplementing incomplete data, identifying and handling outliers, and standardizing data formats. At this stage, the server extracts features from each customer to create a foundation for assessing credit risk.

[0436] The server then applies a generation algorithm to perform a real-time credit assessment for each customer. The algorithm utilizes machine learning techniques to calculate individual credit scores based on transaction patterns and purchasing behavior. For example, customers with a stable income are given high credit scores, while customers who frequently delay credit card payments are given low scores.

[0437] The credit assessment results are sent to the device and can be reviewed by the user as needed. The results may include not only the credit score but also advice on how to improve the score and a breakdown of how specific financial actions have affected the assessment.

[0438] Furthermore, the system incorporates a feedback loop to continuously improve the model. Specifically, it incorporates actual customer behavior and repayment history into the evaluation to improve the accuracy of the algorithm. Through this process, the system evolves over time, enabling it to provide more accurate credit ratings to a wider range of customers.

[0439] Thus, the present invention makes it possible to provide financial institutions with the latest credit assessments of their customers in real time by utilizing transaction information and location information.

[0440] The following describes the processing flow.

[0441] Step 1:

[0442] The server retrieves customer transaction information from financial institutions and partners. This includes deposit and withdrawal history, credit card usage, loan repayment history, and purchase history, and the information is securely collected using Secure File Transfer Protocol (SFTP) and Application Programming Interface (API).

[0443] Step 2:

[0444] The server integrates the collected transaction information and converts information from different data sources into a consistent format. Furthermore, it cleans the data by processing noise and missing values. This results in a clean, analyzable dataset.

[0445] Step 3:

[0446] The server extracts specific features from the pre-processed data. For example, it calculates features that encompass the average monthly credit card spending, purchase frequency, income stability, and the number of payment delays. This information is then used in the subsequent scoring model.

[0447] Step 4:

[0448] The server applies a generative algorithm based on the features to calculate the customer's credit score. This algorithm uses machine learning techniques such as neural networks and decision tree models to simultaneously analyze many features and assess credit risk.

[0449] Step 5:

[0450] The server sends the calculated credit score to the user's device, which the user can then view directly. The data is displayed in a user-friendly interface, providing detailed feedback on the credit rating and areas for improvement.

[0451] Step 6:

[0452] The server collects feedback on actual customer credit performance, incorporates it into the algorithm, and continuously improves the model. This lays the foundation for improving the accuracy of future credit scoring.

[0453] (Example 1)

[0454] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0455] Financial institutions are required to effectively collect and process diverse data in order to properly assess the creditworthiness of their customers. However, conventional methods are insufficient in terms of credit risk assessment due to data incompleteness and inaccuracies in analysis. Therefore, the development of new systems that enable more accurate and efficient credit assessment is necessary.

[0456] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0457] In this invention, the server includes means for collecting activity information of users of financial institutions, means for integrating and pre-processing the collected activity information, and means for extracting indicators from the activity information. This makes it possible to perform more accurate credit risk assessments in real time.

[0458] A "financial institution" refers to an organization that provides services such as money management, lending, and remittance to its users.

[0459] "User" refers to an individual or group that utilizes the services of a financial institution and engages in transactions or purchasing activities.

[0460] "Activity information" refers to records of transactions conducted by users through financial institutions, purchasing behavior, location data, and information related to lifestyle events.

[0461] A "server" refers to a computing device that collects, processes, and analyzes data, and exchanges information with users and other systems.

[0462] "Integration" refers to the process of combining data collected from multiple sources into a single, unified format.

[0463] "Preprocessing" refers to processes that prepare data for analysis, such as imputing missing values, removing outliers, and standardizing the format.

[0464] An "indicator" refers to a numerical representation of characteristics or features extracted from data to assess a user's credit risk.

[0465] An "estimation algorithm" refers to a set of methods and procedures for evaluating indicators using data analysis techniques and calculating credit scores.

[0466] "Information device" refers to a device or terminal used by users to receive and confirm credit evaluation results.

[0467] A "return loop" refers to a system improvement process that involves readjusting the model based on evaluation results to improve the accuracy of subsequent processing.

[0468] This invention provides a system for efficiently and accurately evaluating the creditworthiness of financial institution users. The server first collects user activity information from financial institutions and external data sources. This activity information includes deposit and withdrawal history, purchasing behavior, location data, and information on lifestyle events. This data is integrated and pre-processed, during which incomplete data is supplemented and outliers are removed. From the information, which is then formatted into a standardized format, the server extracts indicators and executes an estimation algorithm based on these indicators.

[0469] Specifically, the server uses machine learning techniques and leverages generative AI models such as Random Forest and XGBoost to calculate a credit score for each user in real time. This allows for a quantitative evaluation of the user's trustworthiness. For example, users with a stable income and no delays in credit card payments are assigned a high score.

[0470] The credit assessment results are delivered to the terminal, and users can check the assessment results through their information devices. The assessment results include the user's credit score as well as specific advice on how to improve it. For example, it might be presented as, "Your score will increase if you improve your recent credit card payments."

[0471] Furthermore, the server has a feedback loop that compares evaluation results with actual actions to improve the accuracy of the estimation algorithm. This continuous improvement further enhances the reliability of the credit rating.

[0472] An example of a prompt message is, "Calculate this user's credit score and assess the likelihood of loan approval," which utilizes a generative AI model. This prompt allows the system to perform the necessary data processing and provide a specific credit assessment.

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The server collects user activity information from financial institutions and external sources. The input data includes deposit and withdrawal history, purchasing behavior, location data, and lifestyle event information. This data is stored in a local database. The output is a raw dataset linked to each user.

[0476] Step 2:

[0477] The server preprocesses the collected raw dataset. It uses medians and means to fill in any incomplete parts of the input data. It also identifies, removes, or corrects outliers. It standardizes the data format and converts it into a format suitable for analysis. The output is a standardized dataset.

[0478] Step 3:

[0479] The server extracts metrics from pre-processed data. Based on the input data, it quantifies specific metrics such as the stability of the user's income and their spending trends. At this stage, a feature selection algorithm is used to extract important metrics. The output is a list of metrics for each user.

[0480] Step 4:

[0481] The server performs credit assessments using a generative AI model. The input is a list of metrics for each user. Machine learning algorithms (e.g., Random Forest or XGBoost) are used to calculate a credit score based on these metrics. The output is an individual credit score for each user.

[0482] Step 5:

[0483] The server delivers the calculated credit score to the terminal. The terminal displays the received credit score to the user. The input is the credit score and its breakdown, and the output is an evaluation interface that the user can review. The user can receive detailed information about their credit score and suggestions for improvement.

[0484] Step 6:

[0485] The server executes a feedback loop, improving the model's accuracy using actual user repayment history and behavioral data. The input consists of historical data and the latest evaluation results. Based on this, the model is retrained and parameters are adjusted. The output is the improved machine learning model.

[0486] (Application Example 1)

[0487] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0488] In electronic payment services, it is difficult to assess a user's credit risk in real time and individually propose the optimal payment method or credit option. Furthermore, conventional credit rating systems cannot effectively combine large amounts of individual purchase history and location data, making them unable to provide specific and useful advice to users. Therefore, it is necessary to conduct credit assessments tailored to users' economic activities and optimize their daily spending.

[0489] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0490] In this invention, the server includes means for collecting transaction data of financial institution users, means for integrating and pre-processing the collected transaction data, and means for extracting characteristics from the transaction data. This makes it possible to perform credit assessments in real time based on the user's purchase history and location information, and to propose the optimal electronic payment method or credit option.

[0491] "Financial institution user" refers to an individual or legal entity that generates transaction data, and that data is generated through a financial institution.

[0492] "Transaction data" is a general term for information related to economic activities, such as deposit and withdrawal history through financial institutions, purchase history, and account transfer details.

[0493] "Means of collection" refers to the processes and functions for collecting and storing data, and this includes various sensors and database technologies.

[0494] "Means of integration and preprocessing" refers to the process of centralizing collected data and converting it into a format suitable for analysis. This includes supplementing incomplete data and removing outliers.

[0495] "Means of extracting characteristics" refers to the process of identifying characteristic elements from data and extracting them in a format usable for analysis.

[0496] A "generative algorithm for credit evaluation" is a computational method or procedure for quantitatively evaluating a user's creditworthiness based on characteristics calculated from transaction data.

[0497] "Means of distribution to information devices" refers to communication processes and functions for providing the generated credit evaluation results in a format accessible to users.

[0498] "Feedback cycle" refers to the process of continuously using data to improve algorithms and enhance the accuracy of evaluations.

[0499] The system for implementing this invention consists of three elements: a server, a terminal, and a user.

[0500] The server first collects transaction data from financial institution users. This transaction data includes users' purchase history and location data. The server integrates and preprocesses this data. Preprocessing includes imputing incomplete data and removing outliers. Next, the server extracts characteristics from the transaction data and applies a generation algorithm to perform credit assessment based on those characteristics. Credit assessment is performed using machine learning techniques to evaluate credit risk in real time.

[0501] The evaluation results are delivered to the user's information device, a terminal, allowing the user to check their credit score. The terminal displays advice and credit suggestions for improving the score through a user interface. Furthermore, through a feedback cycle, the user's actual behavioral data is sent back to the server and used to improve the accuracy of the algorithm.

[0502] As a concrete example, when a user reviews their purchase history, the server displays the user's latest credit score and offers low-interest loans based on that score. These offers also include advice on what purchasing behaviors can contribute to improving the score.

[0503] The generative AI model performs credit assessment using prompts like the following:

[0504] "To perform a credit assessment, please use the following data: Purchase history: [Date, Item, Price], Location information: [Latitude, Longitude], Past credit score: [Date, Score]. Generate advice for the user to improve their future credit score."

[0505] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0506] Step 1:

[0507] The server collects user transaction data from financial institutions and related data sources. This data includes purchase history and location information. The input is raw data, and the output is a well-organized dataset. The server efficiently retrieves data using API calls and stores it in a database.

[0508] Step 2:

[0509] The server integrates and preprocesses the collected data. The input is raw data stored in the database, and the output is clean, preprocessed data. Specifically, it supplements incomplete data, identifies and removes outliers, and standardizes the data format.

[0510] Step 3:

[0511] The server extracts characteristics from pre-processed data. The input is a clean dataset, and the output is a list of extracted characteristics. A machine learning model identifies important characteristics as features, preparing for the next step.

[0512] Step 4:

[0513] The server applies a generative algorithm to perform a credit assessment based on the extracted characteristics. The input is a list of characteristics, and the output is a credit score. Machine learning techniques are used to assess the user's credit risk. The model generates results in real time.

[0514] Step 5:

[0515] The server delivers the generated credit score to the user's device. The input is the generated credit score, and the output is the score displayed on the device. Users can check their own credit information on their device and receive feedback.

[0516] Step 6:

[0517] User behavior data is sent back to the server over time, forming a feedback loop. The input is the user's actual purchasing behavior and payment history, and the output is an improved generation algorithm. This improves the accuracy of credit assessment and ensures that the user's credit score is properly reflected.

[0518] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0519] This invention provides a credit rating system that takes into account the user's emotional state. This system integrates not only transaction information from financial institutions but also user emotional data to achieve a more accurate and personalized credit rating.

[0520] First, the server collects customer transaction information from financial institutions. This transaction information includes account deposit and withdrawal history, card usage records, and purchase history. Simultaneously, the server also collects additional data related to the user's emotional state, such as voice data, behavioral data, and location information.

[0521] Next, this data is integrated and preprocessed. The server analyzes the collected data and uses an emotion engine to determine the user's emotional state. For example, it extracts emotions such as stress and a sense of security from voice data to evaluate the user's everyday psychological state.

[0522] The server then applies a generation algorithm based on a comprehensive set of features, including emotional state, to calculate the user's credit score. This algorithm considers the relationship between the user's economic behavior and emotional state to determine credit risk. For example, a user who is consistently experiencing high stress levels may be considered high-risk because a decrease in their willingness to pay is predicted.

[0523] The calculated credit rating results are delivered to the device for the user to review. The device provides the user with details of their credit score, its breakdown, and how emotional data influenced the rating. For example, it can explain how a large expenditure during a period of high stress affected the credit score.

[0524] Furthermore, the server establishes a feedback loop to continuously improve the accuracy of the algorithm. It monitors the user's actual behavior and emotional changes, and revises the evaluation criteria based on this information. In this way, the system evolves in response to changing times, enabling more accurate user credit assessments.

[0525] This invention incorporates emotion recognition technology into credit evaluation, thereby providing a multifaceted credit scoring system that goes beyond conventional evaluations based on financial information, and improving the quality of financial services.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The server securely collects transaction information provided by financial institutions. This data includes transaction history, credit card statements, and loan repayment information, and is retrieved using APIs and secure data transfer protocols.

[0529] Step 2:

[0530] Users record voice and behavioral data on their devices through an emotion recognition application to collect their own emotional data. This includes the tone of voice during conversations and the frequency of specific activities.

[0531] Step 3:

[0532] The server integrates the collected transaction information and sentiment data and preprocesses it into a consistent data format. It then cleans the data, imputing missing information and removing outliers.

[0533] Step 4:

[0534] The server uses an emotion engine to analyze the user's emotional state. It identifies emotions such as stress levels and joy from voice tone and tags the emotional state.

[0535] Step 5:

[0536] The server extracts features based on pre-processed data and sentiment tags. Specifically, features include monthly spending, credit card usage frequency, and the frequency of sentiment tags.

[0537] Step 6:

[0538] The server applies machine learning algorithms to calculate the user's credit score in real time. The algorithms analyze both financial information and sentiment data to assess credit risk.

[0539] Step 7:

[0540] The device displays the evaluation results, including the calculated credit score, in a user interface. Users can check their own score, the impact of their emotional state on their credit rating, and suggestions for improvement.

[0541] Step 8:

[0542] The server tracks users' financial behavior and emotional changes, and runs a feedback loop to improve the model's accuracy. This ensures continuous improvement in evaluation accuracy.

[0543] (Example 2)

[0544] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0545] Traditional credit rating systems primarily rely on economic activity information from financial institutions and do not take into account the emotional state of users, making it impossible to comprehensively assess credit risk. Furthermore, they are unable to perform personalized assessments that utilize the relationship between emotional state and economic behavior, resulting in insufficient accuracy in assessing user creditworthiness.

[0546] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0547] In this invention, the server includes means for collecting economic activity information of financial institution users, means for collecting additional information related to emotional state from users, and means for analyzing emotional state using an emotion engine. This enables a multifaceted and personalized credit assessment that takes emotional state into account.

[0548] A "financial institution" is an organization that provides financial products and services to users, and includes banks, credit unions, securities companies, and others.

[0549] "Users" refers to individuals or corporations that utilize the services of a financial institution.

[0550] "Economic activity information" refers to data such as transaction history, records of expenses and income, and purchasing behavior related to the user's asset management.

[0551] "Emotional state" refers to data that indicates the user's psychological state and mental condition, and is obtained from voice analysis and behavioral patterns.

[0552] "Additional information" refers to non-financial information such as audio data, behavioral data, and location information related to understanding emotional states.

[0553] An "emotion engine" refers to software or technology that analyzes emotions from a user's voice and behavioral patterns and evaluates their psychological impact on economic behavior.

[0554] "Credit rating" refers to the results of an analysis used to determine a user's financial soundness and ability to pay, and is calculated based on integrated data of economic activity and emotional state.

[0555] A "feedback loop" refers to a series of processes that adjust data and algorithms based on evaluation results to improve the accuracy of the generation method.

[0556] The following system is constructed as an embodiment of this invention. The system consists of three main components: a server, a terminal, and a user.

[0557] The server is primarily designed to retrieve users' financial activity information from financial institutions. This information includes account deposit and withdrawal history, credit card usage records, and purchase history. The server also collects additional information related to the user's emotional state. This additional information includes voice data, behavioral data, and location information, obtained from smartphones and wearable devices.

[0558] The server uses an emotion engine to analyze emotional states. This emotion engine incorporates speech analysis and natural language processing technologies to determine emotions such as stress and feelings of security from voice data. This makes it possible to analyze the psychological impact on users' economic behavior.

[0559] The analyzed data is input into a generative AI model to calculate the user's credit score. This model takes into account both economic activity and emotional state to provide a multifaceted and personalized credit assessment. The credit score aims for real-time optimization, and the generative AI model can provide a highly accurate assessment.

[0560] The calculated credit rating results are delivered to the user via the device. The device provides the user with detailed information such as their credit score, its breakdown, and how sentiment data influenced the rating. This allows the user to clearly understand their own credit situation.

[0561] As a concrete example, it is possible to explain how a large expenditure made while under high stress affects a credit score. An example of a prompt would be, "How would a credit score be affected if a user in their 40s indicated stress in recent voice data?"

[0562] This system aims to improve the quality of financial services by providing a new perspective on credit assessment that takes user emotions into account.

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] Step 1:

[0565] The server collects information on users' economic activities from financial institutions.

[0566] Specifically, the system uses APIs to retrieve account deposit and withdrawal history and credit card usage records from financial institutions. The input is financial data received via the API, which is then filtered and converted into a useful format on the server. The output is analyzable economic activity data.

[0567] Step 2:

[0568] The server collects additional information related to the user's emotional state.

[0569] Specifically, the system acquires voice data, behavioral data, and location information through smartphones and wearable devices. The input consists of various sensor data transmitted from the devices, which are then integrated centrally. The output provides additional information necessary for emotional state analysis.

[0570] Step 3:

[0571] The server integrates and preprocesses the collected economic activity information and additional information.

[0572] This includes data cleansing and format conversion, removing inconsistent data and standardizing it. The input is integrated data from various data sources, and the output is a clean dataset that serves as the basis for analysis.

[0573] Step 4:

[0574] The server uses an emotion engine to analyze the emotional state.

[0575] In concrete terms, an algorithm for analyzing audio data assigns emotional labels such as stress and reassurance. The input is pre-processed audio data, and the output is emotional labels indicating the user's psychological state.

[0576] Step 5:

[0577] The server inputs the analysis data into the generating AI model and calculates the user's credit score.

[0578] The algorithm considers the correlation between economic activity and emotional state to assess credit risk. The input is integrated feature data, and the output is each user's credit score.

[0579] Step 6:

[0580] The server delivers the calculated credit rating results to the terminal.

[0581] Specifically, push notifications or emails are used to inform the user of the credit evaluation results on their device. The input is the credit score and its details, and the output is evaluation information formatted for the user.

[0582] Step 7:

[0583] The device visually displays the user's credit score and its breakdown.

[0584] The dashboard uses graphs and charts to intuitively display information, making it easier for users to understand the results. The input is formalized evaluation data, and the output is user-viewable visualized credit rating data.

[0585] Step 8:

[0586] The server executes a feedback loop to improve the generated AI model based on user feedback.

[0587] Specifically, this involves collecting user behavior data and feedback on evaluations to improve the accuracy of the model. The input is feedback data, and the output is the improved generative AI model.

[0588] (Application Example 2)

[0589] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0590] Traditional credit rating systems rely solely on transaction information from financial institutions and cannot accurately reflect the emotions and psychological state of individual users, potentially resulting in insufficient credit assessments. Furthermore, they lack the ability to provide flexible payment advice based on the user's real-time situation.

[0591] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0592] In this invention, the server includes means for collecting transaction information of financial institution customers, means for integrating and preprocessing the collected transaction information and user sentiment data, and means for extracting features from the transaction information and sentiment data. This enables dynamic and accurate credit assessment and real-time payment option suggestions that take into account the user's sentiment state.

[0593] "Means for collecting transaction information of financial institution customers" refers to technologies that obtain customer account activity and purchase history at financial institutions.

[0594] "Means for integrating and preprocessing emotional state data" refers to a process for collecting data related to emotional state, such as user voice data and location information, and converting it into a format suitable for analysis.

[0595] "Methods for extracting features" refer to techniques for identifying meaningful data points that indicate user behavior and psychological state from transaction information and sentiment data.

[0596] "Means of applying a generation algorithm" refers to computational methods that generate user credit ratings and payment options based on collected data.

[0597] "Means of distribution to information terminals" refers to technologies that transmit credit evaluation results and payment proposals to users' devices such as smartphones.

[0598] A "means of implementing a feedback loop" is a process for continuously improving algorithms based on user responses and actions.

[0599] This invention utilizes specific hardware and software to realize a system that provides credit assessment and payment suggestions while taking into account the user's emotional state. A server collects customer transaction information from financial institutions, including data on the user's economic activities. Furthermore, it collects emotional state-related data, such as voice data and location information, using the user's smartphone or wearable device. This involves using an emotion analysis engine, such as the Google Cloud Speech API, to supplement the voice data.

[0600] The server integrates and preprocesses this data to transform it into an analyzable state. Next, it extracts significant features from the data, calculates a credit score using a generative AI model, and generates payment options based on emotional states. This credit score and payment suggestion are delivered to the user's information terminal in real time, allowing the user to view this information and select a payment method on their smartphone.

[0601] Furthermore, the server monitors user behavior and feedback, and uses this information to improve the algorithm. This enables continuously evolving, dynamic credit assessment and payment management. For example, if a user is paying at a cafe they frequent and their voice is low-energy and they seem stressed, the system might suggest a smaller payment.

[0602] An example of a prompt message would be: "Emotional data indicating the user is experiencing stress has been detected from the voice. This user is currently slightly over budget. Please suggest a recommended payment method to provide appropriate financial advice."

[0603] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0604] Step 1:

[0605] The server retrieves user transaction information from financial institutions. This information includes account deposit and withdrawal history and card usage records. The input is transaction information from the financial institution's database, and the output is transaction information in a parseable format. The server imports this data into its internal database and formats it so that it can be used in subsequent processing.

[0606] Step 2:

[0607] The server collects emotional state-related data, such as voice data and location information, from the user's smartphone or wearable device. The input is sensor data from the user's device, and the output is data converted into a format suitable for emotion analysis. The server processes the voice data using an emotion analysis engine such as the Google Cloud Speech API to determine the emotional state.

[0608] Step 3:

[0609] The server integrates and preprocesses the collected transaction information and sentiment data. The inputs are transaction information and sentiment data, and the outputs are features extracted from each of these pieces of information. The server applies a feature extraction algorithm to identify meaningful patterns from the data.

[0610] Step 4:

[0611] The server calculates a user's credit score using a generative AI model based on the extracted features. It also generates payment options based on the user's emotional state. The input is the extracted features, and the output is the credit score and proposed payment options. The server selects the optimal payment method based on the calculated score.

[0612] Step 5:

[0613] The server delivers the calculated credit score and proposed payment options to the user's information terminal. Inputs are the credit score and payment options, and output is a notification to the user's terminal. The user then reviews this information on their smartphone screen.

[0614] Step 6:

[0615] The user reviews the proposed payment options and selects the appropriate method. Input is notification information from the server, and output is the user's selection information. User feedback is sent to the server and used to improve the accuracy of future suggestions.

[0616] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0617] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0618] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0619] [Fourth Embodiment]

[0620] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0621] As shown in Figure 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.

[0622] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0623] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0624] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0625] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0626] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0627] The controlled 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0628] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0629] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0630] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0631] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0632] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0633] This invention provides a system for more accurate and efficient credit assessment of customers of various financial institutions. This system is implemented in the following manner.

[0634] First, the server collects customer transaction information provided by financial institutions. This transaction information includes detailed data about the customer's economic activities, such as deposit and withdrawal history, purchase history, and account transfer details. The server also obtains location information, purchasing trends, and life event data from other sources.

[0635] Next, this data is integrated and preprocessed to transform it into a format suitable for analysis. Data preprocessing includes supplementing incomplete data, identifying and handling outliers, and standardizing data formats. At this stage, the server extracts features from each customer to create a foundation for assessing credit risk.

[0636] The server then applies a generation algorithm to perform a real-time credit assessment for each customer. The algorithm utilizes machine learning techniques to calculate individual credit scores based on transaction patterns and purchasing behavior. For example, customers with a stable income are given high credit scores, while customers who frequently delay credit card payments are given low scores.

[0637] The credit assessment results are sent to the device and can be reviewed by the user as needed. The results may include not only the credit score but also advice on how to improve the score and a breakdown of how specific financial actions have affected the assessment.

[0638] Furthermore, the system incorporates a feedback loop to continuously improve the model. Specifically, it incorporates actual customer behavior and repayment history into the evaluation to improve the accuracy of the algorithm. Through this process, the system evolves over time, enabling it to provide more accurate credit ratings to a wider range of customers.

[0639] Thus, the present invention makes it possible to provide financial institutions with the latest credit assessments of their customers in real time by utilizing transaction information and location information.

[0640] The following describes the processing flow.

[0641] Step 1:

[0642] The server retrieves customer transaction information from financial institutions and partners. This includes deposit and withdrawal history, credit card usage, loan repayment history, and purchase history, and the information is securely collected using Secure File Transfer Protocol (SFTP) and Application Programming Interface (API).

[0643] Step 2:

[0644] The server integrates the collected transaction information and converts information from different data sources into a consistent format. Furthermore, it cleans the data by processing noise and missing values. This results in a clean, analyzable dataset.

[0645] Step 3:

[0646] The server extracts specific features from the pre-processed data. For example, it calculates features that encompass the average monthly credit card spending, purchase frequency, income stability, and the number of payment delays. This information is then used in the subsequent scoring model.

[0647] Step 4:

[0648] The server applies a generative algorithm based on the features to calculate the customer's credit score. This algorithm uses machine learning techniques such as neural networks and decision tree models to simultaneously analyze many features and assess credit risk.

[0649] Step 5:

[0650] The server sends the calculated credit score to the user's device, which the user can then view directly. The data is displayed in a user-friendly interface, providing detailed feedback on the credit rating and areas for improvement.

[0651] Step 6:

[0652] The server collects feedback on actual customer credit performance, incorporates it into the algorithm, and continuously improves the model. This lays the foundation for improving the accuracy of future credit scoring.

[0653] (Example 1)

[0654] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0655] Financial institutions are required to effectively collect and process diverse data in order to properly assess the creditworthiness of their customers. However, conventional methods are insufficient in terms of credit risk assessment due to data incompleteness and inaccuracies in analysis. Therefore, the development of new systems that enable more accurate and efficient credit assessment is necessary.

[0656] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0657] In this invention, the server includes means for collecting activity information of users of financial institutions, means for integrating and pre-processing the collected activity information, and means for extracting indicators from the activity information. This makes it possible to perform more accurate credit risk assessments in real time.

[0658] A "financial institution" refers to an organization that provides services such as money management, lending, and remittance to its users.

[0659] "User" refers to an individual or group that utilizes the services of a financial institution and engages in transactions or purchasing activities.

[0660] "Activity information" refers to records of transactions conducted by users through financial institutions, purchasing behavior, location data, and information related to lifestyle events.

[0661] A "server" refers to a computing device that collects, processes, and analyzes data, and exchanges information with users and other systems.

[0662] "Integration" refers to the process of combining data collected from multiple sources into a single, unified format.

[0663] "Preprocessing" refers to processes that prepare data for analysis, such as imputing missing values, removing outliers, and standardizing the format.

[0664] An "indicator" refers to a numerical representation of characteristics or features extracted from data to assess a user's credit risk.

[0665] An "estimation algorithm" refers to a set of methods and procedures for evaluating indicators using data analysis techniques and calculating credit scores.

[0666] "Information device" refers to a device or terminal used by users to receive and confirm credit evaluation results.

[0667] A "return loop" refers to a system improvement process that involves readjusting the model based on evaluation results to improve the accuracy of subsequent processing.

[0668] This invention provides a system for efficiently and accurately evaluating the creditworthiness of financial institution users. The server first collects user activity information from financial institutions and external data sources. This activity information includes deposit and withdrawal history, purchasing behavior, location data, and information on lifestyle events. This data is integrated and pre-processed, during which incomplete data is supplemented and outliers are removed. From the information, which is then formatted into a standardized format, the server extracts indicators and executes an estimation algorithm based on these indicators.

[0669] Specifically, the server uses machine learning techniques and leverages generative AI models such as Random Forest and XGBoost to calculate a credit score for each user in real time. This allows for a quantitative evaluation of the user's trustworthiness. For example, users with a stable income and no delays in credit card payments are assigned a high score.

[0670] The credit assessment results are delivered to the terminal, and users can check the assessment results through their information devices. The assessment results include the user's credit score as well as specific advice on how to improve it. For example, it might be presented as, "Your score will increase if you improve your recent credit card payments."

[0671] Furthermore, the server has a feedback loop that compares evaluation results with actual actions to improve the accuracy of the estimation algorithm. This continuous improvement further enhances the reliability of the credit rating.

[0672] An example of a prompt message is, "Calculate this user's credit score and assess the likelihood of loan approval," which utilizes a generative AI model. This prompt allows the system to perform the necessary data processing and provide a specific credit assessment.

[0673] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0674] Step 1:

[0675] The server collects user activity information from financial institutions and external sources. The input data includes deposit and withdrawal history, purchasing behavior, location data, and lifestyle event information. This data is stored in a local database. The output is a raw dataset linked to each user.

[0676] Step 2:

[0677] The server preprocesses the collected raw dataset. It uses medians and means to fill in any incomplete parts of the input data. It also identifies, removes, or corrects outliers. It standardizes the data format and converts it into a format suitable for analysis. The output is a standardized dataset.

[0678] Step 3:

[0679] The server extracts metrics from pre-processed data. Based on the input data, it quantifies specific metrics such as the stability of the user's income and their spending trends. At this stage, a feature selection algorithm is used to extract important metrics. The output is a list of metrics for each user.

[0680] Step 4:

[0681] The server performs credit assessments using a generative AI model. The input is a list of metrics for each user. Machine learning algorithms (e.g., Random Forest or XGBoost) are used to calculate a credit score based on these metrics. The output is an individual credit score for each user.

[0682] Step 5:

[0683] The server delivers the calculated credit score to the terminal. The terminal displays the received credit score to the user. The input is the credit score and its breakdown, and the output is an evaluation interface that the user can review. The user can receive detailed information about their credit score and suggestions for improvement.

[0684] Step 6:

[0685] The server executes a feedback loop, improving the model's accuracy using actual user repayment history and behavioral data. The input consists of historical data and the latest evaluation results. Based on this, the model is retrained and parameters are adjusted. The output is the improved machine learning model.

[0686] (Application Example 1)

[0687] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0688] In electronic payment services, it is difficult to assess a user's credit risk in real time and individually propose the optimal payment method or credit option. Furthermore, conventional credit rating systems cannot effectively combine large amounts of individual purchase history and location data, making them unable to provide specific and useful advice to users. Therefore, it is necessary to conduct credit assessments tailored to users' economic activities and optimize their daily spending.

[0689] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0690] In this invention, the server includes means for collecting transaction data of financial institution users, means for integrating and pre-processing the collected transaction data, and means for extracting characteristics from the transaction data. This makes it possible to perform credit assessments in real time based on the user's purchase history and location information, and to propose the optimal electronic payment method or credit option.

[0691] "Financial institution user" refers to an individual or legal entity that generates transaction data, and that data is generated through a financial institution.

[0692] "Transaction data" is a general term for information related to economic activities, such as deposit and withdrawal history through financial institutions, purchase history, and account transfer details.

[0693] "Means of collection" refers to the processes and functions for collecting and storing data, and this includes various sensors and database technologies.

[0694] "Means of integration and preprocessing" refers to the process of centralizing collected data and converting it into a format suitable for analysis. This includes supplementing incomplete data and removing outliers.

[0695] "Means of extracting characteristics" refers to the process of identifying characteristic elements from data and extracting them in a format usable for analysis.

[0696] A "generative algorithm for credit evaluation" is a computational method or procedure for quantitatively evaluating a user's creditworthiness based on characteristics calculated from transaction data.

[0697] "Means of distribution to information devices" refers to communication processes and functions for providing the generated credit evaluation results in a format accessible to users.

[0698] "Feedback cycle" refers to the process of continuously using data to improve algorithms and enhance the accuracy of evaluations.

[0699] The system for implementing this invention consists of three elements: a server, a terminal, and a user.

[0700] The server first collects transaction data from financial institution users. This transaction data includes users' purchase history and location data. The server integrates and preprocesses this data. Preprocessing includes imputing incomplete data and removing outliers. Next, the server extracts characteristics from the transaction data and applies a generation algorithm to perform credit assessment based on those characteristics. Credit assessment is performed using machine learning techniques to evaluate credit risk in real time.

[0701] The evaluation results are delivered to the user's information device, a terminal, allowing the user to check their credit score. The terminal displays advice and credit suggestions for improving the score through a user interface. Furthermore, through a feedback cycle, the user's actual behavioral data is sent back to the server and used to improve the accuracy of the algorithm.

[0702] As a concrete example, when a user reviews their purchase history, the server displays the user's latest credit score and offers low-interest loans based on that score. These offers also include advice on what purchasing behaviors can contribute to improving the score.

[0703] The generative AI model performs credit assessment using prompts like the following:

[0704] "To perform a credit assessment, please use the following data: Purchase history: [Date, Item, Price], Location information: [Latitude, Longitude], Past credit score: [Date, Score]. Generate advice for the user to improve their future credit score."

[0705] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0706] Step 1:

[0707] The server collects user transaction data from financial institutions and related data sources. This data includes purchase history and location information. The input is raw data, and the output is a well-organized dataset. The server efficiently retrieves data using API calls and stores it in a database.

[0708] Step 2:

[0709] The server integrates and preprocesses the collected data. The input is raw data stored in the database, and the output is clean, preprocessed data. Specifically, it supplements incomplete data, identifies and removes outliers, and standardizes the data format.

[0710] Step 3:

[0711] The server extracts characteristics from pre-processed data. The input is a clean dataset, and the output is a list of extracted characteristics. A machine learning model identifies important characteristics as features, preparing for the next step.

[0712] Step 4:

[0713] The server applies a generative algorithm to perform a credit assessment based on the extracted characteristics. The input is a list of characteristics, and the output is a credit score. Machine learning techniques are used to assess the user's credit risk. The model generates results in real time.

[0714] Step 5:

[0715] The server delivers the generated credit score to the user's device. The input is the generated credit score, and the output is the score displayed on the device. Users can check their own credit information on their device and receive feedback.

[0716] Step 6:

[0717] User behavior data is sent back to the server over time, forming a feedback loop. The input is the user's actual purchasing behavior and payment history, and the output is an improved generation algorithm. This improves the accuracy of credit assessment and ensures that the user's credit score is properly reflected.

[0718] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0719] This invention provides a credit rating system that takes into account the user's emotional state. This system integrates not only transaction information from financial institutions but also user emotional data to achieve a more accurate and personalized credit rating.

[0720] First, the server collects customer transaction information from financial institutions. This transaction information includes account deposit and withdrawal history, card usage records, and purchase history. Simultaneously, the server also collects additional data related to the user's emotional state, such as voice data, behavioral data, and location information.

[0721] Next, this data is integrated and preprocessed. The server analyzes the collected data and uses an emotion engine to determine the user's emotional state. For example, it extracts emotions such as stress and a sense of security from voice data to evaluate the user's everyday psychological state.

[0722] The server then applies a generation algorithm based on a comprehensive set of features, including emotional state, to calculate the user's credit score. This algorithm considers the relationship between the user's economic behavior and emotional state to determine credit risk. For example, a user who is consistently experiencing high stress levels may be considered high-risk because a decrease in their willingness to pay is predicted.

[0723] The calculated credit rating results are delivered to the device for the user to review. The device provides the user with details of their credit score, its breakdown, and how emotional data influenced the rating. For example, it can explain how a large expenditure during a period of high stress affected the credit score.

[0724] Furthermore, the server establishes a feedback loop to continuously improve the accuracy of the algorithm. It monitors the user's actual behavior and emotional changes, and revises the evaluation criteria based on this information. In this way, the system evolves in response to changing times, enabling more accurate user credit assessments.

[0725] This invention incorporates emotion recognition technology into credit evaluation, thereby providing a multifaceted credit scoring system that goes beyond conventional evaluations based on financial information, and improving the quality of financial services.

[0726] The following describes the processing flow.

[0727] Step 1:

[0728] The server securely collects transaction information provided by financial institutions. This data includes transaction history, credit card statements, and loan repayment information, and is retrieved using APIs and secure data transfer protocols.

[0729] Step 2:

[0730] Users record voice and behavioral data on their devices through an emotion recognition application to collect their own emotional data. This includes the tone of voice during conversations and the frequency of specific activities.

[0731] Step 3:

[0732] The server integrates the collected transaction information and sentiment data and preprocesses it into a consistent data format. It then cleans the data, imputing missing information and removing outliers.

[0733] Step 4:

[0734] The server uses an emotion engine to analyze the user's emotional state. It identifies emotions such as stress levels and joy from voice tone and tags the emotional state.

[0735] Step 5:

[0736] The server extracts features based on pre-processed data and sentiment tags. Specifically, features include monthly spending, credit card usage frequency, and the frequency of sentiment tags.

[0737] Step 6:

[0738] The server applies machine learning algorithms to calculate the user's credit score in real time. The algorithms analyze both financial information and sentiment data to assess credit risk.

[0739] Step 7:

[0740] The device displays the evaluation results, including the calculated credit score, in a user interface. Users can check their own score, the impact of their emotional state on their credit rating, and suggestions for improvement.

[0741] Step 8:

[0742] The server tracks users' financial behavior and emotional changes, and runs a feedback loop to improve the model's accuracy. This ensures continuous improvement in evaluation accuracy.

[0743] (Example 2)

[0744] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0745] Traditional credit rating systems primarily rely on economic activity information from financial institutions and do not take into account the emotional state of users, making it impossible to comprehensively assess credit risk. Furthermore, they are unable to perform personalized assessments that utilize the relationship between emotional state and economic behavior, resulting in insufficient accuracy in assessing user creditworthiness.

[0746] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0747] In this invention, the server includes means for collecting economic activity information of financial institution users, means for collecting additional information related to emotional state from users, and means for analyzing emotional state using an emotion engine. This enables a multifaceted and personalized credit assessment that takes emotional state into account.

[0748] A "financial institution" is an organization that provides financial products and services to users, and includes banks, credit unions, securities companies, and others.

[0749] "Users" refers to individuals or corporations that utilize the services of a financial institution.

[0750] "Economic activity information" refers to data such as transaction history, records of expenses and income, and purchasing behavior related to the user's asset management.

[0751] "Emotional state" refers to data that indicates the user's psychological state and mental condition, and is obtained from voice analysis and behavioral patterns.

[0752] "Additional information" refers to non-financial information such as audio data, behavioral data, and location information related to understanding emotional states.

[0753] An "emotion engine" refers to software or technology that analyzes emotions from a user's voice and behavioral patterns and evaluates their psychological impact on economic behavior.

[0754] "Credit rating" refers to the results of an analysis used to determine a user's financial soundness and ability to pay, and is calculated based on integrated data of economic activity and emotional state.

[0755] A "feedback loop" refers to a series of processes that adjust data and algorithms based on evaluation results to improve the accuracy of the generation method.

[0756] The following system is constructed as an embodiment of this invention. The system consists of three main components: a server, a terminal, and a user.

[0757] The server is primarily designed to retrieve users' financial activity information from financial institutions. This information includes account deposit and withdrawal history, credit card usage records, and purchase history. The server also collects additional information related to the user's emotional state. This additional information includes voice data, behavioral data, and location information, obtained from smartphones and wearable devices.

[0758] The server uses an emotion engine to analyze emotional states. This emotion engine incorporates speech analysis and natural language processing technologies to determine emotions such as stress and feelings of security from voice data. This makes it possible to analyze the psychological impact on users' economic behavior.

[0759] The analyzed data is input into a generative AI model to calculate the user's credit score. This model takes into account both economic activity and emotional state to provide a multifaceted and personalized credit assessment. The credit score aims for real-time optimization, and the generative AI model can provide a highly accurate assessment.

[0760] The calculated credit rating results are delivered to the user via the device. The device provides the user with detailed information such as their credit score, its breakdown, and how sentiment data influenced the rating. This allows the user to clearly understand their own credit situation.

[0761] As a concrete example, it is possible to explain how a large expenditure made while under high stress affects a credit score. An example of a prompt would be, "How would a credit score be affected if a user in their 40s indicated stress in recent voice data?"

[0762] This system aims to improve the quality of financial services by providing a new perspective on credit assessment that takes user emotions into account.

[0763] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0764] Step 1:

[0765] The server collects information on users' economic activities from financial institutions.

[0766] Specifically, the system uses APIs to retrieve account deposit and withdrawal history and credit card usage records from financial institutions. The input is financial data received via the API, which is then filtered and converted into a useful format on the server. The output is analyzable economic activity data.

[0767] Step 2:

[0768] The server collects additional information related to the user's emotional state.

[0769] Specifically, the system acquires voice data, behavioral data, and location information through smartphones and wearable devices. The input consists of various sensor data transmitted from the devices, which are then integrated centrally. The output provides additional information necessary for emotional state analysis.

[0770] Step 3:

[0771] The server integrates and preprocesses the collected economic activity information and additional information.

[0772] This includes data cleansing and format conversion, removing inconsistent data and standardizing it. The input is integrated data from various data sources, and the output is a clean dataset that serves as the basis for analysis.

[0773] Step 4:

[0774] The server uses an emotion engine to analyze the emotional state.

[0775] In concrete terms, an algorithm for analyzing audio data assigns emotional labels such as stress and reassurance. The input is pre-processed audio data, and the output is emotional labels indicating the user's psychological state.

[0776] Step 5:

[0777] The server inputs the analysis data into the generating AI model and calculates the user's credit score.

[0778] The algorithm considers the correlation between economic activity and emotional state to assess credit risk. The input is integrated feature data, and the output is each user's credit score.

[0779] Step 6:

[0780] The server delivers the calculated credit rating results to the terminal.

[0781] Specifically, push notifications or emails are used to inform the user of the credit evaluation results on their device. The input is the credit score and its details, and the output is evaluation information formatted for the user.

[0782] Step 7:

[0783] The device visually displays the user's credit score and its breakdown.

[0784] The dashboard uses graphs and charts to intuitively display information, making it easier for users to understand the results. The input is formalized evaluation data, and the output is user-viewable visualized credit rating data.

[0785] Step 8:

[0786] The server executes a feedback loop to improve the generated AI model based on user feedback.

[0787] Specifically, this involves collecting user behavior data and feedback on evaluations to improve the accuracy of the model. The input is feedback data, and the output is the improved generative AI model.

[0788] (Application Example 2)

[0789] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0790] Traditional credit rating systems rely solely on transaction information from financial institutions and cannot accurately reflect the emotions and psychological state of individual users, potentially resulting in insufficient credit assessments. Furthermore, they lack the ability to provide flexible payment advice based on the user's real-time situation.

[0791] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0792] In this invention, the server includes means for collecting transaction information of financial institution customers, means for integrating and preprocessing the collected transaction information and user sentiment data, and means for extracting features from the transaction information and sentiment data. This enables dynamic and accurate credit assessment and real-time payment option suggestions that take into account the user's sentiment state.

[0793] "Means for collecting transaction information of financial institution customers" refers to technologies that obtain customer account activity and purchase history at financial institutions.

[0794] "Means for integrating and preprocessing emotional state data" refers to a process for collecting data related to emotional state, such as user voice data and location information, and converting it into a format suitable for analysis.

[0795] "Methods for extracting features" refer to techniques for identifying meaningful data points that indicate user behavior and psychological state from transaction information and sentiment data.

[0796] "Means of applying a generation algorithm" refers to computational methods that generate user credit ratings and payment options based on collected data.

[0797] "Means of distribution to information terminals" refers to technologies that transmit credit evaluation results and payment proposals to users' devices such as smartphones.

[0798] A "means of implementing a feedback loop" is a process for continuously improving algorithms based on user responses and actions.

[0799] This invention utilizes specific hardware and software to realize a system that provides credit assessment and payment suggestions while taking into account the user's emotional state. A server collects customer transaction information from financial institutions, including data on the user's economic activities. Furthermore, it collects emotional state-related data, such as voice data and location information, using the user's smartphone or wearable device. This involves using an emotion analysis engine, such as the Google Cloud Speech API, to supplement the voice data.

[0800] The server integrates and preprocesses this data to transform it into an analyzable state. Next, it extracts significant features from the data, calculates a credit score using a generative AI model, and generates payment options based on emotional states. This credit score and payment suggestion are delivered to the user's information terminal in real time, allowing the user to view this information and select a payment method on their smartphone.

[0801] Furthermore, the server monitors user behavior and feedback, and uses this information to improve the algorithm. This enables continuously evolving, dynamic credit assessment and payment management. For example, if a user is paying at a cafe they frequent and their voice is low-energy and they seem stressed, the system might suggest a smaller payment.

[0802] An example of a prompt message would be: "Emotional data indicating the user is experiencing stress has been detected from the voice. This user is currently slightly over budget. Please suggest a recommended payment method to provide appropriate financial advice."

[0803] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0804] Step 1:

[0805] The server retrieves user transaction information from financial institutions. This information includes account deposit and withdrawal history and card usage records. The input is transaction information from the financial institution's database, and the output is transaction information in a parseable format. The server imports this data into its internal database and formats it so that it can be used in subsequent processing.

[0806] Step 2:

[0807] The server collects emotional state-related data, such as voice data and location information, from the user's smartphone or wearable device. The input is sensor data from the user's device, and the output is data converted into a format suitable for emotion analysis. The server processes the voice data using an emotion analysis engine such as the Google Cloud Speech API to determine the emotional state.

[0808] Step 3:

[0809] The server integrates and preprocesses the collected transaction information and sentiment data. The inputs are transaction information and sentiment data, and the outputs are features extracted from each of these pieces of information. The server applies a feature extraction algorithm to identify meaningful patterns from the data.

[0810] Step 4:

[0811] The server calculates a user's credit score using a generative AI model based on the extracted features. It also generates payment options based on the user's emotional state. The input is the extracted features, and the output is the credit score and proposed payment options. The server selects the optimal payment method based on the calculated score.

[0812] Step 5:

[0813] The server delivers the calculated credit score and proposed payment options to the user's information terminal. Inputs are the credit score and payment options, and output is a notification to the user's terminal. The user then reviews this information on their smartphone screen.

[0814] Step 6:

[0815] The user reviews the proposed payment options and selects the appropriate method. Input is notification information from the server, and output is the user's selection information. User feedback is sent to the server and used to improve the accuracy of future suggestions.

[0816] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0817] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0818] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0819] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0820] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0821] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0822] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0823] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0824] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0825] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0826] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0827] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0828] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0829] 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.

[0830] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0831] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0832] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0833] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0834] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0835] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0836] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0837] The following is further disclosed regarding the embodiments described above.

[0838] (Claim 1)

[0839] Means for collecting transaction information of financial institution customers,

[0840] Means for integrating and preprocessing collected transaction information,

[0841] A method for extracting features from transaction information,

[0842] A means of applying a generative algorithm that performs credit evaluation based on extracted features,

[0843] A means of delivering credit evaluation results to the customer's information terminal,

[0844] A means of implementing a feedback loop to improve the model based on credit evaluation results,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, which integrates and preprocesses data from multiple information sources, including purchase history, location information, and life event information.

[0848] (Claim 3)

[0849] The system according to claim 1, which uses machine learning technology to analyze features and optimize credit risk in real time.

[0850] "Example 1"

[0851] (Claim 1)

[0852] Means for collecting activity information of financial institution users,

[0853] Means for integrating and preprocessing collected activity information,

[0854] A means of extracting indicators from activity information,

[0855] A means of applying an estimation algorithm that performs credit evaluation based on extracted indicators,

[0856] A means of distributing credit evaluation results to the user's information device,

[0857] A means of executing a return loop to improve the model based on the credit rating results,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, which integrates and preprocesses data from multiple sources, including purchasing behavior, location data, and lifestyle event information.

[0861] (Claim 3)

[0862] The system according to claim 1, which uses data analysis technology to evaluate indicators and optimize credit risk in real time.

[0863] "Application Example 1"

[0864] (Claim 1)

[0865] Means for collecting transaction data of financial institution users,

[0866] Means for integrating and preprocessing collected transaction data,

[0867] A method for extracting characteristics from transaction data,

[0868] A means of applying a generation algorithm that performs credit evaluation based on extracted characteristics,

[0869] A means of distributing credit evaluation results to the user's information device,

[0870] A means of implementing a feedback loop to improve the model based on credit evaluation results,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, which integrates and preprocesses data from multiple sources, including purchase history, location data, and life event data.

[0874] (Claim 3)

[0875] The system according to claim 1, which uses machine learning technology to analyze characteristics and optimize credit risk in real time.

[0876] (Claim 4)

[0877] The system according to claim 1, which dynamically proposes the optimal electronic payment method based on credit evaluation using location data and purchase history.

[0878] "Example 2 of combining an emotion engine"

[0879] (Claim 1)

[0880] Means for collecting information on the economic activities of financial institution users,

[0881] A means of collecting additional information from users related to their emotional state,

[0882] A means for integrating and preprocessing collected economic activity information and emotional state information,

[0883] A means of analyzing emotional states using an emotion engine,

[0884] A means for applying a generation method that performs credit evaluation based on analyzed emotional states and economic activity features,

[0885] A means of delivering credit evaluation results to the user's device,

[0886] A means of executing a feedback loop to improve the generation method based on the credit evaluation results,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, which integrates and preprocesses data from various sources, including purchase history, travel information, and personal important event information.

[0890] (Claim 3)

[0891] The system according to claim 1, which uses machine learning technology to interpret features and optimize credit risk in real time.

[0892] "Application example 2 when combining with an emotional engine"

[0893] (Claim 1)

[0894] Means for collecting transaction information of financial institution customers,

[0895] Means for integrating and preprocessing collected transaction information and user sentiment data,

[0896] A means for extracting features from transaction information and sentiment data,

[0897] A means of applying a generative algorithm that performs credit evaluation based on extracted features and proposes dynamic payment options that take emotional states into consideration,

[0898] A means for delivering credit assessment results and proposed payment options to the customer's information terminal,

[0899] A means of implementing a feedback loop to improve the model based on the proposed payment options and credit assessment results,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, which integrates and preprocesses data from multiple information sources, including purchase history, location information, and voice data.

[0903] (Claim 3)

[0904] The system according to claim 1, which uses machine learning technology to optimize credit risk and payment options based on emotional state in real time. [Explanation of Symbols]

[0905] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting transaction information of financial institution customers, Means for integrating and preprocessing collected transaction information, A method for extracting features from transaction information, A means of applying a generative algorithm that performs credit evaluation based on extracted features, A means of delivering credit evaluation results to the customer's information terminal, A means of implementing a feedback loop to improve the model based on credit evaluation results, A system that includes this.

2. The system according to claim 1, which integrates and preprocesses data from multiple information sources, including purchase history, location information, and life event information.

3. The system according to claim 1, which uses machine learning technology to analyze features and optimize credit risk in real time.

Images