system

Abstract

We provide the system. [Solution] A means for receiving credit information and business status data from users, Means for analyzing the aforementioned credit information and business status data, A means for generating improvement proposals based on analysis results, A means for notifying the user of the aforementioned improvement proposal, A means of receiving user feedback, Means for readjusting the proposed improvements based on the aforementioned feedback, 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 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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

[0006] A "user" is an individual or organization that inputs credit information and business performance data into the system and receives suggestions for improvement.

[0007] "Credit information" refers to data used to assess credit risk, and includes information such as financial data and credit history.

[0008] "Business status data" refers to data related to the business activities of companies and individuals, including information such as the current status and operational flow of review and debt collection processes.

[0009] "Means of analysis" refers to system components that have the function of analyzing credit information and business status data to identify patterns and anomalies.

[0010] A "means for generating improvement plans" refers to a system component that has the function of creating specific action plans based on analysis results, with the aim of improving credit risk management and operational efficiency.

[0011] "Means of notification" refers to system components that have the function of communicating generated improvement suggestions to users, and includes chat tools.

[0012] A "means of receiving feedback" refers to a system component that has the functionality to receive opinions and information from users.

[0013] A "means of readjustment" refers to a system component that has the functionality to modify and update existing improvement proposals based on user feedback.

[0014] "System" refers to the overall technical configuration that includes the means of the present invention. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This 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 Embodiment 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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (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), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage 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.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. Specific embodiments of this system are described in detail below.

[0037] 1. Data input from the user

[0038] User actions:

[0039] Users input historical data on default rates and information about the current state of loan application and collection processes using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current collection process flow.

[0040] 2. Receiving and storing data

[0041] server:

[0042] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[0043] 3. Data Analysis

[0044] server:

[0045] The server analyzes the data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies any shortcomings.

[0046] 4. Generating improvement plans

[0047] server:

[0048] Based on the analysis results, the server generates improvement plans. For example, it might identify specific months when the default rate is high and suggest a special campaign to be implemented during that period, or propose concrete steps for automating debt collection operations.

[0049] 5. Notification of proposed improvements

[0050] Server and user operations:

[0051] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[0052] 6. Receiving Feedback

[0053] User actions:

[0054] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[0055] 7. Readjustments based on feedback

[0056] server:

[0057] The server receives user feedback and readjusts improvement suggestions based on it. It reruns the analysis algorithm and generates new improvement suggestions. For example, it might suggest "holding an online seminar that can be implemented without incurring a budget" as an alternative.

[0058] 8. Re-notification of the revised improvement plan

[0059] Server and user operations:

[0060] The revised improvement plan will be notified to the user again via the chat tool. The user can review the new improvement plan and provide further feedback as needed.

[0061] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, generation and notification of improvement proposals, reception of feedback, and readjustment of improvement proposals. This system enables users to manage their credit flexibly based on their actual needs, thereby reducing bad debt rates and improving operational efficiency.

[0062] The following describes the processing flow.

[0063] Step 1: Data Input

[0064] The user uses a terminal to enter credit information and business status data.

[0065] The user enters details of the default rate and debt collection process for each month into a form on their device and clicks the submit button.

[0066] Step 2: Receiving and saving data

[0067] The server receives data sent by the user.

[0068] The server parses the HTTP request and inserts the received data into the database.

[0069] Step 3: Data Analysis

[0070] The server analyzes credit information and business status data stored in the database.

[0071] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[0072] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[0073] Step 4: Generating improvement plans

[0074] The server generates improvement suggestions based on the analysis results.

[0075] The server generates action plans such as "Consider a special campaign during June-August when the default rate is high."

[0076] Step 5: Notification of proposed improvements

[0077] A chat tool is used to notify users in real time of improvement suggestions generated by the server.

[0078] The server sends improvement suggestions as text messages via the chat API.

[0079] The user reviews the suggested improvements notified within the chat tool.

[0080] Step 6: Receiving Feedback

[0081] Users can input feedback on suggested improvements via their device.

[0082] Users enter specific comments, such as "It's difficult to implement a special campaign due to budget constraints," into a feedback form and submit it.

[0083] Step 7: Receiving and Re-analyzing Feedback

[0084] The server receives feedback sent from the user.

[0085] The server parses the HTTP request and saves the feedback data to the database.

[0086] The server reruns its analysis algorithm to readjust the improvement plan based on the saved feedback.

[0087] Step 8: Re-present the proposed improvement plan.

[0088] The server generates revised suggestions based on the feedback.

[0089] The server generates new improvement suggestions, such as "holding online seminars without incurring any costs," and sends them to the chat tool.

[0090] The user reviews the revised improvement suggestions within the chat tool.

[0091] (Example 1)

[0092] 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."

[0093] The present invention aims to quickly and effectively identify specific risks and problems in the management of users' credit information and business status, and to provide appropriate improvement proposals based on these findings. Furthermore, it aims to provide a more effective management method by receiving feedback from users and making readjustments that reflect that feedback.

[0094] 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.

[0095] In this invention, the server includes means for acquiring credit data and work status data from users, means for storing the credit data and work status data, means for analyzing the data, means for generating improvement proposals based on the analysis results, means for presenting the improvement proposals to users, means for receiving responses from users, and means for redefining the improvement proposals based on the responses. This enables users to manage their accounts flexibly based on their actual needs, allowing them to quickly and effectively reduce bad debt rates and improve operational efficiency.

[0096] A "user" is an entity that operates the system and provides credit data and work status data.

[0097] "Credit data" refers to information about a user's credit status, including time-series data.

[0098] "Work status data" refers to data related to the tasks a user is currently performing, including information about the workflow and efficiency of debt collection tasks.

[0099] A "server" refers to an entire device or system that receives, stores, analyzes, notifies, and provides feedback on data from users.

[0100] "Means of acquisition" refers to mechanisms for collecting credit data and work status data from users. Specifically, this includes terminal interfaces and HTTP requests.

[0101] "Means of storage" refers to storage systems such as databases for saving acquired data.

[0102] "Means of analysis" refers to algorithms and analytical tools used to analyze stored data and detect trends and anomalies.

[0103] "Means for generating improvement proposals" refers to a mechanism that generates suggestions to improve user creditworthiness and operational efficiency based on data analysis results.

[0104] "Means of presentation" refers to a mechanism for informing users of the generated improvement suggestions. Specifically, this includes chat tools and notification systems.

[0105] "Means of receiving responses" refer to mechanisms for receiving feedback and comments from users. Specifically, this includes feedback forms and HTTP requests.

[0106] A "means of redefinition" refers to a mechanism for modifying and recreating improvement plans based on user feedback. This includes analytical algorithms and data analysis processes.

[0107] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. The following describes in detail how this system should be implemented.

[0108] 1. Data input from the user

[0109] The user enters data through the terminal interface. The terminal displays forms for entering historical data on default rates and the current status of credit checks and debt collection operations. For example, if the default rate in January 2022 was 2%, the user enters this value and clicks the submit button.

[0110] 2. Receiving and storing data

[0111] The server receives data sent from the user via HTTP requests. The server parses these requests and extracts the data. Default rate data, for example, is converted into an appropriate format and written to a database (e.g., MySQL®).

[0112] 3. Data Analysis

[0113] The server analyzes the data stored in the database. It uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms to detect trends and outliers. For example, it uses Z-scores for outlier detection.

[0114] 4. Generating improvement plans

[0115] The server generates improvement suggestions based on the results of data analysis. For example, if the default rate was high during a specific period, it will generate a suggestion to implement a special campaign during that period. It also evaluates the efficiency of each step in the debt collection workflow and identifies steps that can be automated.

[0116] 5. Notification of proposed improvements

[0117] The server notifies the user of the generated improvement suggestions. A chat tool (e.g., Slack API) is used for this purpose. The user reviews the suggestions via the chat tool. For example, a message might be sent stating, "The default rate is high from June to August, so increase customer contact frequency during this period."

[0118] 6. Receiving Feedback

[0119] Users provide feedback on suggested improvements. Users enter their feedback into the feedback form on their device and click the submit button. For example, they might comment, "Implementing a special campaign is difficult due to budget constraints."

[0120] 7. Readjustments based on feedback

[0121] The server receives feedback from the user. The server analyzes the feedback, reruns the analysis algorithm, and generates new improvement suggestions. For example, it might suggest an alternative such as "holding an online seminar that can be implemented without incurring a budget."

[0122] 8. Re-notification of the revised improvement plan

[0123] The server will notify the user again of the revised improvement plan via the chat tool. The user can then review the new improvement plan and provide further feedback.

[0124] Examples of specific actions

[0125] The user inputs data on default rates from January to June 2022 and details of the current debt collection workflow. The server receives this data and saves it to the database. It then performs data analysis and generates improvement suggestions, such as, "Due to a sharp increase in default rates in March, special debt collection activities should be intensified during February." The improvement suggestion is notified to the user via a chat tool, and the user responds with feedback such as, "The budget for February has already been allocated." The server receives this feedback and proposes an alternative: "To reduce the budget, intensify non-face-to-face debt collection activities." This improvement suggestion is again notified to the user via the chat tool.

[0126] Example of a prompt

[0127] Analyze customer credit information and business performance data, and generate appropriate improvement plans based on the analysis results obtained from the following databases:

[0128] January 2022: Bad debt rate 2%

[0129] February 2022: Bad debt rate 1.8%

[0130] [Further data...]

[0131] The improvement plan also includes special campaigns and procedures for streamlining debt collection operations.

[0132] As described above, this system efficiently supports users in managing their credit risk.

[0133] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0134] Step 1:

[0135] Users input historical data on default rates and the current status of loan application and collection processes through a terminal interface. Specifically, they enter data such as "January 2022: Default rate 2%, February 2022: Default rate 1.8%" into the input form and click the submit button. The input includes detailed information on default rates and business workflows. The output is the input data sent to the server in JSON format.

[0136] Step 2:

[0137] The server receives data sent from the user via HTTP requests. Specifically, the server parses the request and extracts the data. Default rate data, etc., is converted into an appropriate format and written to a database (e.g., MySQL). The input includes JSON formatted data sent from the user. The output is data saved to the database without delay.

[0138] Step 3:

[0139] The server analyzes data stored in the database. Specifically, the server uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms (e.g., Z-scores) to detect trends and outliers. The input includes default rate data and business flow data stored in the database. The output provides analysis results and generates information on trends and outliers.

[0140] Step 4:

[0141] The server generates improvement suggestions based on the results of data analysis. Specifically, if the default rate is high during a particular period, it will suggest implementing a special campaign during that period or automating business processes. The input includes the results of the data analysis. The output generates specific improvement suggestions (e.g., "Since the default rate is high from June to August, increase the frequency of customer contact during this period").

[0142] Step 5:

[0143] The server notifies the user of the generated improvement suggestions. Specifically, it sends a message containing the improvement suggestions to the user using a chat tool (e.g., Slack API). The input includes the generated improvement suggestions. The output is a notification displayed in the user's chat tool.

[0144] Step 6:

[0145] Users provide feedback on the suggested improvements. Specifically, they enter a comment such as "Implementing a special campaign is difficult due to budget constraints" into the feedback form on their device and click the submit button. The input includes the user's feedback. The output is the feedback content sent to the server.

[0146] Step 7:

[0147] The server receives feedback sent from users. Specifically, it analyzes the feedback content, re-runs the analysis algorithm, and generates new improvement suggestions. For example, it might generate "holding an online seminar that can be implemented without budgeting" as an alternative suggestion. The input includes the feedback received from users. The output is a revised improvement suggestion.

[0148] Step 8:

[0149] The server will notify the user again of the revised improvement plan via the chat tool. The user can review the new improvement plan and provide further feedback. The input will include the revised improvement plan. The output will be the new improvement plan notified to the user.

[0150] (Application Example 1)

[0151] 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."

[0152] Conventional credit management systems have functions to analyze user credit information and business performance data and provide improvement suggestions, but they lack real-time fraud detection and warning functions using transaction data. This creates a risk that fraudulent transactions requiring immediate action may be overlooked. Solving this problem is essential.

[0153] 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.

[0154] In this invention, the server includes means for receiving user credit information and business status data, means for analyzing this data, means for generating improvement plans based on the analysis results, means for notifying the user of the improvement plans, means for receiving feedback from the user, means for readjusting the improvement plans based on the feedback, means for analyzing user transaction data and detecting the possibility of fraudulent transactions, means for generating warnings based on the detected possibility of fraudulent transactions, and means for notifying the user of the warnings in real time. This enables real-time detection and warning of fraudulent transactions simultaneously with credit management, making it possible to take appropriate measures immediately.

[0155] "User credit information" refers to historical data such as each user's past financial transactions and utility bill payments, and is used to assess their creditworthiness and risk.

[0156] "Business status data" refers to information such as the progress, efficiency, and procedures of the tasks that users are currently performing, and this data is used to analyze and improve business processes.

[0157] "Methods for analyzing data" refers to the process of analyzing credit information and business performance data collected from users using algorithms and statistical models to identify important trends and outliers.

[0158] "Means for generating improvement plans" refers to a function that automatically creates specific suggestions and countermeasures to reduce problems and risks faced by users, based on analysis results.

[0159] "Means for notifying users of improvement suggestions" refers to a function for communicating created improvement suggestions to users in real time through electronic means (e.g., chat tools or notification systems).

[0160] "Means of receiving feedback" refers to a function that allows users to input their opinions and comments on suggested improvements into the system and receive them.

[0161] "Methods for readjusting improvement proposals" refers to the process of re-analyzing the received feedback, reviewing the initial improvement proposals, and generating more appropriate suggestions.

[0162] "User transaction data" refers to the individual transaction history of each user related to electronic payments and financial transactions, and this data is used to detect fraudulent transactions.

[0163] "Means for detecting potential fraudulent transactions" refer to algorithms and methods for analyzing user transaction data to identify potentially fraudulent transactions.

[0164] "Warning generation mechanism" refers to a function that automatically creates warning messages to inform users of potential risks based on detected fraudulent transactions.

[0165] "Means of notifying users of warnings in real time" refers to electronic means (e.g., real-time chat notifications) for immediately conveying generated warnings to users.

[0166] This invention relates to a system for enhancing credit information management and fraudulent transaction detection in electronic payment services. This system generates improvement suggestions based on the analysis of user credit information and business status data, and also has the function of detecting potential fraudulent transactions in real time and notifying warnings.

[0167] System Configuration

[0168] 1. Data entry

[0169] User actions:

[0170] Users input credit information, business status data, and transaction data using their smartphones. The interface is built with React Native and Flutter®. This allows users to easily input their past credit history and current transaction information.

[0171] 2. Data reception and storage

[0172] server:

[0173] The server receives input data via a REST API and securely stores it in a database (MySQL or PostgreSQL). The server is built using Flask or Django, which properly parses HTTP requests and writes them to the database.

[0174] 3. Data Analysis

[0175] server:

[0176] The system analyzes credit information, business status data, and transaction data stored in a database. Machine learning libraries such as Sci-kit Learn and TENSORFLOW® are used for the analysis. From the analysis results, trends in credit risk and fraudulent transaction risks at specific time periods are extracted.

[0177] 4. Generating improvement plans

[0178] server:

[0179] Based on the analysis results, the system automatically generates improvement plans to reduce credit risk. These plans can include suggestions for implementing special campaigns during months when specific risks are higher.

[0180] 5. Generating and notifying warnings

[0181] Server and user operations:

[0182] If a transaction with a high probability of being fraudulent is detected, the server immediately generates an alert and sends a real-time notification to your smartphone. The notification uses Twilio or the Slack API. For example, a message such as "The specified transaction is suspicious and requires additional authentication" might be sent.

[0183] 6. Receiving user feedback

[0184] User actions:

[0185] Users provide feedback on suggestions for improvement and warnings through the interface. This feedback is sent to the server.

[0186] 7. Readjustment of the improvement plan

[0187] server:

[0188] Based on feedback received from users, the analysis algorithm is re-executed and improvement suggestions are readjusted. This provides the optimal improvement suggestions tailored to the user's needs and circumstances.

[0189] 8.Renotification

[0190] Server and user operations:

[0191] The user will be notified again with the adjusted improvements and regenerated warnings. The user can then provide feedback again if necessary.

[0192] These processes enable real-time reduction of credit risk and detection of fraudulent transactions, allowing for efficient business operations.

[0193] Specific examples and prompt statements

[0194] Specific example

[0195] Example 1: If a user frequently makes high-value transactions, the system may determine that these transactions are highly likely to be fraudulent, and a notification will be sent recommending additional authentication steps before the transaction.

[0196] Example 2: If a user's transaction history indicates a high credit risk during a specific period, a recommendation will be sent to activate a special monitoring mode during that period.

[0197] Example of a prompt

[0198] Prompt: Analyze the transaction history for the past 6 months and identify patterns that are likely to indicate fraudulent transactions. Based on the results, provide specific countermeasures.

[0199] The above describes specific embodiments for implementing the present invention. The system of the present invention allows users to enjoy flexible credit risk management and fraud prevention measures based on their actual needs.

[0200] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0201] Step 1:

[0202] Users input credit information, business status data, and transaction data through a smartphone interface. The software used is built with React Native or Flutter. The data entered includes past credit history (e.g., credit score and payment history) and current transaction information (e.g., transaction amount and date / time). After input, this data is temporarily stored in the smartphone's memory.

[0203] Step 2:

[0204] Credit information, business status data, and transaction data are sent from the smartphone to the server via a REST API. The server is configured using either Flask or Django. Here, the server parses the HTTP request and stores the received data in a database such as MySQL or PostgreSQL.

[0205] Step 3:

[0206] The server analyzes credit information, business status data, and transaction data stored in the database. Machine learning libraries such as Sci-kit Learn and TensorFlow are used for the analysis. Time series analysis and anomaly detection algorithms are implemented to extract user credit risk trends and potential fraudulent transactions.

[0207] Step 4:

[0208] The server generates improvement suggestions to reduce credit risk based on the analysis results. For example, if there is a tendency for credit risk to increase in a particular month, it will generate a suggestion to implement a special campaign during that month. The generated improvement suggestions are stored on the server.

[0209] Step 5:

[0210] The server detects transactions that are highly likely to be fraudulent based on the analysis results and generates a warning. For example, if a series of high-value transactions occur, the anomaly detection algorithm will be activated and a warning message such as "This transaction is suspicious. Additional authentication is required" will be generated. The warning is stored on the server.

[0211] Step 6:

[0212] The server notifies users in real time of any improvement suggestions and warnings it generates. Twilio and Slack APIs are used for notifications. Users can view improvement suggestions and warnings on their smartphones.

[0213] Step 7:

[0214] Users provide feedback on improvement suggestions and warnings they receive. This feedback is submitted using a smartphone interface.

[0215] Step 8:

[0216] Feedback is sent to the server via a REST API. The server reruns the analysis algorithm based on the received feedback and readjusts the suggested improvements. For example, if a special campaign cannot be implemented due to budget constraints, a new suggestion such as "hold an online seminar" will be generated.

[0217] Step 9:

[0218] The server regenerates revised improvement suggestions and warnings, and notifies the user in real time. The user can then provide further feedback. By repeating this process, the user's credit risk management and fraud prevention are optimized.

[0219] This series of processes allows users to efficiently manage their credit information, detect fraudulent transactions, and take appropriate measures immediately.

[0220] 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.

[0221] This invention relates to a system that analyzes a user's credit information and business performance data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on the user's feedback and emotions. Specific embodiments of this system are described in detail below.

[0222] 1. Data input from the user

[0223] User actions:

[0224] Users input credit information and business status data using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow.

[0225] 2. Receiving and storing data

[0226] server:

[0227] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[0228] 3. Data Analysis

[0229] server:

[0230] The server analyzes credit information and business status data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[0231] 4. Recognition of emotions

[0232] Server (emotion engine):

[0233] The system incorporates an emotion engine to analyze emotions from text data entered by the user. The emotion engine analyzes the user's input and feedback to recognize emotions (e.g., joy, anger, sadness, satisfaction, etc.).

[0234] 5. Generating improvement plans

[0235] server:

[0236] Based on the analysis results and the output of the emotion engine, the server generates improvement suggestions. For example, if the emotion engine detects stress or dissatisfaction from user feedback, it will consider improvement measures corresponding to those emotions. It will generate action plans such as "Consider a special campaign during June-August when the default rate is high."

[0237] 6. Notification of proposed improvements

[0238] Server and user operations:

[0239] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[0240] 7. Receiving feedback and re-recognizing emotions

[0241] User actions:

[0242] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[0243] Server (emotion engine):

[0244] The server receives feedback from the user and analyzes it again using the emotion engine. It monitors changes in the user's emotions and readjusts improvement plans based on the emotional feedback.

[0245] 8. Re-adjustment and re-notification of improvement proposals

[0246] server:

[0247] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending money" and send it to the chat tool.

[0248] User actions:

[0249] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[0250] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, sentiment recognition, generation and notification of improvement suggestions, feedback and sentiment reconfirmation, and readjustment of improvement suggestions. This system enables users to manage their credit flexibly based on their actual needs and emotions, thereby reducing bad debt rates and improving operational efficiency.

[0251] The following describes the processing flow.

[0252] Step 1: Data Input

[0253] The user uses a terminal to enter credit information and business status data.

[0254] For example, the user enters the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow into a form on the terminal and clicks the submit button.

[0255] Step 2: Receiving and saving data

[0256] The server receives data sent by the user.

[0257] The server parses the HTTP request and inserts the received data into the database.

[0258] Step 3: Data Analysis

[0259] The server analyzes credit information and business status data stored in the database.

[0260] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[0261] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[0262] Step 4: Recognizing Emotions

[0263] The server uses an emotion engine to analyze the user's emotions from their text input.

[0264] For example, in response to a user's comment, "Special campaigns are difficult to budget for," the sentiment engine detects "dissatisfaction."

[0265] Step 5: Generating improvement proposals

[0266] The server generates improvement suggestions based on the analysis results and the output of the emotion engine.

[0267] For example, the server might propose "holding an online seminar that can be implemented without incurring a budget" to create improvement plans that address user dissatisfaction.

[0268] Step 6: Notification of proposed improvements

[0269] A chat tool is used to notify users in real time of improvement suggestions generated by the server.

[0270] The server sends improvement suggestions as text messages via the chat API.

[0271] The user reviews the suggested improvements notified within the chat tool.

[0272] Step 7: Receiving feedback and re-evaluating emotions

[0273] Users can input feedback on suggested improvements via their device.

[0274] For example, a user might enter a comment in the feedback form saying, "The online seminar proposal is a good idea, but the date and time don't work for me," and submit it.

[0275] The server receives the feedback and the sentiment engine analyzes it again. For example, it might determine that "the user is satisfied with the comment, but has concerns about the date and time."

[0276] Step 8: Readjust and re-notify the proposed improvements.

[0277] The server generates refined improvement suggestions based on feedback and the output of the emotion engine.

[0278] For example, "Holding online seminars with flexible scheduling options" could be generated as a new improvement suggestion.

[0279] The server sends the revised improvement suggestions to the chat tool for the user to review.

[0280] If users provide further feedback, that feedback will be used to make further adjustments.

[0281] Through these steps, the system of the present invention efficiently and flexibly supports the user's credit risk management by receiving data input from the user, analyzing the data and emotions, generating and notifying improvement suggestions, providing feedback and reassessing emotions, and readjusting the improvement suggestions.

[0282] (Example 2)

[0283] 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".

[0284] Conventional credit information and business management systems lack the appropriate data analysis and readjustment functions to efficiently and flexibly support users' credit risk management. Furthermore, they often unilaterally provide standard improvement suggestions without considering user sentiment, making it difficult to provide optimal solutions tailored to users' specific needs and feelings. This results in users being unable to effectively manage credit risk based on actual business situations and emotions.

[0285] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means.

[0286] In this invention, the server includes means for receiving credit information and business management information from a user, means for storing the credit information and business management information in a database, means for analyzing the credit information and business management information, means for recognizing the user's emotion based on the analysis result, means for generating an improvement plan based on the analysis result and the recognized emotion, means for notifying the user of the improvement plan, means for receiving feedback from the user, and means for readjusting the improvement plan based on the feedback. Thereby, the server can efficiently and flexibly support the credit risk management of the user and provide an optimal solution according to the user's emotion and specific needs.

[0287] "Credit information" is data related to the credit status of a user or a company, and includes information such as the default rate and payment history.

[0288] "Business management information" is data related to the business process and its efficiency performed by a user or a company, and includes the procedure of the business flow and the progress status of tasks.

[0289] "Database" is a system that stores information organizationally and can retrieve it later, and software such as MySQL corresponds to this.

[0290] "Analysis" refers to the operation of finding the meaning, trend, and outliers of data using specific algorithms or methods based on the collected data.

[0291] "Recognizing emotion" means specifying the user's emotion from the text data input by the user using a natural language processing model.

[0292] A "proposal for improvement" refers to a specific action plan or measure proposed to improve user credit risk and operational efficiency based on analysis results and emotion recognition results.

[0293] A "chat tool" is software used for exchanging messages in real time, and examples include Slack and MICROSOFT® TEAMS®.

[0294] "Feedback" refers to specific opinions and comments that users provide regarding suggestions for improvement from the server.

[0295] "Readjustment" is the process of reviewing existing improvement proposals and changing them to more appropriate ones based on feedback received from users and sentiment recognition results.

[0296] This invention is a system that analyzes a user's credit information and business management information, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on the user's feedback and sentiment. Specific embodiments of this system are described in detail below.

[0297] Data input from users

[0298] User actions:

[0299] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate in January 2022 was 2%, and the default rate in February 2022 was 1.8%," and also input the current debt collection workflow.

[0300] Receiving and storing data

[0301] server:

[0302] The server receives the data sent by the user and stores it in the database. Specifically, it analyzes the HTTP request from the terminal, converts the data into an appropriate format, and stores it in the database (e.g., MySQL). After the data is stored, the server sends a confirmation message to the terminal.

[0303] Analysis of data

[0304] Server:

[0305] Retrieve the stored credit information and business management information and perform analysis. Specifically, using a time-series analysis algorithm implemented in Python, plot the past default rate data in a time series to detect outliers and trends. Also, evaluate the efficiency of each step in the current collection process and identify deficiencies.

[0306] Recognition of emotions

[0307] Server (emotion engine):

[0308] The server is equipped with an emotion engine (e.g., natural language processing model) to analyze emotions from the user's input text data. As analysis results, emotions such as "joy," "anger," "sadness," and "satisfaction" are tagged.

[0309] Generation of improvement plans

[0310] Server:

[0311] The server generates improvement plans based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "unease" from the user's feedback, the server considers a specific action plan such as "Implement a special campaign from June to August when the default rate increases."

[0312] Notification of improvement plans

[0313] Operations of the server and the user:

[0314] A chat tool (e.g., Slack, Microsoft Teams) is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. Specifically, a message such as "The default rate is high from June to August, so we suggest increasing the frequency of customer contact during this period" will be displayed.

[0315] Receiving feedback and re-recognizing emotions

[0316] User actions:

[0317] Users provide feedback on the proposed improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[0318] Server (emotion engine):

[0319] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[0320] Re-adjustment and re-notification of improvement proposals

[0321] server:

[0322] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending a budget" and send it to the chat tool.

[0323] User actions:

[0324] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary. The server repeats this process to ensure the user receives the best possible solution.

[0325] Specific examples and prompt statements

[0326] As a concrete example, if a user submits feedback stating, "It's difficult to run a special campaign because the default rate in June is high," the server receives this input and uses its emotion engine to recognize the emotion of "dissatisfaction." Next, the server generates a new improvement suggestion, "Hold an online seminar that can be implemented without incurring a budget," and notifies the user again.

[0327] Examples of prompt statements to input into a generative AI model are as follows:

[0328] "Please propose effective improvement measures for months when the loan default rate is high."

[0329] "Please tell me how to streamline our current debt collection process."

[0330] In this way, the system can efficiently and flexibly support users' credit risk management and provide optimal solutions tailored to users' emotions and specific needs.

[0331] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0332] Step 1:

[0333] User data input

[0334] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate for January 2022 was 2%, and the default rate for February 2022 was 1.8%," and similarly input the current debt collection workflow procedure. This becomes the input data.

[0335] Input: Credit information and business management information (e.g., default rate, business flow procedures)

[0336] Output: HTTP request sent from the terminal

[0337] Step 2:

[0338] Receiving and storing data

[0339] The server receives data sent by the user and stores it in a database. The server parses the HTTP request, converts the data into the appropriate format, and stores it in the database (e.g., MySQL). After saving the data, the server sends a confirmation message to the terminal.

[0340] Specific actions:

[0341] The server parses the HTTP request and extracts credit information and business management information. It then generates and executes an SQL query to write the extracted data to the database.

[0342] Input: HTTP request from terminal (credit information and business management information)

[0343] Output: Credit information and business management information stored in the database, and a confirmation message.

[0344] Step 3:

[0345] Data analysis

[0346] The server retrieves and analyzes stored credit and business management information. Specifically, it uses a time-series analysis algorithm implemented in Python to plot historical default rate data over time and detect outliers and trends. Furthermore, it evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[0347] Specific actions:

[0348] The server retrieves the necessary data from the database and inputs it into a time-series analysis algorithm. Furthermore, an efficiency evaluation model is used for each step in the workflow to analyze the performance of each step.

[0349] Input: Credit information and business management information stored in the database

[0350] Output: Analysis results (anomaly detection, trend analysis, efficiency evaluation)

[0351] Step 4:

[0352] Recognition of emotions

[0353] Server (emotion engine):

[0354] The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's input text data to determine their emotions. The analysis results in emotions such as "joy," "anger," "sadness," and "satisfaction."

[0355] Specific actions:

[0356] The server inputs text data from the user into the sentiment engine, and a natural language processing model analyzes the text and labels it with emotions.

[0357] Input: User's text data

[0358] Output: Sentiment analysis results (sentiment labels)

[0359] Step 5:

[0360] Generating improvement plans

[0361] The server generates improvement suggestions based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "anxiety" from user feedback, it will generate improvement suggestions such as "implement a special campaign during June to August when the default rate is high" as a specific action plan.

[0362] Specific actions:

[0363] The server receives the analysis results and emotion labels as input, and uses prompt sentences to generate improvement suggestions into the AI ​​model. At this time, it determines whether the generated improvement suggestions are best suited to the user's needs.

[0364] Input: Analysis results, emotion labels

[0365] Output: Improvement plan

[0366] Step 6:

[0367] Notification of improvement proposals

[0368] To notify users in real time of improvement suggestions generated by the server, a chat tool (e.g., Slack, Microsoft Teams) is used. Users can review the improvement suggestions through the chat tool and take specific actions.

[0369] Specific actions:

[0370] The server uses the chat tool's API to send the generated improvement suggestions as a message. The user receives and acknowledges the notification in the chat tool.

[0371] Input: Improvement proposal

[0372] Output: Suggestions for improving the message format sent to the user

[0373] Step 7:

[0374] Receiving feedback and re-recognizing emotions

[0375] User actions:

[0376] Users provide feedback on the suggested improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[0377] server:

[0378] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[0379] Specific actions:

[0380] The server parses the feedback, inputs it into the emotion engine for analysis, and then saves the analysis results for use in the next step.

[0381] Input: User feedback

[0382] Output: Feedback analysis results, emotion labels

[0383] Step 8:

[0384] Re-adjustment and re-notification of improvement proposals

[0385] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. Specifically, it generates new improvement suggestions such as "Hold an online seminar that can be conducted without spending a budget" and sends them to the chat tool.

[0386] User:

[0387] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[0388] Specific actions:

[0389] The server incorporates the feedback into its analysis results, inputs new prompts into the generating AI model, and generates a revised improvement plan. The user is then notified again via the chat tool.

[0390] Input: Feedback analysis results, emotion labels

[0391] Output: Revised improvement proposals, re-notified messages

[0392] (Application Example 2)

[0393] 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."

[0394] Conventional credit risk management systems are effective in analyzing user credit information and business performance data to generate improvement plans, but they have the drawback of not being able to consider user emotions and thus failing to adequately reduce user stress and dissatisfaction. Therefore, there is a need to improve the user experience and generate more accurate improvement plans.

[0395] 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. In this invention, the server includes means for receiving credit information and business status data from a user, means for analyzing the credit information and business status data, means for generating improvement proposals based on the analysis results, means for notifying the user of the improvement proposals, means for receiving feedback from the user, means for readjusting the improvement proposals based on the feedback, means for analyzing the sentiment of the user's feedback, and means for generating and notifying improvement proposals based on the sentiment analysis results. This makes it possible to generate and notify highly accurate improvement proposals that take the user's sentiment into consideration.

[0396] "Credit information" refers to data used to assess a user's credit risk, and specifically includes information such as default rates and payment history.

[0397] "Work status data" refers to data used to evaluate the progress and efficiency of a user's work, and specifically includes the progress and procedures of debt collection tasks.

[0398] "Data analysis" refers to the process of analyzing received credit information and business status data using statistical and machine learning methods to identify outliers and trends.

[0399] "Generating improvement plans" refers to devising specific action plans to improve operational efficiency and reduce credit risk, based on data analysis results and user sentiment analysis results.

[0400] "Notification means" refers to a means of communicating generated improvement suggestions to users, and includes chat tools and notification applications.

[0401] "Receiving feedback" refers to collecting opinions and comments that users provide regarding the improvement suggestions they have been notified about.

[0402] "Sentiment analysis" refers to the process of analyzing user feedback and comments using natural language processing technology to identify emotions (such as joy, anger, sadness, satisfaction, etc.).

[0403] "Readjustment" refers to reviewing initial improvement proposals based on user feedback and sentiment analysis results, and generating more appropriate new improvement proposals.

[0404] The system of this invention is designed to support users in managing their credit risk. Specifically, it has the function of analyzing users' credit information and work status data, and generating and notifying improvement suggestions based on user feedback and sentiment analysis results. The detailed configuration for implementing this system is described below.

[0405] Program processing and the hardware / software used

[0406] 1. User data input

[0407] Users input credit information and business performance data using a smartphone app. This data is used to evaluate business efficiency and credit risk. The terminal interface is intuitive and easy to use, for example, by providing input forms and dropdown menus.

[0408] 2. Receiving and storing data

[0409] The terminal sends the entered data to the server, which receives the HTTP request and writes it to the database. This allows for centralized data management.

[0410] 3. Data Analysis

[0411] The server analyzes the received data. Specifically, it uses Python and the Flask framework to identify anomalies and trends from the data using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, making it easy to spot anomalies at a glance.

[0412] 4. Feedback and Recognition of Emotions

[0413] The server receives user feedback and analyzes its content using a sentiment analysis engine (e.g., TextBlob library). It identifies positive and negative emotions from the comments and feedback entered by the user.

[0414] 5. Generating improvement plans

[0415] Based on the analysis results and sentiment analysis results, the server generates improvement suggestions. Using an AI model, it provides concrete and realistic solutions to the user's challenges. Action plans such as "Consider a special campaign during June-August when the default rate is high" are generated.

[0416] 6. Notification of proposed improvements

[0417] The generated improvement suggestions are notified to the user in real time. The notification method uses a chat tool within the smartphone app. Users can check the notification and take action.

[0418] 7. Receiving and readjusting feedback

[0419] The user submits feedback on the suggested improvements. The server receives this feedback and performs sentiment analysis again to understand the user's feelings and opinions. Based on the results, it regenerates and notifies the user of even more appropriate improvement suggestions.

[0420] Examples of specific cases and prompt statements

[0421] For example, if a user provides feedback stating that "implementing the campaign is financially difficult," a process is initiated to generate new improvement proposals based on that feedback. The sentiment analysis engine uses this feedback to understand the user's realistic constraints and proposes a readjusted improvement proposal such as "holding an online seminar that can be implemented without incurring a budget."

[0422] Example of a prompt

[0423] User input: The campaign is a good idea, but it's not practical.

[0424] Prompt to the generated AI: Users rate the campaign as "good" but find it "difficult." Please suggest realistic and actionable improvements.

[0425] In this way, the system analyzes user data from multiple perspectives and provides optimal solutions while considering user sentiment, thereby achieving more effective credit risk management.

[0426] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0427] Step 1:

[0428] Users input credit information and business status data through a terminal interface. This data includes default rates, payment history, and the progress of debt collection efforts. Detailed business data is then transmitted to the server.

[0429] Step 2:

[0430] The server receives data sent by the user and stores it in the database. This process involves parsing the HTTP request and writing the data to the database in the appropriate format. Input data is sent to the server in JSON format and stored in the database.

[0431] Step 3:

[0432] The server analyzes data stored in the database. Specifically, it uses Python and the Flask framework to identify outliers and trends using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, visualizing them so that anomalies can be easily detected.

[0433] Step 4:

[0434] Users input feedback using their devices. This feedback includes suggestions for improvement and expressions of emotion. The user then sends their opinion on the improvement suggestions provided by the system to the server.

[0435] Step 5:

[0436] The server receives user feedback and analyzes its content using an emotion analysis engine. Specifically, it uses the TextBlob library to identify emotions from text data. This analysis extracts positive and negative emotions.

[0437] Step 6:

[0438] The server generates improvement suggestions based on data analysis and sentiment analysis results. Using an AI model, it generates the optimal action plan based on the user's emotions and credit information. For example, if the emotion of the feedback is negative, it will suggest an alternative improvement that is less burdensome.

[0439] Step 7:

[0440] The server notifies users in real time of the improvement suggestions it generates. A chat tool is used for notifications, and users check the notifications on their devices. The chat tool displays specific improvement suggestions to the user.

[0441] Step 8:

[0442] The user submits feedback again using their device. If the suggested improvements are not realistic, new feedback is submitted.

[0443] Step 9:

[0444] The server receives new feedback and performs sentiment analysis again. It monitors changes in sentiment and uses the AI ​​model to readjust existing improvement suggestions. For example, in response to feedback that it is difficult due to budget constraints, new improvement suggestions such as online seminars are generated.

[0445] Step 10:

[0446] The server then notifies the user again of the revised improvement plan. The user then reviews the new improvement plan on their device via the chat tool. This completes the notification of the final improvement plan to the user.

[0447] The input data and feedback are analyzed sequentially, and flexible improvement suggestions that take user sentiment into account are provided, thereby improving operational efficiency and credit risk management.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] [Second Embodiment]

[0452] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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).

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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".

[0464] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. Specific embodiments of this system are described in detail below.

[0465] 1. Data input from the user

[0466] User actions:

[0467] Users input historical data on default rates and information about the current state of loan application and collection processes using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current collection process flow.

[0468] 2. Receiving and storing data

[0469] server:

[0470] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[0471] 3. Data Analysis

[0472] server:

[0473] The server analyzes the data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies any shortcomings.

[0474] 4. Generating improvement plans

[0475] server:

[0476] Based on the analysis results, the server generates improvement plans. For example, it might identify specific months when the default rate is high and suggest a special campaign to be implemented during that period, or propose concrete steps for automating debt collection operations.

[0477] 5. Notification of proposed improvements

[0478] Server and user operations:

[0479] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[0480] 6. Receiving Feedback

[0481] User actions:

[0482] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[0483] 7. Readjustments based on feedback

[0484] server:

[0485] The server receives user feedback and readjusts improvement suggestions based on it. It reruns the analysis algorithm and generates new improvement suggestions. For example, it might suggest "holding an online seminar that can be implemented without incurring a budget" as an alternative.

[0486] 8. Re-notification of the revised improvement plan

[0487] Server and user operations:

[0488] The revised improvement plan will be notified to the user again via the chat tool. The user can review the new improvement plan and provide further feedback as needed.

[0489] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, generation and notification of improvement proposals, reception of feedback, and readjustment of improvement proposals. This system enables users to manage their credit flexibly based on their actual needs, thereby reducing bad debt rates and improving operational efficiency.

[0490] The following describes the processing flow.

[0491] Step 1: Data Input

[0492] The user uses a terminal to enter credit information and business status data.

[0493] The user enters details of the default rate and debt collection process for each month into a form on their device and clicks the submit button.

[0494] Step 2: Receiving and saving data

[0495] The server receives data sent by the user.

[0496] The server parses the HTTP request and inserts the received data into the database.

[0497] Step 3: Data Analysis

[0498] The server analyzes credit information and business status data stored in the database.

[0499] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[0500] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[0501] Step 4: Generating improvement plans

[0502] The server generates improvement suggestions based on the analysis results.

[0503] The server generates action plans such as "Consider a special campaign during June-August when the default rate is high."

[0504] Step 5: Notification of proposed improvements

[0505] A chat tool is used to notify users in real time of improvement suggestions generated by the server.

[0506] The server sends improvement suggestions as text messages via the chat API.

[0507] The user reviews the suggested improvements notified within the chat tool.

[0508] Step 6: Receiving Feedback

[0509] Users can input feedback on suggested improvements via their device.

[0510] Users enter specific comments, such as "It's difficult to implement a special campaign due to budget constraints," into a feedback form and submit it.

[0511] Step 7: Receiving and Re-analyzing Feedback

[0512] The server receives feedback sent from the user.

[0513] The server parses the HTTP request and saves the feedback data to the database.

[0514] The server reruns its analysis algorithm to readjust the improvement plan based on the saved feedback.

[0515] Step 8: Re-present the proposed improvement plan.

[0516] The server generates revised suggestions based on the feedback.

[0517] The server generates new improvement suggestions, such as "holding online seminars without incurring any costs," and sends them to the chat tool.

[0518] The user reviews the revised improvement suggestions within the chat tool.

[0519] (Example 1)

[0520] 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".

[0521] The present invention aims to quickly and effectively identify specific risks and problems in the management of users' credit information and business status, and to provide appropriate improvement proposals based on these findings. Furthermore, it aims to provide a more effective management method by receiving feedback from users and making readjustments that reflect that feedback.

[0522] 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.

[0523] In this invention, the server includes means for acquiring credit data and work status data from users, means for storing the credit data and work status data, means for analyzing the data, means for generating improvement proposals based on the analysis results, means for presenting the improvement proposals to users, means for receiving responses from users, and means for redefining the improvement proposals based on the responses. This enables users to manage their accounts flexibly based on their actual needs, allowing them to quickly and effectively reduce bad debt rates and improve operational efficiency.

[0524] A "user" is an entity that operates the system and provides credit data and work status data.

[0525] "Credit data" refers to information about a user's credit status, including time-series data.

[0526] "Work status data" refers to data related to the tasks a user is currently performing, including information about the workflow and efficiency of debt collection tasks.

[0527] A "server" refers to an entire device or system that receives, stores, analyzes, notifies, and provides feedback on data from users.

[0528] "Means of acquisition" refers to mechanisms for collecting credit data and work status data from users. Specifically, this includes terminal interfaces and HTTP requests.

[0529] "Means of storage" refers to storage systems such as databases for saving acquired data.

[0530] "Means of analysis" refers to algorithms and analytical tools used to analyze stored data and detect trends and anomalies.

[0531] "Means for generating improvement proposals" refers to a mechanism that generates suggestions to improve user creditworthiness and operational efficiency based on data analysis results.

[0532] "Means of presentation" refers to a mechanism for informing users of the generated improvement suggestions. Specifically, this includes chat tools and notification systems.

[0533] "Means of receiving responses" refer to mechanisms for receiving feedback and comments from users. Specifically, this includes feedback forms and HTTP requests.

[0534] A "means of redefinition" refers to a mechanism for modifying and recreating improvement plans based on user feedback. This includes analytical algorithms and data analysis processes.

[0535] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. The following describes in detail how this system should be implemented.

[0536] 1. Data input from the user

[0537] The user enters data through the terminal interface. The terminal displays forms for entering historical data on default rates and the current status of credit checks and debt collection operations. For example, if the default rate in January 2022 was 2%, the user enters this value and clicks the submit button.

[0538] 2. Receiving and storing data

[0539] The server receives data sent from the user via an HTTP request. The server parses this request and extracts the data. Default rate data, for example, is converted to an appropriate format and written to a database (e.g., MySQL).

[0540] 3. Data Analysis

[0541] The server analyzes the data stored in the database. It uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms to detect trends and outliers. For example, it uses Z-scores for outlier detection.

[0542] 4. Generating improvement plans

[0543] The server generates improvement suggestions based on the results of data analysis. For example, if the default rate was high during a specific period, it will generate a suggestion to implement a special campaign during that period. It also evaluates the efficiency of each step in the debt collection workflow and identifies steps that can be automated.

[0544] 5. Notification of proposed improvements

[0545] The server notifies the user of the generated improvement suggestions. A chat tool (e.g., Slack API) is used for this purpose. The user reviews the suggestions via the chat tool. For example, a message might be sent stating, "The default rate is high from June to August, so increase customer contact frequency during this period."

[0546] 6. Receiving Feedback

[0547] Users provide feedback on suggested improvements. Users enter their feedback into the feedback form on their device and click the submit button. For example, they might comment, "Implementing a special campaign is difficult due to budget constraints."

[0548] 7. Readjustments based on feedback

[0549] The server receives feedback from the user. The server analyzes the feedback, reruns the analysis algorithm, and generates new improvement suggestions. For example, it might suggest an alternative such as "holding an online seminar that can be implemented without incurring a budget."

[0550] 8. Re-notification of the revised improvement plan

[0551] The server will notify the user again of the revised improvement plan via the chat tool. The user can then review the new improvement plan and provide further feedback.

[0552] Examples of specific actions

[0553] The user inputs data on default rates from January to June 2022 and details of the current debt collection workflow. The server receives this data and saves it to the database. It then performs data analysis and generates improvement suggestions, such as, "Due to a sharp increase in default rates in March, special debt collection activities should be intensified during February." The improvement suggestion is notified to the user via a chat tool, and the user responds with feedback such as, "The budget for February has already been allocated." The server receives this feedback and proposes an alternative: "To reduce the budget, intensify non-face-to-face debt collection activities." This improvement suggestion is again notified to the user via the chat tool.

[0554] Example of a prompt

[0555] Analyze customer credit information and business performance data, and generate appropriate improvement plans based on the analysis results obtained from the following databases:

[0556] January 2022: Bad debt rate 2%

[0557] February 2022: Bad debt rate 1.8%

[0558] [Further data...]

[0559] The improvement plan also includes special campaigns and procedures for streamlining debt collection operations.

[0560] As described above, this system efficiently supports users in managing their credit risk.

[0561] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0562] Step 1:

[0563] Users input historical data on default rates and the current status of loan application and collection processes through a terminal interface. Specifically, they enter data such as "January 2022: Default rate 2%, February 2022: Default rate 1.8%" into the input form and click the submit button. The input includes detailed information on default rates and business workflows. The output is the input data sent to the server in JSON format.

[0564] Step 2:

[0565] The server receives data sent from the user via HTTP requests. Specifically, the server parses the request and extracts the data. Default rate data, etc., is converted into an appropriate format and written to a database (e.g., MySQL). The input includes JSON formatted data sent from the user. The output is data saved to the database without delay.

[0566] Step 3:

[0567] The server analyzes data stored in the database. Specifically, the server uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms (e.g., Z-scores) to detect trends and outliers. The input includes default rate data and business flow data stored in the database. The output provides analysis results and generates information on trends and outliers.

[0568] Step 4:

[0569] The server generates improvement suggestions based on the results of data analysis. Specifically, if the default rate is high during a particular period, it will suggest implementing a special campaign during that period or automating business processes. The input includes the results of the data analysis. The output generates specific improvement suggestions (e.g., "Since the default rate is high from June to August, increase the frequency of customer contact during this period").

[0570] Step 5:

[0571] The server notifies the user of the generated improvement suggestions. Specifically, it sends a message containing the improvement suggestions to the user using a chat tool (e.g., Slack API). The input includes the generated improvement suggestions. The output is a notification displayed in the user's chat tool.

[0572] Step 6:

[0573] Users provide feedback on the suggested improvements. Specifically, they enter a comment such as "Implementing a special campaign is difficult due to budget constraints" into the feedback form on their device and click the submit button. The input includes the user's feedback. The output is the feedback content sent to the server.

[0574] Step 7:

[0575] The server receives feedback sent from users. Specifically, it analyzes the feedback content, re-runs the analysis algorithm, and generates new improvement suggestions. For example, it might generate "holding an online seminar that can be implemented without budgeting" as an alternative suggestion. The input includes the feedback received from users. The output is a revised improvement suggestion.

[0576] Step 8:

[0577] The server will notify the user again of the revised improvement plan via the chat tool. The user can review the new improvement plan and provide further feedback. The input will include the revised improvement plan. The output will be the new improvement plan notified to the user.

[0578] (Application Example 1)

[0579] 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."

[0580] Conventional credit management systems have functions to analyze user credit information and business performance data and provide improvement suggestions, but they lack real-time fraud detection and warning functions using transaction data. This creates a risk that fraudulent transactions requiring immediate action may be overlooked. Solving this problem is essential.

[0581] 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.

[0582] In this invention, the server includes means for receiving user credit information and business status data, means for analyzing this data, means for generating improvement plans based on the analysis results, means for notifying the user of the improvement plans, means for receiving feedback from the user, means for readjusting the improvement plans based on the feedback, means for analyzing user transaction data and detecting the possibility of fraudulent transactions, means for generating warnings based on the detected possibility of fraudulent transactions, and means for notifying the user of the warnings in real time. This enables real-time detection and warning of fraudulent transactions simultaneously with credit management, making it possible to take appropriate measures immediately.

[0583] "User credit information" refers to historical data such as each user's past financial transactions and utility bill payments, and is used to assess their creditworthiness and risk.

[0584] "Business status data" refers to information such as the progress, efficiency, and procedures of the tasks that users are currently performing, and this data is used to analyze and improve business processes.

[0585] "Methods for analyzing data" refers to the process of analyzing credit information and business performance data collected from users using algorithms and statistical models to identify important trends and outliers.

[0586] "Means for generating improvement plans" refers to a function that automatically creates specific suggestions and countermeasures to reduce problems and risks faced by users, based on analysis results.

[0587] "Means for notifying users of improvement suggestions" refers to a function for communicating created improvement suggestions to users in real time through electronic means (e.g., chat tools or notification systems).

[0588] "Means of receiving feedback" refers to a function that allows users to input their opinions and comments on suggested improvements into the system and receive them.

[0589] "Methods for readjusting improvement proposals" refers to the process of re-analyzing the received feedback, reviewing the initial improvement proposals, and generating more appropriate suggestions.

[0590] "User transaction data" refers to the individual transaction history of each user related to electronic payments and financial transactions, and this data is used to detect fraudulent transactions.

[0591] "Means for detecting potential fraudulent transactions" refer to algorithms and methods for analyzing user transaction data to identify potentially fraudulent transactions.

[0592] "Warning generation mechanism" refers to a function that automatically creates warning messages to inform users of potential risks based on detected fraudulent transactions.

[0593] "Means of notifying users of warnings in real time" refers to electronic means (e.g., real-time chat notifications) for immediately conveying generated warnings to users.

[0594] This invention relates to a system for enhancing credit information management and fraudulent transaction detection in electronic payment services. This system generates improvement suggestions based on the analysis of user credit information and business status data, and also has the function of detecting potential fraudulent transactions in real time and notifying warnings.

[0595] System Configuration

[0596] 1. Data entry

[0597] User actions:

[0598] Users input credit information, business status data, and transaction data using their smartphones. The interface is built with React Native and Flutter. This allows users to easily input their past credit history and current transaction information.

[0599] 2. Data reception and storage

[0600] server:

[0601] The server receives input data via a REST API and securely stores it in a database (MySQL or PostgreSQL). The server is built using Flask or Django, which properly parses HTTP requests and writes them to the database.

[0602] 3. Data Analysis

[0603] server:

[0604] This system analyzes credit information, business status data, and transaction data stored in a database. Machine learning libraries such as Sci-kit Learn and TensorFlow are used for the analysis. From the analysis results, trends in credit risk and fraudulent transaction risks at specific time periods are extracted.

[0605] 4. Generating improvement plans

[0606] server:

[0607] Based on the analysis results, the system automatically generates improvement plans to reduce credit risk. These plans can include suggestions for implementing special campaigns during months when specific risks are higher.

[0608] 5. Generating and notifying warnings

[0609] Server and user operations:

[0610] If a transaction with a high probability of being fraudulent is detected, the server immediately generates an alert and sends a real-time notification to your smartphone. The notification uses Twilio or the Slack API. For example, a message such as "The specified transaction is suspicious and requires additional authentication" might be sent.

[0611] 6. Receiving user feedback

[0612] User actions:

[0613] Users provide feedback on suggestions for improvement and warnings through the interface. This feedback is sent to the server.

[0614] 7. Readjustment of the improvement plan

[0615] server:

[0616] Based on feedback received from users, the analysis algorithm is re-executed and improvement suggestions are readjusted. This provides the optimal improvement suggestions tailored to the user's needs and circumstances.

[0617] 8.Renotification

[0618] Server and user operations:

[0619] The user will be notified again with the adjusted improvements and regenerated warnings. The user can then provide feedback again if necessary.

[0620] These processes enable real-time reduction of credit risk and detection of fraudulent transactions, allowing for efficient business operations.

[0621] Specific examples and prompt statements

[0622] Specific example

[0623] Example 1: If a user frequently makes high-value transactions, the system may determine that these transactions are highly likely to be fraudulent, and a notification will be sent recommending additional authentication steps before the transaction.

[0624] Example 2: If a user's transaction history indicates a high credit risk during a specific period, a recommendation will be sent to activate a special monitoring mode during that period.

[0625] Example of a prompt

[0626] Prompt: Analyze the transaction history for the past 6 months and identify patterns that are likely to indicate fraudulent transactions. Based on the results, provide specific countermeasures.

[0627] The above describes specific embodiments for implementing the present invention. The system of the present invention allows users to enjoy flexible credit risk management and fraud prevention measures based on their actual needs.

[0628] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0629] Step 1:

[0630] Users input credit information, business status data, and transaction data through a smartphone interface. The software used is built with React Native or Flutter. The data entered includes past credit history (e.g., credit score and payment history) and current transaction information (e.g., transaction amount and date / time). After input, this data is temporarily stored in the smartphone's memory.

[0631] Step 2:

[0632] Credit information, business status data, and transaction data are sent from the smartphone to the server via a REST API. The server is configured using either Flask or Django. Here, the server parses the HTTP request and stores the received data in a database such as MySQL or PostgreSQL.

[0633] Step 3:

[0634] The server analyzes credit information, business status data, and transaction data stored in the database. Machine learning libraries such as Sci-kit Learn and TensorFlow are used for the analysis. Time series analysis and anomaly detection algorithms are implemented to extract user credit risk trends and potential fraudulent transactions.

[0635] Step 4:

[0636] The server generates improvement suggestions to reduce credit risk based on the analysis results. For example, if there is a tendency for credit risk to increase in a particular month, it will generate a suggestion to implement a special campaign during that month. The generated improvement suggestions are stored on the server.

[0637] Step 5:

[0638] The server detects transactions that are highly likely to be fraudulent based on the analysis results and generates a warning. For example, if a series of high-value transactions occur, the anomaly detection algorithm will be activated and a warning message such as "This transaction is suspicious. Additional authentication is required" will be generated. The warning is stored on the server.

[0639] Step 6:

[0640] The server notifies users in real time of any improvement suggestions and warnings it generates. Twilio and Slack APIs are used for notifications. Users can view improvement suggestions and warnings on their smartphones.

[0641] Step 7:

[0642] Users provide feedback on improvement suggestions and warnings they receive. This feedback is submitted using a smartphone interface.

[0643] Step 8:

[0644] Feedback is sent to the server via a REST API. The server reruns the analysis algorithm based on the received feedback and readjusts the suggested improvements. For example, if a special campaign cannot be implemented due to budget constraints, a new suggestion such as "hold an online seminar" will be generated.

[0645] Step 9:

[0646] The server regenerates revised improvement suggestions and warnings, and notifies the user in real time. The user can then provide further feedback. By repeating this process, the user's credit risk management and fraud prevention are optimized.

[0647] This series of processes allows users to efficiently manage their credit information, detect fraudulent transactions, and take appropriate measures immediately.

[0648] 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.

[0649] This invention relates to a system that analyzes a user's credit information and business performance data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on the user's feedback and emotions. Specific embodiments of this system are described in detail below.

[0650] 1. Data input from the user

[0651] User actions:

[0652] Users input credit information and business status data using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow.

[0653] 2. Receiving and storing data

[0654] server:

[0655] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[0656] 3. Data Analysis

[0657] server:

[0658] The server analyzes credit information and business status data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[0659] 4. Recognition of emotions

[0660] Server (emotion engine):

[0661] The system incorporates an emotion engine to analyze emotions from text data entered by the user. The emotion engine analyzes the user's input and feedback to recognize emotions (e.g., joy, anger, sadness, satisfaction, etc.).

[0662] 5. Generating improvement plans

[0663] server:

[0664] Based on the analysis results and the output of the emotion engine, the server generates improvement suggestions. For example, if the emotion engine detects stress or dissatisfaction from user feedback, it will consider improvement measures corresponding to those emotions. It will generate action plans such as "Consider a special campaign during June-August when the default rate is high."

[0665] 6. Notification of proposed improvements

[0666] Server and user operations:

[0667] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[0668] 7. Receiving feedback and re-recognizing emotions

[0669] User actions:

[0670] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[0671] Server (emotion engine):

[0672] The server receives feedback from the user and analyzes it again using the emotion engine. It monitors changes in the user's emotions and readjusts improvement plans based on the emotional feedback.

[0673] 8. Re-adjustment and re-notification of improvement proposals

[0674] server:

[0675] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending money" and send it to the chat tool.

[0676] User actions:

[0677] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[0678] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, sentiment recognition, generation and notification of improvement suggestions, feedback and sentiment reconfirmation, and readjustment of improvement suggestions. This system enables users to manage their credit flexibly based on their actual needs and emotions, thereby reducing bad debt rates and improving operational efficiency.

[0679] The following describes the processing flow.

[0680] Step 1: Data Input

[0681] The user uses a terminal to enter credit information and business status data.

[0682] For example, the user enters the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow into a form on the terminal and clicks the submit button.

[0683] Step 2: Receiving and saving data

[0684] The server receives data sent by the user.

[0685] The server parses the HTTP request and inserts the received data into the database.

[0686] Step 3: Data Analysis

[0687] The server analyzes credit information and business status data stored in the database.

[0688] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[0689] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[0690] Step 4: Recognizing Emotions

[0691] The server uses an emotion engine to analyze the user's emotions from their text input.

[0692] For example, in response to a user's comment, "Special campaigns are difficult to budget for," the sentiment engine detects "dissatisfaction."

[0693] Step 5: Generating improvement proposals

[0694] The server generates improvement suggestions based on the analysis results and the output of the emotion engine.

[0695] For example, the server might propose "holding an online seminar that can be implemented without incurring a budget" to create improvement plans that address user dissatisfaction.

[0696] Step 6: Notification of proposed improvements

[0697] A chat tool is used to notify users in real time of improvement suggestions generated by the server.

[0698] The server sends improvement suggestions as text messages via the chat API.

[0699] The user reviews the suggested improvements notified within the chat tool.

[0700] Step 7: Receiving feedback and re-evaluating emotions

[0701] Users can input feedback on suggested improvements via their device.

[0702] For example, a user might enter a comment in the feedback form saying, "The online seminar proposal is a good idea, but the date and time don't work for me," and submit it.

[0703] The server receives the feedback and the sentiment engine analyzes it again. For example, it might determine that "the user is satisfied with the comment, but has concerns about the date and time."

[0704] Step 8: Readjust and re-notify the proposed improvements.

[0705] The server generates refined improvement suggestions based on feedback and the output of the emotion engine.

[0706] For example, "Holding online seminars with flexible scheduling options" could be generated as a new improvement suggestion.

[0707] The server sends the revised improvement suggestions to the chat tool for the user to review.

[0708] If users provide further feedback, that feedback will be used to make further adjustments.

[0709] Through these steps, the system of the present invention efficiently and flexibly supports the user's credit risk management by receiving data input from the user, analyzing the data and emotions, generating and notifying improvement suggestions, providing feedback and reassessing emotions, and readjusting the improvement suggestions.

[0710] (Example 2)

[0711] 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".

[0712] Conventional credit information and business management systems lack the appropriate data analysis and readjustment functions to efficiently and flexibly support users' credit risk management. Furthermore, they often unilaterally provide standard improvement suggestions without considering user sentiment, making it difficult to provide optimal solutions tailored to users' specific needs and feelings. This results in users being unable to effectively manage credit risk based on actual business situations and emotions.

[0713] 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.

[0714] In this invention, the server includes means for receiving credit information and business management information from a user; means for storing the credit information and business management information in a database; means for analyzing the credit information and business management information; means for recognizing the user's emotions based on the analysis results; means for generating improvement proposals based on the analysis results and recognized emotions; means for notifying the user of the improvement proposals; means for receiving feedback from the user; and means for readjusting the improvement proposals based on the feedback. This enables the server to efficiently and flexibly support the user's credit risk management and provide optimal solutions tailored to the user's emotions and specific needs.

[0715] "Credit information" refers to data about the creditworthiness of a user or company, including information such as default rates and payment history.

[0716] "Business management information" refers to data related to the business processes performed by a user or company and their efficiency, including business flow procedures and task progress.

[0717] A "database" is a system that systematically stores information and allows it to be retrieved later; software such as MySQL is an example of this.

[0718] "Analysis" refers to the process of using specific algorithms and methods to identify the meaning, trends, and outliers of collected data.

[0719] "Recognizing emotions" means using a natural language processing model to identify the user's emotions from the text data they input.

[0720] A "proposal for improvement" refers to a specific action plan or measure proposed to improve user credit risk and operational efficiency based on analysis results and emotion recognition results.

[0721] A "chat tool" is software used for exchanging messages in real time; examples include Slack and Microsoft Teams.

[0722] "Feedback" refers to specific opinions and comments that users provide regarding suggestions for improvement from the server.

[0723] "Readjustment" is the process of reviewing existing improvement proposals and changing them to more appropriate ones based on feedback received from users and sentiment recognition results.

[0724] This invention is a system that analyzes a user's credit information and business management information, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on the user's feedback and sentiment. Specific embodiments of this system are described in detail below.

[0725] Data input from users

[0726] User actions:

[0727] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate in January 2022 was 2%, and the default rate in February 2022 was 1.8%," and also input the current debt collection workflow.

[0728] Receiving and storing data

[0729] server:

[0730] The server receives data sent by the user and stores it in a database. Specifically, it parses the HTTP request from the terminal, converts the data into the appropriate format, and stores it in the database (e.g., MySQL). After the data is saved, the server sends a confirmation message to the terminal.

[0731] Data analysis

[0732] server:

[0733] The system retrieves and analyzes stored credit and business management information. Specifically, it uses a time-series analysis algorithm implemented in Python to plot historical default rate data over time and detect outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[0734] Recognition of emotions

[0735] Server (emotion engine):

[0736] The server is equipped with an emotion engine (e.g., a natural language processing model) that analyzes emotions from the user's input text data. As a result of the analysis, emotions such as "joy," "anger," "sadness," and "satisfaction" are tagged.

[0737] Generating improvement plans

[0738] server:

[0739] The server generates improvement suggestions based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "anxiety" from user feedback, the server will consider specific action plans such as "implement a special campaign during June to August when the default rate is high."

[0740] Notification of improvement proposals

[0741] Server and user operations:

[0742] A chat tool (e.g., Slack, Microsoft Teams) is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. Specifically, a message such as "The default rate is high from June to August, so we suggest increasing the frequency of customer contact during this period" will be displayed.

[0743] Receiving feedback and re-recognizing emotions

[0744] User actions:

[0745] Users provide feedback on the proposed improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[0746] Server (emotion engine):

[0747] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[0748] Re-adjustment and re-notification of improvement proposals

[0749] server:

[0750] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending a budget" and send it to the chat tool.

[0751] User actions:

[0752] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary. The server repeats this process to ensure the user receives the best possible solution.

[0753] Specific examples and prompt statements

[0754] As a concrete example, if a user submits feedback stating, "It's difficult to run a special campaign because the default rate in June is high," the server receives this input and uses its emotion engine to recognize the emotion of "dissatisfaction." Next, the server generates a new improvement suggestion, "Hold an online seminar that can be implemented without incurring a budget," and notifies the user again.

[0755] Examples of prompt statements to input into a generative AI model are as follows:

[0756] "Please propose effective improvement measures for months when the loan default rate is high."

[0757] "Please tell me how to streamline our current debt collection process."

[0758] In this way, the system can efficiently and flexibly support users' credit risk management and provide optimal solutions tailored to users' emotions and specific needs.

[0759] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0760] Step 1:

[0761] User data input

[0762] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate for January 2022 was 2%, and the default rate for February 2022 was 1.8%," and similarly input the current debt collection workflow procedure. This becomes the input data.

[0763] Input: Credit information and business management information (e.g., default rate, business flow procedures)

[0764] Output: HTTP request sent from the terminal

[0765] Step 2:

[0766] Receiving and storing data

[0767] The server receives data sent by the user and stores it in a database. The server parses the HTTP request, converts the data into the appropriate format, and stores it in the database (e.g., MySQL). After saving the data, the server sends a confirmation message to the terminal.

[0768] Specific actions:

[0769] The server parses the HTTP request and extracts credit information and business management information. It then generates and executes an SQL query to write the extracted data to the database.

[0770] Input: HTTP request from terminal (credit information and business management information)

[0771] Output: Credit information and business management information stored in the database, and a confirmation message.

[0772] Step 3:

[0773] Data analysis

[0774] The server retrieves and analyzes stored credit and business management information. Specifically, it uses a time-series analysis algorithm implemented in Python to plot historical default rate data over time and detect outliers and trends. Furthermore, it evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[0775] Specific actions:

[0776] The server retrieves the necessary data from the database and inputs it into a time-series analysis algorithm. Furthermore, an efficiency evaluation model is used for each step in the workflow to analyze the performance of each step.

[0777] Input: Credit information and business management information stored in the database

[0778] Output: Analysis results (anomaly detection, trend analysis, efficiency evaluation)

[0779] Step 4:

[0780] Recognition of emotions

[0781] Server (emotion engine):

[0782] The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's input text data to determine their emotions. The analysis results in emotions such as "joy," "anger," "sadness," and "satisfaction."

[0783] Specific actions:

[0784] The server inputs text data from the user into the sentiment engine, and a natural language processing model analyzes the text and labels it with emotions.

[0785] Input: User's text data

[0786] Output: Sentiment analysis results (sentiment labels)

[0787] Step 5:

[0788] Generating improvement plans

[0789] The server generates improvement suggestions based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "anxiety" from user feedback, it will generate improvement suggestions such as "implement a special campaign during June to August when the default rate is high" as a specific action plan.

[0790] Specific actions:

[0791] The server receives the analysis results and emotion labels as input, and uses prompt sentences to generate improvement suggestions into the AI ​​model. At this time, it determines whether the generated improvement suggestions are best suited to the user's needs.

[0792] Input: Analysis results, emotion labels

[0793] Output: Improvement plan

[0794] Step 6:

[0795] Notification of improvement proposals

[0796] To notify users in real time of improvement suggestions generated by the server, a chat tool (e.g., Slack, Microsoft Teams) is used. Users can review the improvement suggestions through the chat tool and take specific actions.

[0797] Specific actions:

[0798] The server uses the chat tool's API to send the generated improvement suggestions as a message. The user receives and acknowledges the notification in the chat tool.

[0799] Input: Improvement proposal

[0800] Output: Suggestions for improving the message format sent to the user

[0801] Step 7:

[0802] Receiving feedback and re-recognizing emotions

[0803] User actions:

[0804] Users provide feedback on the suggested improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[0805] server:

[0806] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[0807] Specific actions:

[0808] The server parses the feedback, inputs it into the emotion engine for analysis, and then saves the analysis results for use in the next step.

[0809] Input: User feedback

[0810] Output: Feedback analysis results, emotion labels

[0811] Step 8:

[0812] Re-adjustment and re-notification of improvement proposals

[0813] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. Specifically, it generates new improvement suggestions such as "Hold an online seminar that can be conducted without spending a budget" and sends them to the chat tool.

[0814] User:

[0815] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[0816] Specific actions:

[0817] The server incorporates the feedback into its analysis results, inputs new prompts into the generating AI model, and generates a revised improvement plan. The user is then notified again via the chat tool.

[0818] Input: Feedback analysis results, emotion labels

[0819] Output: Revised improvement proposals, re-notified messages

[0820] (Application Example 2)

[0821] 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."

[0822] Conventional credit risk management systems are effective in analyzing user credit information and business performance data to generate improvement plans, but they have the drawback of not being able to consider user emotions and thus failing to adequately reduce user stress and dissatisfaction. Therefore, there is a need to improve the user experience and generate more accurate improvement plans.

[0823] 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. In this invention, the server includes means for receiving credit information and business status data from a user, means for analyzing the credit information and business status data, means for generating improvement proposals based on the analysis results, means for notifying the user of the improvement proposals, means for receiving feedback from the user, means for readjusting the improvement proposals based on the feedback, means for analyzing the sentiment of the user's feedback, and means for generating and notifying improvement proposals based on the sentiment analysis results. This makes it possible to generate and notify highly accurate improvement proposals that take the user's sentiment into consideration.

[0824] "Credit information" refers to data used to assess a user's credit risk, and specifically includes information such as default rates and payment history.

[0825] "Work status data" refers to data used to evaluate the progress and efficiency of a user's work, and specifically includes the progress and procedures of debt collection tasks.

[0826] "Data analysis" refers to the process of analyzing received credit information and business status data using statistical and machine learning methods to identify outliers and trends.

[0827] "Generating improvement plans" refers to devising specific action plans to improve operational efficiency and reduce credit risk, based on data analysis results and user sentiment analysis results.

[0828] "Notification means" refers to a means of communicating generated improvement suggestions to users, and includes chat tools and notification applications.

[0829] "Receiving feedback" refers to collecting opinions and comments that users provide regarding the improvement suggestions they have been notified about.

[0830] "Sentiment analysis" refers to the process of analyzing user feedback and comments using natural language processing technology to identify emotions (such as joy, anger, sadness, satisfaction, etc.).

[0831] "Readjustment" refers to reviewing initial improvement proposals based on user feedback and sentiment analysis results, and generating more appropriate new improvement proposals.

[0832] The system of this invention is designed to support users in managing their credit risk. Specifically, it has the function of analyzing users' credit information and work status data, and generating and notifying improvement suggestions based on user feedback and sentiment analysis results. The detailed configuration for implementing this system is described below.

[0833] Program processing and the hardware / software used

[0834] 1. User data input

[0835] Users input credit information and business performance data using a smartphone app. This data is used to evaluate business efficiency and credit risk. The terminal interface is intuitive and easy to use, for example, by providing input forms and dropdown menus.

[0836] 2. Receiving and storing data

[0837] The terminal sends the entered data to the server, which receives the HTTP request and writes it to the database. This allows for centralized data management.

[0838] 3. Data Analysis

[0839] The server analyzes the received data. Specifically, it uses Python and the Flask framework to identify anomalies and trends from the data using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, making it easy to spot anomalies at a glance.

[0840] 4. Feedback and Recognition of Emotions

[0841] The server receives user feedback and analyzes its content using a sentiment analysis engine (e.g., TextBlob library). It identifies positive and negative emotions from the comments and feedback entered by the user.

[0842] 5. Generating improvement plans

[0843] Based on the analysis results and sentiment analysis results, the server generates improvement suggestions. Using an AI model, it provides concrete and realistic solutions to the user's challenges. Action plans such as "Consider a special campaign during June-August when the default rate is high" are generated.

[0844] 6. Notification of proposed improvements

[0845] The generated improvement suggestions are notified to the user in real time. The notification method uses a chat tool within the smartphone app. Users can check the notification and take action.

[0846] 7. Receiving and readjusting feedback

[0847] The user submits feedback on the suggested improvements. The server receives this feedback and performs sentiment analysis again to understand the user's feelings and opinions. Based on the results, it regenerates and notifies the user of even more appropriate improvement suggestions.

[0848] Examples of specific cases and prompt statements

[0849] For example, if a user provides feedback stating that "implementing the campaign is financially difficult," a process is initiated to generate new improvement proposals based on that feedback. The sentiment analysis engine uses this feedback to understand the user's realistic constraints and proposes a readjusted improvement proposal such as "holding an online seminar that can be implemented without incurring a budget."

[0850] Example of a prompt

[0851] User input: The campaign is a good idea, but it's not practical.

[0852] Prompt to the generated AI: Users rate the campaign as "good" but find it "difficult." Please suggest realistic and actionable improvements.

[0853] In this way, the system analyzes user data from multiple perspectives and provides optimal solutions while considering user sentiment, thereby achieving more effective credit risk management.

[0854] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0855] Step 1:

[0856] Users input credit information and business status data through a terminal interface. This data includes default rates, payment history, and the progress of debt collection efforts. Detailed business data is then transmitted to the server.

[0857] Step 2:

[0858] The server receives data sent by the user and stores it in the database. This process involves parsing the HTTP request and writing the data to the database in the appropriate format. Input data is sent to the server in JSON format and stored in the database.

[0859] Step 3:

[0860] The server analyzes data stored in the database. Specifically, it uses Python and the Flask framework to identify outliers and trends using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, visualizing them so that anomalies can be easily detected.

[0861] Step 4:

[0862] Users input feedback using their devices. This feedback includes suggestions for improvement and expressions of emotion. The user then sends their opinion on the improvement suggestions provided by the system to the server.

[0863] Step 5:

[0864] The server receives user feedback and analyzes its content using an emotion analysis engine. Specifically, it uses the TextBlob library to identify emotions from text data. This analysis extracts positive and negative emotions.

[0865] Step 6:

[0866] The server generates improvement suggestions based on data analysis and sentiment analysis results. Using an AI model, it generates the optimal action plan based on the user's emotions and credit information. For example, if the emotion of the feedback is negative, it will suggest an alternative improvement that is less burdensome.

[0867] Step 7:

[0868] The server notifies users in real time of the improvement suggestions it generates. A chat tool is used for notifications, and users check the notifications on their devices. The chat tool displays specific improvement suggestions to the user.

[0869] Step 8:

[0870] The user submits feedback again using their device. If the suggested improvements are not realistic, new feedback is submitted.

[0871] Step 9:

[0872] The server receives new feedback and performs sentiment analysis again. It monitors changes in sentiment and uses the AI ​​model to readjust existing improvement suggestions. For example, in response to feedback that it is difficult due to budget constraints, new improvement suggestions such as online seminars are generated.

[0873] Step 10:

[0874] The server then notifies the user again of the revised improvement plan. The user then reviews the new improvement plan on their device via the chat tool. This completes the notification of the final improvement plan to the user.

[0875] The input data and feedback are analyzed sequentially, and flexible improvement suggestions that take user sentiment into account are provided, thereby improving operational efficiency and credit risk management.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] [Third Embodiment]

[0880] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0881] 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.

[0882] 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).

[0883] 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.

[0884] 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.

[0885] 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).

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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".

[0892] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. Specific embodiments of this system are described in detail below.

[0893] 1. Data input from the user

[0894] User actions:

[0895] Users input historical data on default rates and information about the current state of loan application and collection processes using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current collection process flow.

[0896] 2. Receiving and storing data

[0897] server:

[0898] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[0899] 3. Data Analysis

[0900] server:

[0901] The server analyzes the data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies any shortcomings.

[0902] 4. Generating improvement plans

[0903] server:

[0904] Based on the analysis results, the server generates improvement plans. For example, it might identify specific months when the default rate is high and suggest a special campaign to be implemented during that period, or propose concrete steps for automating debt collection operations.

[0905] 5. Notification of proposed improvements

[0906] Server and user operations:

[0907] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[0908] 6. Receiving Feedback

[0909] User actions:

[0910] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[0911] 7. Readjustments based on feedback

[0912] server:

[0913] The server receives user feedback and readjusts improvement suggestions based on it. It reruns the analysis algorithm and generates new improvement suggestions. For example, it might suggest "holding an online seminar that can be implemented without incurring a budget" as an alternative.

[0914] 8. Re-notification of the revised improvement plan

[0915] Server and user operations:

[0916] The revised improvement plan will be notified to the user again via the chat tool. The user can review the new improvement plan and provide further feedback as needed.

[0917] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, generation and notification of improvement proposals, reception of feedback, and readjustment of improvement proposals. This system enables users to manage their credit flexibly based on their actual needs, thereby reducing bad debt rates and improving operational efficiency.

[0918] The following describes the processing flow.

[0919] Step 1: Data Input

[0920] The user uses a terminal to enter credit information and business status data.

[0921] The user enters details of the default rate and debt collection process for each month into a form on their device and clicks the submit button.

[0922] Step 2: Receiving and saving data

[0923] The server receives data sent by the user.

[0924] The server parses the HTTP request and inserts the received data into the database.

[0925] Step 3: Data Analysis

[0926] The server analyzes credit information and business status data stored in the database.

[0927] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[0928] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[0929] Step 4: Generating improvement plans

[0930] The server generates improvement suggestions based on the analysis results.

[0931] The server generates action plans such as "Consider a special campaign during June-August when the default rate is high."

[0932] Step 5: Notification of proposed improvements

[0933] A chat tool is used to notify users in real time of improvement suggestions generated by the server.

[0934] The server sends improvement suggestions as text messages via the chat API.

[0935] The user reviews the suggested improvements notified within the chat tool.

[0936] Step 6: Receiving Feedback

[0937] Users can input feedback on suggested improvements via their device.

[0938] Users enter specific comments, such as "It's difficult to implement a special campaign due to budget constraints," into a feedback form and submit it.

[0939] Step 7: Receiving and Re-analyzing Feedback

[0940] The server receives feedback sent from the user.

[0941] The server parses the HTTP request and saves the feedback data to the database.

[0942] The server reruns its analysis algorithm to readjust the improvement plan based on the saved feedback.

[0943] Step 8: Re-present the proposed improvement plan.

[0944] The server generates revised suggestions based on the feedback.

[0945] The server generates new improvement suggestions, such as "holding online seminars without incurring any costs," and sends them to the chat tool.

[0946] The user reviews the revised improvement suggestions within the chat tool.

[0947] (Example 1)

[0948] 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."

[0949] The present invention aims to quickly and effectively identify specific risks and problems in the management of users' credit information and business status, and to provide appropriate improvement proposals based on these findings. Furthermore, it aims to provide a more effective management method by receiving feedback from users and making readjustments that reflect that feedback.

[0950] 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.

[0951] In this invention, the server includes means for acquiring credit data and work status data from users, means for storing the credit data and work status data, means for analyzing the data, means for generating improvement proposals based on the analysis results, means for presenting the improvement proposals to users, means for receiving responses from users, and means for redefining the improvement proposals based on the responses. This enables users to manage their accounts flexibly based on their actual needs, allowing them to quickly and effectively reduce bad debt rates and improve operational efficiency.

[0952] A "user" is an entity that operates the system and provides credit data and work status data.

[0953] "Credit data" refers to information about a user's credit status, including time-series data.

[0954] "Work status data" refers to data related to the tasks a user is currently performing, including information about the workflow and efficiency of debt collection tasks.

[0955] A "server" refers to an entire device or system that receives, stores, analyzes, notifies, and provides feedback on data from users.

[0956] "Means of acquisition" refers to mechanisms for collecting credit data and work status data from users. Specifically, this includes terminal interfaces and HTTP requests.

[0957] "Means of storage" refers to storage systems such as databases for saving acquired data.

[0958] "Means of analysis" refers to algorithms and analytical tools used to analyze stored data and detect trends and anomalies.

[0959] "Means for generating improvement proposals" refers to a mechanism that generates suggestions to improve user creditworthiness and operational efficiency based on data analysis results.

[0960] "Means of presentation" refers to a mechanism for informing users of the generated improvement suggestions. Specifically, this includes chat tools and notification systems.

[0961] "Means of receiving responses" refer to mechanisms for receiving feedback and comments from users. Specifically, this includes feedback forms and HTTP requests.

[0962] A "means of redefinition" refers to a mechanism for modifying and recreating improvement plans based on user feedback. This includes analytical algorithms and data analysis processes.

[0963] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. The following describes in detail how this system should be implemented.

[0964] 1. Data input from the user

[0965] The user enters data through the terminal interface. The terminal displays forms for entering historical data on default rates and the current status of credit checks and debt collection operations. For example, if the default rate in January 2022 was 2%, the user enters this value and clicks the submit button.

[0966] 2. Receiving and storing data

[0967] The server receives data sent from the user via an HTTP request. The server parses this request and extracts the data. Default rate data, for example, is converted to an appropriate format and written to a database (e.g., MySQL).

[0968] 3. Data Analysis

[0969] The server analyzes the data stored in the database. It uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms to detect trends and outliers. For example, it uses Z-scores for outlier detection.

[0970] 4. Generating improvement plans

[0971] The server generates improvement suggestions based on the results of data analysis. For example, if the default rate was high during a specific period, it will generate a suggestion to implement a special campaign during that period. It also evaluates the efficiency of each step in the debt collection workflow and identifies steps that can be automated.

[0972] 5. Notification of proposed improvements

[0973] The server notifies the user of the generated improvement suggestions. A chat tool (e.g., Slack API) is used for this purpose. The user reviews the suggestions via the chat tool. For example, a message might be sent stating, "The default rate is high from June to August, so increase customer contact frequency during this period."

[0974] 6. Receiving Feedback

[0975] Users provide feedback on suggested improvements. Users enter their feedback into the feedback form on their device and click the submit button. For example, they might comment, "Implementing a special campaign is difficult due to budget constraints."

[0976] 7. Readjustments based on feedback

[0977] The server receives feedback from the user. The server analyzes the feedback, reruns the analysis algorithm, and generates new improvement suggestions. For example, it might suggest an alternative such as "holding an online seminar that can be implemented without incurring a budget."

[0978] 8. Re-notification of the revised improvement plan

[0979] The server will notify the user again of the revised improvement plan via the chat tool. The user can then review the new improvement plan and provide further feedback.

[0980] Examples of specific actions

[0981] The user inputs data on default rates from January to June 2022 and details of the current debt collection workflow. The server receives this data and saves it to the database. It then performs data analysis and generates improvement suggestions, such as, "Due to a sharp increase in default rates in March, special debt collection activities should be intensified during February." The improvement suggestion is notified to the user via a chat tool, and the user responds with feedback such as, "The budget for February has already been allocated." The server receives this feedback and proposes an alternative: "To reduce the budget, intensify non-face-to-face debt collection activities." This improvement suggestion is again notified to the user via the chat tool.

[0982] Example of a prompt

[0983] Analyze customer credit information and business performance data, and generate appropriate improvement plans based on the analysis results obtained from the following databases:

[0984] January 2022: Bad debt rate 2%

[0985] February 2022: Bad debt rate 1.8%

[0986] [Further data...]

[0987] The improvement plan also includes special campaigns and procedures for streamlining debt collection operations.

[0988] As described above, this system efficiently supports users in managing their credit risk.

[0989] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0990] Step 1:

[0991] Users input historical data on default rates and the current status of loan application and collection processes through a terminal interface. Specifically, they enter data such as "January 2022: Default rate 2%, February 2022: Default rate 1.8%" into the input form and click the submit button. The input includes detailed information on default rates and business workflows. The output is the input data sent to the server in JSON format.

[0992] Step 2:

[0993] The server receives data sent from the user via HTTP requests. Specifically, the server parses the request and extracts the data. Default rate data, etc., is converted into an appropriate format and written to a database (e.g., MySQL). The input includes JSON formatted data sent from the user. The output is data saved to the database without delay.

[0994] Step 3:

[0995] The server analyzes data stored in the database. Specifically, the server uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms (e.g., Z-scores) to detect trends and outliers. The input includes default rate data and business flow data stored in the database. The output provides analysis results and generates information on trends and outliers.

[0996] Step 4:

[0997] The server generates improvement suggestions based on the results of data analysis. Specifically, if the default rate is high during a particular period, it will suggest implementing a special campaign during that period or automating business processes. The input includes the results of the data analysis. The output generates specific improvement suggestions (e.g., "Since the default rate is high from June to August, increase the frequency of customer contact during this period").

[0998] Step 5:

[0999] The server notifies the user of the generated improvement suggestions. Specifically, it sends a message containing the improvement suggestions to the user using a chat tool (e.g., Slack API). The input includes the generated improvement suggestions. The output is a notification displayed in the user's chat tool.

[1000] Step 6:

[1001] Users provide feedback on the suggested improvements. Specifically, they enter a comment such as "Implementing a special campaign is difficult due to budget constraints" into the feedback form on their device and click the submit button. The input includes the user's feedback. The output is the feedback content sent to the server.

[1002] Step 7:

[1003] The server receives feedback sent from users. Specifically, it analyzes the feedback content, re-runs the analysis algorithm, and generates new improvement suggestions. For example, it might generate "holding an online seminar that can be implemented without budgeting" as an alternative suggestion. The input includes the feedback received from users. The output is a revised improvement suggestion.

[1004] Step 8:

[1005] The server will notify the user again of the revised improvement plan via the chat tool. The user can review the new improvement plan and provide further feedback. The input will include the revised improvement plan. The output will be the new improvement plan notified to the user.

[1006] (Application Example 1)

[1007] 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."

[1008] Conventional credit management systems have functions to analyze user credit information and business performance data and provide improvement suggestions, but they lack real-time fraud detection and warning functions using transaction data. This creates a risk that fraudulent transactions requiring immediate action may be overlooked. Solving this problem is essential.

[1009] 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.

[1010] In this invention, the server includes means for receiving user credit information and business status data, means for analyzing this data, means for generating improvement plans based on the analysis results, means for notifying the user of the improvement plans, means for receiving feedback from the user, means for readjusting the improvement plans based on the feedback, means for analyzing user transaction data and detecting the possibility of fraudulent transactions, means for generating warnings based on the detected possibility of fraudulent transactions, and means for notifying the user of the warnings in real time. This enables real-time detection and warning of fraudulent transactions simultaneously with credit management, making it possible to take appropriate measures immediately.

[1011] "User credit information" refers to historical data such as each user's past financial transactions and utility bill payments, and is used to assess their creditworthiness and risk.

[1012] "Business status data" refers to information such as the progress, efficiency, and procedures of the tasks that users are currently performing, and this data is used to analyze and improve business processes.

[1013] "Methods for analyzing data" refers to the process of analyzing credit information and business performance data collected from users using algorithms and statistical models to identify important trends and outliers.

[1014] "Means for generating improvement plans" refers to a function that automatically creates specific suggestions and countermeasures to reduce problems and risks faced by users, based on analysis results.

[1015] "Means for notifying users of improvement suggestions" refers to a function for communicating created improvement suggestions to users in real time through electronic means (e.g., chat tools or notification systems).

[1016] "Means of receiving feedback" refers to a function that allows users to input their opinions and comments on suggested improvements into the system and receive them.

[1017] "Methods for readjusting improvement proposals" refers to the process of re-analyzing the received feedback, reviewing the initial improvement proposals, and generating more appropriate suggestions.

[1018] "User transaction data" refers to the individual transaction history of each user related to electronic payments and financial transactions, and this data is used to detect fraudulent transactions.

[1019] "Means for detecting potential fraudulent transactions" refer to algorithms and methods for analyzing user transaction data to identify potentially fraudulent transactions.

[1020] "Warning generation mechanism" refers to a function that automatically creates warning messages to inform users of potential risks based on detected fraudulent transactions.

[1021] "Means of notifying users of warnings in real time" refers to electronic means (e.g., real-time chat notifications) for immediately conveying generated warnings to users.

[1022] This invention relates to a system for enhancing credit information management and fraudulent transaction detection in electronic payment services. This system generates improvement suggestions based on the analysis of user credit information and business status data, and also has the function of detecting potential fraudulent transactions in real time and notifying warnings.

[1023] System Configuration

[1024] 1. Data entry

[1025] User actions:

[1026] Users input credit information, business status data, and transaction data using their smartphones. The interface is built with React Native and Flutter. This allows users to easily input their past credit history and current transaction information.

[1027] 2. Data reception and storage

[1028] server:

[1029] The server receives input data via a REST API and securely stores it in a database (MySQL or PostgreSQL). The server is built using Flask or Django, which properly parses HTTP requests and writes them to the database.

[1030] 3. Data Analysis

[1031] server:

[1032] This system analyzes credit information, business status data, and transaction data stored in a database. Machine learning libraries such as Sci-kit Learn and TensorFlow are used for the analysis. From the analysis results, trends in credit risk and fraudulent transaction risks at specific time periods are extracted.

[1033] 4. Generating improvement plans

[1034] server:

[1035] Based on the analysis results, the system automatically generates improvement plans to reduce credit risk. These plans can include suggestions for implementing special campaigns during months when specific risks are higher.

[1036] 5. Generating and notifying warnings

[1037] Server and user operations:

[1038] If a transaction with a high probability of being fraudulent is detected, the server immediately generates an alert and sends a real-time notification to your smartphone. The notification uses Twilio or the Slack API. For example, a message such as "The specified transaction is suspicious and requires additional authentication" might be sent.

[1039] 6. Receiving user feedback

[1040] User actions:

[1041] Users provide feedback on suggestions for improvement and warnings through the interface. This feedback is sent to the server.

[1042] 7. Readjustment of the improvement plan

[1043] server:

[1044] Based on feedback received from users, the analysis algorithm is re-executed and improvement suggestions are readjusted. This provides the optimal improvement suggestions tailored to the user's needs and circumstances.

[1045] 8.Renotification

[1046] Server and user operations:

[1047] The user will be notified again with the adjusted improvements and regenerated warnings. The user can then provide feedback again if necessary.

[1048] These processes enable real-time reduction of credit risk and detection of fraudulent transactions, allowing for efficient business operations.

[1049] Specific examples and prompt statements

[1050] Specific example

[1051] Example 1: If a user frequently makes high-value transactions, the system may determine that these transactions are highly likely to be fraudulent, and a notification will be sent recommending additional authentication steps before the transaction.

[1052] Example 2: If a user's transaction history indicates a high credit risk during a specific period, a recommendation will be sent to activate a special monitoring mode during that period.

[1053] Example of a prompt

[1054] Prompt: Analyze the transaction history for the past 6 months and identify patterns that are likely to indicate fraudulent transactions. Based on the results, provide specific countermeasures.

[1055] The above describes specific embodiments for implementing the present invention. The system of the present invention allows users to enjoy flexible credit risk management and fraud prevention measures based on their actual needs.

[1056] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1057] Step 1:

[1058] Users input credit information, business status data, and transaction data through a smartphone interface. The software used is built with React Native or Flutter. The data entered includes past credit history (e.g., credit score and payment history) and current transaction information (e.g., transaction amount and date / time). After input, this data is temporarily stored in the smartphone's memory.

[1059] Step 2:

[1060] Credit information, business status data, and transaction data are sent from the smartphone to the server via a REST API. The server is configured using either Flask or Django. Here, the server parses the HTTP request and stores the received data in a database such as MySQL or PostgreSQL.

[1061] Step 3:

[1062] The server analyzes credit information, business status data, and transaction data stored in the database. Machine learning libraries such as Sci-kit Learn and TensorFlow are used for the analysis. Time series analysis and anomaly detection algorithms are implemented to extract user credit risk trends and potential fraudulent transactions.

[1063] Step 4:

[1064] The server generates improvement suggestions to reduce credit risk based on the analysis results. For example, if there is a tendency for credit risk to increase in a particular month, it will generate a suggestion to implement a special campaign during that month. The generated improvement suggestions are stored on the server.

[1065] Step 5:

[1066] The server detects transactions that are highly likely to be fraudulent based on the analysis results and generates a warning. For example, if a series of high-value transactions occur, the anomaly detection algorithm will be activated and a warning message such as "This transaction is suspicious. Additional authentication is required" will be generated. The warning is stored on the server.

[1067] Step 6:

[1068] The server notifies users in real time of any improvement suggestions and warnings it generates. Twilio and Slack APIs are used for notifications. Users can view improvement suggestions and warnings on their smartphones.

[1069] Step 7:

[1070] Users provide feedback on improvement suggestions and warnings they receive. This feedback is submitted using a smartphone interface.

[1071] Step 8:

[1072] Feedback is sent to the server via a REST API. The server reruns the analysis algorithm based on the received feedback and readjusts the suggested improvements. For example, if a special campaign cannot be implemented due to budget constraints, a new suggestion such as "hold an online seminar" will be generated.

[1073] Step 9:

[1074] The server regenerates revised improvement suggestions and warnings, and notifies the user in real time. The user can then provide further feedback. By repeating this process, the user's credit risk management and fraud prevention are optimized.

[1075] This series of processes allows users to efficiently manage their credit information, detect fraudulent transactions, and take appropriate measures immediately.

[1076] 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.

[1077] This invention relates to a system that analyzes a user's credit information and business performance data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on the user's feedback and emotions. Specific embodiments of this system are described in detail below.

[1078] 1. Data input from the user

[1079] User actions:

[1080] Users input credit information and business status data using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow.

[1081] 2. Receiving and storing data

[1082] server:

[1083] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[1084] 3. Data Analysis

[1085] server:

[1086] The server analyzes credit information and business status data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[1087] 4. Recognition of emotions

[1088] Server (emotion engine):

[1089] The system incorporates an emotion engine to analyze emotions from text data entered by the user. The emotion engine analyzes the user's input and feedback to recognize emotions (e.g., joy, anger, sadness, satisfaction, etc.).

[1090] 5. Generating improvement plans

[1091] server:

[1092] Based on the analysis results and the output of the emotion engine, the server generates improvement suggestions. For example, if the emotion engine detects stress or dissatisfaction from user feedback, it will consider improvement measures corresponding to those emotions. It will generate action plans such as "Consider a special campaign during June-August when the default rate is high."

[1093] 6. Notification of proposed improvements

[1094] Server and user operations:

[1095] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[1096] 7. Receiving feedback and re-recognizing emotions

[1097] User actions:

[1098] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[1099] Server (emotion engine):

[1100] The server receives feedback from the user and analyzes it again using the emotion engine. It monitors changes in the user's emotions and readjusts improvement plans based on the emotional feedback.

[1101] 8. Re-adjustment and re-notification of improvement proposals

[1102] server:

[1103] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending money" and send it to the chat tool.

[1104] User actions:

[1105] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[1106] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, sentiment recognition, generation and notification of improvement suggestions, feedback and sentiment reconfirmation, and readjustment of improvement suggestions. This system enables users to manage their credit flexibly based on their actual needs and emotions, thereby reducing bad debt rates and improving operational efficiency.

[1107] The following describes the processing flow.

[1108] Step 1: Data Input

[1109] The user uses a terminal to enter credit information and business status data.

[1110] For example, the user enters the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow into a form on the terminal and clicks the submit button.

[1111] Step 2: Receiving and saving data

[1112] The server receives data sent by the user.

[1113] The server parses the HTTP request and inserts the received data into the database.

[1114] Step 3: Data Analysis

[1115] The server analyzes credit information and business status data stored in the database.

[1116] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[1117] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[1118] Step 4: Recognizing Emotions

[1119] The server uses an emotion engine to analyze the user's emotions from their text input.

[1120] For example, in response to a user's comment, "Special campaigns are difficult to budget for," the sentiment engine detects "dissatisfaction."

[1121] Step 5: Generating improvement proposals

[1122] The server generates improvement suggestions based on the analysis results and the output of the emotion engine.

[1123] For example, the server might propose "holding an online seminar that can be implemented without incurring a budget" to create improvement plans that address user dissatisfaction.

[1124] Step 6: Notification of proposed improvements

[1125] A chat tool is used to notify users in real time of improvement suggestions generated by the server.

[1126] The server sends improvement suggestions as text messages via the chat API.

[1127] The user reviews the suggested improvements notified within the chat tool.

[1128] Step 7: Receiving feedback and re-evaluating emotions

[1129] Users can input feedback on suggested improvements via their device.

[1130] For example, a user might enter a comment in the feedback form saying, "The online seminar proposal is a good idea, but the date and time don't work for me," and submit it.

[1131] The server receives the feedback and the sentiment engine analyzes it again. For example, it might determine that "the user is satisfied with the comment, but has concerns about the date and time."

[1132] Step 8: Readjust and re-notify the proposed improvements.

[1133] The server generates refined improvement suggestions based on feedback and the output of the emotion engine.

[1134] For example, "Holding online seminars with flexible scheduling options" could be generated as a new improvement suggestion.

[1135] The server sends the revised improvement suggestions to the chat tool for the user to review.

[1136] If users provide further feedback, that feedback will be used to make further adjustments.

[1137] Through these steps, the system of the present invention efficiently and flexibly supports the user's credit risk management by receiving data input from the user, analyzing the data and emotions, generating and notifying improvement suggestions, providing feedback and reassessing emotions, and readjusting the improvement suggestions.

[1138] (Example 2)

[1139] 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."

[1140] Conventional credit information and business management systems lack the appropriate data analysis and readjustment functions to efficiently and flexibly support users' credit risk management. Furthermore, they often unilaterally provide standard improvement suggestions without considering user sentiment, making it difficult to provide optimal solutions tailored to users' specific needs and feelings. This results in users being unable to effectively manage credit risk based on actual business situations and emotions.

[1141] 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.

[1142] In this invention, the server includes means for receiving credit information and business management information from a user; means for storing the credit information and business management information in a database; means for analyzing the credit information and business management information; means for recognizing the user's emotions based on the analysis results; means for generating improvement proposals based on the analysis results and recognized emotions; means for notifying the user of the improvement proposals; means for receiving feedback from the user; and means for readjusting the improvement proposals based on the feedback. This enables the server to efficiently and flexibly support the user's credit risk management and provide optimal solutions tailored to the user's emotions and specific needs.

[1143] "Credit information" refers to data about the creditworthiness of a user or company, including information such as default rates and payment history.

[1144] "Business management information" refers to data related to the business processes performed by a user or company and their efficiency, including business flow procedures and task progress.

[1145] A "database" is a system that systematically stores information and allows it to be retrieved later; software such as MySQL is an example of this.

[1146] "Analysis" refers to the process of using specific algorithms and methods to identify the meaning, trends, and outliers of collected data.

[1147] "Recognizing emotions" means using a natural language processing model to identify the user's emotions from the text data they input.

[1148] A "proposal for improvement" refers to a specific action plan or measure proposed to improve user credit risk and operational efficiency based on analysis results and emotion recognition results.

[1149] A "chat tool" is software used for exchanging messages in real time; examples include Slack and Microsoft Teams.

[1150] "Feedback" refers to specific opinions and comments that users provide regarding suggestions for improvement from the server.

[1151] "Readjustment" is the process of reviewing existing improvement proposals and changing them to more appropriate ones based on feedback received from users and sentiment recognition results.

[1152] This invention is a system that analyzes a user's credit information and business management information, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on the user's feedback and sentiment. Specific embodiments of this system are described in detail below.

[1153] Data input from users

[1154] User actions:

[1155] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate in January 2022 was 2%, and the default rate in February 2022 was 1.8%," and also input the current debt collection workflow.

[1156] Receiving and storing data

[1157] server:

[1158] The server receives data sent by the user and stores it in a database. Specifically, it parses the HTTP request from the terminal, converts the data into the appropriate format, and stores it in the database (e.g., MySQL). After the data is saved, the server sends a confirmation message to the terminal.

[1159] Data analysis

[1160] server:

[1161] The system retrieves and analyzes stored credit and business management information. Specifically, it uses a time-series analysis algorithm implemented in Python to plot historical default rate data over time and detect outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[1162] Recognition of emotions

[1163] Server (emotion engine):

[1164] The server is equipped with an emotion engine (e.g., a natural language processing model) that analyzes emotions from the user's input text data. As a result of the analysis, emotions such as "joy," "anger," "sadness," and "satisfaction" are tagged.

[1165] Generating improvement plans

[1166] server:

[1167] The server generates improvement suggestions based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "anxiety" from user feedback, the server will consider specific action plans such as "implement a special campaign during June to August when the default rate is high."

[1168] Notification of improvement proposals

[1169] Server and user operations:

[1170] A chat tool (e.g., Slack, Microsoft Teams) is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. Specifically, a message such as "The default rate is high from June to August, so we suggest increasing the frequency of customer contact during this period" will be displayed.

[1171] Receiving feedback and re-recognizing emotions

[1172] User actions:

[1173] Users provide feedback on the proposed improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[1174] Server (emotion engine):

[1175] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[1176] Re-adjustment and re-notification of improvement proposals

[1177] server:

[1178] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending a budget" and send it to the chat tool.

[1179] User actions:

[1180] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary. The server repeats this process to ensure the user receives the best possible solution.

[1181] Specific examples and prompt statements

[1182] As a concrete example, if a user submits feedback stating, "It's difficult to run a special campaign because the default rate in June is high," the server receives this input and uses its emotion engine to recognize the emotion of "dissatisfaction." Next, the server generates a new improvement suggestion, "Hold an online seminar that can be implemented without incurring a budget," and notifies the user again.

[1183] Examples of prompt statements to input into a generative AI model are as follows:

[1184] "Please propose effective improvement measures for months when the loan default rate is high."

[1185] "Please tell me how to streamline our current debt collection process."

[1186] In this way, the system can efficiently and flexibly support users' credit risk management and provide optimal solutions tailored to users' emotions and specific needs.

[1187] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1188] Step 1:

[1189] User data input

[1190] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate for January 2022 was 2%, and the default rate for February 2022 was 1.8%," and similarly input the current debt collection workflow procedure. This becomes the input data.

[1191] Input: Credit information and business management information (e.g., default rate, business flow procedures)

[1192] Output: HTTP request sent from the terminal

[1193] Step 2:

[1194] Receiving and storing data

[1195] The server receives data sent by the user and stores it in a database. The server parses the HTTP request, converts the data into the appropriate format, and stores it in the database (e.g., MySQL). After saving the data, the server sends a confirmation message to the terminal.

[1196] Specific actions:

[1197] The server parses the HTTP request and extracts credit information and business management information. It then generates and executes an SQL query to write the extracted data to the database.

[1198] Input: HTTP request from terminal (credit information and business management information)

[1199] Output: Credit information and business management information stored in the database, and a confirmation message.

[1200] Step 3:

[1201] Data analysis

[1202] The server retrieves and analyzes stored credit and business management information. Specifically, it uses a time-series analysis algorithm implemented in Python to plot historical default rate data over time and detect outliers and trends. Furthermore, it evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[1203] Specific actions:

[1204] The server retrieves the necessary data from the database and inputs it into a time-series analysis algorithm. Furthermore, an efficiency evaluation model is used for each step in the workflow to analyze the performance of each step.

[1205] Input: Credit information and business management information stored in the database

[1206] Output: Analysis results (anomaly detection, trend analysis, efficiency evaluation)

[1207] Step 4:

[1208] Recognition of emotions

[1209] Server (emotion engine):

[1210] The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's input text data to determine their emotions. The analysis results in emotions such as "joy," "anger," "sadness," and "satisfaction."

[1211] Specific actions:

[1212] The server inputs text data from the user into the sentiment engine, and a natural language processing model analyzes the text and labels it with emotions.

[1213] Input: User's text data

[1214] Output: Sentiment analysis results (sentiment labels)

[1215] Step 5:

[1216] Generating improvement plans

[1217] The server generates improvement suggestions based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "anxiety" from user feedback, it will generate improvement suggestions such as "implement a special campaign during June to August when the default rate is high" as a specific action plan.

[1218] Specific actions:

[1219] The server receives the analysis results and emotion labels as input, and uses prompt sentences to generate improvement suggestions into the AI ​​model. At this time, it determines whether the generated improvement suggestions are best suited to the user's needs.

[1220] Input: Analysis results, emotion labels

[1221] Output: Improvement plan

[1222] Step 6:

[1223] Notification of improvement proposals

[1224] To notify users in real time of improvement suggestions generated by the server, a chat tool (e.g., Slack, Microsoft Teams) is used. Users can review the improvement suggestions through the chat tool and take specific actions.

[1225] Specific actions:

[1226] The server uses the chat tool's API to send the generated improvement suggestions as a message. The user receives and acknowledges the notification in the chat tool.

[1227] Input: Improvement proposal

[1228] Output: Suggestions for improving the message format sent to the user

[1229] Step 7:

[1230] Receiving feedback and re-recognizing emotions

[1231] User actions:

[1232] Users provide feedback on the suggested improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[1233] server:

[1234] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[1235] Specific actions:

[1236] The server parses the feedback, inputs it into the emotion engine for analysis, and then saves the analysis results for use in the next step.

[1237] Input: User feedback

[1238] Output: Feedback analysis results, emotion labels

[1239] Step 8:

[1240] Re-adjustment and re-notification of improvement proposals

[1241] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. Specifically, it generates new improvement suggestions such as "Hold an online seminar that can be conducted without spending a budget" and sends them to the chat tool.

[1242] User:

[1243] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[1244] Specific actions:

[1245] The server incorporates the feedback into its analysis results, inputs new prompts into the generating AI model, and generates a revised improvement plan. The user is then notified again via the chat tool.

[1246] Input: Feedback analysis results, emotion labels

[1247] Output: Revised improvement proposals, re-notified messages

[1248] (Application Example 2)

[1249] 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."

[1250] Conventional credit risk management systems are effective in analyzing user credit information and business performance data to generate improvement plans, but they have the drawback of not being able to consider user emotions and thus failing to adequately reduce user stress and dissatisfaction. Therefore, there is a need to improve the user experience and generate more accurate improvement plans.

[1251] 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. In this invention, the server includes means for receiving credit information and business status data from a user, means for analyzing the credit information and business status data, means for generating improvement proposals based on the analysis results, means for notifying the user of the improvement proposals, means for receiving feedback from the user, means for readjusting the improvement proposals based on the feedback, means for analyzing the sentiment of the user's feedback, and means for generating and notifying improvement proposals based on the sentiment analysis results. This makes it possible to generate and notify highly accurate improvement proposals that take the user's sentiment into consideration.

[1252] "Credit information" refers to data used to assess a user's credit risk, and specifically includes information such as default rates and payment history.

[1253] "Work status data" refers to data used to evaluate the progress and efficiency of a user's work, and specifically includes the progress and procedures of debt collection tasks.

[1254] "Data analysis" refers to the process of analyzing received credit information and business status data using statistical and machine learning methods to identify outliers and trends.

[1255] "Generating improvement plans" refers to devising specific action plans to improve operational efficiency and reduce credit risk, based on data analysis results and user sentiment analysis results.

[1256] "Notification means" refers to a means of communicating generated improvement suggestions to users, and includes chat tools and notification applications.

[1257] "Receiving feedback" refers to collecting opinions and comments that users provide regarding the improvement suggestions they have been notified about.

[1258] "Sentiment analysis" refers to the process of analyzing user feedback and comments using natural language processing technology to identify emotions (such as joy, anger, sadness, satisfaction, etc.).

[1259] "Readjustment" refers to reviewing initial improvement proposals based on user feedback and sentiment analysis results, and generating more appropriate new improvement proposals.

[1260] The system of this invention is designed to support users in managing their credit risk. Specifically, it has the function of analyzing users' credit information and work status data, and generating and notifying improvement suggestions based on user feedback and sentiment analysis results. The detailed configuration for implementing this system is described below.

[1261] Program processing and the hardware / software used

[1262] 1. User data input

[1263] Users input credit information and business performance data using a smartphone app. This data is used to evaluate business efficiency and credit risk. The terminal interface is intuitive and easy to use, for example, by providing input forms and dropdown menus.

[1264] 2. Receiving and storing data

[1265] The terminal sends the entered data to the server, which receives the HTTP request and writes it to the database. This allows for centralized data management.

[1266] 3. Data Analysis

[1267] The server analyzes the received data. Specifically, it uses Python and the Flask framework to identify anomalies and trends from the data using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, making it easy to spot anomalies at a glance.

[1268] 4. Feedback and Recognition of Emotions

[1269] The server receives user feedback and analyzes its content using a sentiment analysis engine (e.g., TextBlob library). It identifies positive and negative emotions from the comments and feedback entered by the user.

[1270] 5. Generating improvement plans

[1271] Based on the analysis results and sentiment analysis results, the server generates improvement suggestions. Using an AI model, it provides concrete and realistic solutions to the user's challenges. Action plans such as "Consider a special campaign during June-August when the default rate is high" are generated.

[1272] 6. Notification of proposed improvements

[1273] The generated improvement suggestions are notified to the user in real time. The notification method uses a chat tool within the smartphone app. Users can check the notification and take action.

[1274] 7. Receiving and readjusting feedback

[1275] The user submits feedback on the suggested improvements. The server receives this feedback and performs sentiment analysis again to understand the user's feelings and opinions. Based on the results, it regenerates and notifies the user of even more appropriate improvement suggestions.

[1276] Examples of specific cases and prompt statements

[1277] For example, if a user provides feedback stating that "implementing the campaign is financially difficult," a process is initiated to generate new improvement proposals based on that feedback. The sentiment analysis engine uses this feedback to understand the user's realistic constraints and proposes a readjusted improvement proposal such as "holding an online seminar that can be implemented without incurring a budget."

[1278] Example of a prompt

[1279] User input: The campaign is a good idea, but it's not practical.

[1280] Prompt to the generated AI: Users rate the campaign as "good" but find it "difficult." Please suggest realistic and actionable improvements.

[1281] In this way, the system analyzes user data from multiple perspectives and provides optimal solutions while considering user sentiment, thereby achieving more effective credit risk management.

[1282] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1283] Step 1:

[1284] Users input credit information and business status data through a terminal interface. This data includes default rates, payment history, and the progress of debt collection efforts. Detailed business data is then transmitted to the server.

[1285] Step 2:

[1286] The server receives data sent by the user and stores it in the database. This process involves parsing the HTTP request and writing the data to the database in the appropriate format. Input data is sent to the server in JSON format and stored in the database.

[1287] Step 3:

[1288] The server analyzes data stored in the database. Specifically, it uses Python and the Flask framework to identify outliers and trends using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, visualizing them so that anomalies can be easily detected.

[1289] Step 4:

[1290] Users input feedback using their devices. This feedback includes suggestions for improvement and expressions of emotion. The user then sends their opinion on the improvement suggestions provided by the system to the server.

[1291] Step 5:

[1292] The server receives user feedback and analyzes its content using an emotion analysis engine. Specifically, it uses the TextBlob library to identify emotions from text data. This analysis extracts positive and negative emotions.

[1293] Step 6:

[1294] The server generates improvement suggestions based on data analysis and sentiment analysis results. Using an AI model, it generates the optimal action plan based on the user's emotions and credit information. For example, if the emotion of the feedback is negative, it will suggest an alternative improvement that is less burdensome.

[1295] Step 7:

[1296] The server notifies users in real time of the improvement suggestions it generates. A chat tool is used for notifications, and users check the notifications on their devices. The chat tool displays specific improvement suggestions to the user.

[1297] Step 8:

[1298] The user submits feedback again using their device. If the suggested improvements are not realistic, new feedback is submitted.

[1299] Step 9:

[1300] The server receives new feedback and performs sentiment analysis again. It monitors changes in sentiment and uses the AI ​​model to readjust existing improvement suggestions. For example, in response to feedback that it is difficult due to budget constraints, new improvement suggestions such as online seminars are generated.

[1301] Step 10:

[1302] The server then notifies the user again of the revised improvement plan. The user then reviews the new improvement plan on their device via the chat tool. This completes the notification of the final improvement plan to the user.

[1303] The input data and feedback are analyzed sequentially, and flexible improvement suggestions that take user sentiment into account are provided, thereby improving operational efficiency and credit risk management.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] [Fourth Embodiment]

[1308] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1309] 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.

[1310] 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).

[1311] 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.

[1312] The microphone 238 receives voice signals from the user 20 and accepts 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.

[1313] 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).

[1314] 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.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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.

[1319] 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.

[1320] 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".

[1321] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. Specific embodiments of this system are described in detail below.

[1322] 1. Data input from the user

[1323] User actions:

[1324] Users input historical data on default rates and information about the current state of loan application and collection processes using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current collection process flow.

[1325] 2. Receiving and storing data

[1326] server:

[1327] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[1328] 3. Data Analysis

[1329] server:

[1330] The server analyzes the data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies any shortcomings.

[1331] 4. Generating improvement plans

[1332] server:

[1333] Based on the analysis results, the server generates improvement plans. For example, it might identify specific months when the default rate is high and suggest a special campaign to be implemented during that period, or propose concrete steps for automating debt collection operations.

[1334] 5. Notification of proposed improvements

[1335] Server and user operations:

[1336] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[1337] 6. Receiving Feedback

[1338] User actions:

[1339] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[1340] 7. Readjustments based on feedback

[1341] server:

[1342] The server receives user feedback and readjusts improvement suggestions based on it. It reruns the analysis algorithm and generates new improvement suggestions. For example, it might suggest "holding an online seminar that can be implemented without incurring a budget" as an alternative.

[1343] 8. Re-notification of the revised improvement plan

[1344] Server and user operations:

[1345] The revised improvement plan will be notified to the user again via the chat tool. The user can review the new improvement plan and provide further feedback as needed.

[1346] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, generation and notification of improvement proposals, reception of feedback, and readjustment of improvement proposals. This system enables users to manage their credit flexibly based on their actual needs, thereby reducing bad debt rates and improving operational efficiency.

[1347] The following describes the processing flow.

[1348] Step 1: Data Input

[1349] The user uses a terminal to enter credit information and business status data.

[1350] The user enters details of the default rate and debt collection process for each month into a form on their device and clicks the submit button.

[1351] Step 2: Receiving and saving data

[1352] The server receives data sent by the user.

[1353] The server parses the HTTP request and inserts the received data into the database.

[1354] Step 3: Data Analysis

[1355] The server analyzes credit information and business status data stored in the database.

[1356] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[1357] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[1358] Step 4: Generating improvement plans

[1359] The server generates improvement suggestions based on the analysis results.

[1360] The server generates action plans such as "Consider a special campaign during June-August when the default rate is high."

[1361] Step 5: Notification of proposed improvements

[1362] A chat tool will be used to notify users in real time of improvement suggestions generated by the server.

[1363] The server sends improvement suggestions as text messages via the chat API.

[1364] The user reviews the suggested improvements notified within the chat tool.

[1365] Step 6: Receiving Feedback

[1366] Users provide feedback on suggested improvements via their device.

[1367] Users enter specific comments, such as "It's difficult to implement a special campaign due to budget constraints," into a feedback form and submit it.

[1368] Step 7: Receiving and Re-analyzing Feedback

[1369] The server receives feedback sent from the user.

[1370] The server parses the HTTP request and saves the feedback data to the database.

[1371] The server reruns its analysis algorithm to readjust the improvement plan based on the saved feedback.

[1372] Step 8: Re-present the proposed improvement plan.

[1373] The server generates revised suggestions based on the feedback.

[1374] The server generates new improvement suggestions, such as "holding online seminars without incurring any costs," and sends them to the chat tool.

[1375] The user reviews the revised improvement suggestions within the chat tool.

[1376] (Example 1)

[1377] 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".

[1378] The present invention aims to quickly and effectively identify specific risks and problems in the management of users' credit information and business status, and to provide appropriate improvement proposals based on these findings. Furthermore, it aims to provide a more effective management method by receiving feedback from users and making readjustments that reflect that feedback.

[1379] 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.

[1380] In this invention, the server includes means for acquiring credit data and work status data from users, means for storing the credit data and work status data, means for analyzing the data, means for generating improvement proposals based on the analysis results, means for presenting the improvement proposals to users, means for receiving responses from users, and means for redefining the improvement proposals based on the responses. This enables users to manage their accounts flexibly based on their actual needs, allowing them to quickly and effectively reduce bad debt rates and improve operational efficiency.

[1381] A "user" is an entity that operates the system and provides credit data and work status data.

[1382] "Credit data" refers to information about a user's credit status, including time-series data.

[1383] "Work status data" refers to data related to the tasks a user is currently performing, including information about the workflow and efficiency of debt collection tasks.

[1384] A "server" refers to an entire device or system that receives, stores, analyzes, notifies, and provides feedback on data from users.

[1385] "Means of acquisition" refers to mechanisms for collecting credit data and work status data from users. Specifically, this includes terminal interfaces and HTTP requests.

[1386] "Means of storage" refers to storage systems such as databases for saving acquired data.

[1387] "Means of analysis" refers to algorithms and analytical tools used to analyze stored data and detect trends and anomalies.

[1388] "Means for generating improvement proposals" refers to a mechanism that generates suggestions to improve user creditworthiness and operational efficiency based on data analysis results.

[1389] "Means of presentation" refers to a mechanism for informing users of the generated improvement suggestions. Specifically, this includes chat tools and notification systems.

[1390] "Means for receiving responses" refers to mechanisms for receiving feedback and comments from users. Specifically, this includes feedback forms and HTTP requests.

[1391] A "means of redefinition" refers to a mechanism for modifying and recreating improvement plans based on user feedback. This includes analytical algorithms and data analysis processes.

[1392] This invention relates to a system that analyzes a user's credit information and business status data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback. The following describes in detail how this system should be implemented.

[1393] 1. Data input from the user

[1394] The user enters data through the terminal interface. The terminal displays forms for entering historical data on default rates and the current status of credit checks and debt collection operations. For example, if the default rate in January 2022 was 2%, the user enters this value and clicks the submit button.

[1395] 2. Receiving and storing data

[1396] The server receives data sent from the user via an HTTP request. The server parses this request and extracts the data. Default rate data, for example, is converted into an appropriate format and written to a database (e.g., MySQL).

[1397] 3. Data Analysis

[1398] The server analyzes the data stored in the database. It uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms to detect trends and outliers. For example, it uses Z-scores for outlier detection.

[1399] 4. Generating improvement plans

[1400] The server generates improvement suggestions based on the results of data analysis. For example, if the default rate was high during a specific period, it will generate a suggestion to implement a special campaign during that period. It also evaluates the efficiency of each step in the debt collection workflow and identifies steps that can be automated.

[1401] 5. Notification of proposed improvements

[1402] The server notifies the user of the generated improvement suggestions. A chat tool (e.g., Slack API) is used for this purpose. The user checks the suggestions via the chat tool. For example, a message might be sent stating, "The default rate is high from June to August, so increase customer contact frequency during this period."

[1403] 6. Receiving Feedback

[1404] Users provide feedback on suggested improvements. Users enter their feedback into the feedback form on their device and click the submit button. For example, they might comment, "Implementing a special campaign is difficult due to budget constraints."

[1405] 7. Readjustments based on feedback

[1406] The server receives feedback from the user. The server analyzes the feedback, reruns the analysis algorithm, and generates new improvement suggestions. For example, it might suggest an alternative such as "holding an online seminar that can be implemented without incurring a budget."

[1407] 8. Re-notification of the revised improvement plan

[1408] The server will notify the user again of the revised improvement plan via the chat tool. The user can then review the new improvement plan and provide further feedback.

[1409] Examples of specific actions

[1410] The user inputs data on default rates from January to June 2022 and details of the current debt collection workflow. The server receives this data and saves it to the database. It then performs data analysis and generates improvement suggestions, such as, "Due to a sharp increase in default rates in March, special debt collection activities should be intensified during February." The improvement suggestion is notified to the user via a chat tool, and the user responds with feedback such as, "The budget for February has already been allocated." The server receives this feedback and proposes an alternative: "To reduce the budget, intensify non-face-to-face debt collection activities." This improvement suggestion is again notified to the user via the chat tool.

[1411] Example of a prompt

[1412] Analyze customer credit information and business performance data, and generate appropriate improvement plans based on the analysis results obtained from the following databases:

[1413] January 2022: Bad debt rate 2%

[1414] February 2022: Bad debt rate 1.8%

[1415] [Further data...]

[1416] The improvement plan also includes special campaigns and procedures for streamlining debt collection operations.

[1417] As described above, this system efficiently supports users in managing their credit risk.

[1418] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1419] Step 1:

[1420] Users input historical data on default rates and the current status of loan application and collection processes through a terminal interface. Specifically, they enter data such as "January 2022: Default rate 2%, February 2022: Default rate 1.8%" into the input form and click the submit button. The input includes detailed information on default rates and business workflows. The output is the input data sent to the server in JSON format.

[1421] Step 2:

[1422] The server receives data sent from the user via HTTP requests. Specifically, the server parses the request and extracts the data. Default rate data, etc., is converted into an appropriate format and written to a database (e.g., MySQL). The input includes JSON formatted data sent from the user. The output is data saved to the database without delay.

[1423] Step 3:

[1424] The server analyzes data stored in the database. Specifically, the server uses the Python Pandas library to read time-series data and Matplotlib to plot the data. It then executes algorithms (e.g., Z-scores) to detect trends and outliers. The input includes default rate data and business flow data stored in the database. The output provides analysis results and generates information on trends and outliers.

[1425] Step 4:

[1426] The server generates improvement suggestions based on the results of data analysis. Specifically, if the default rate is high during a particular period, it will suggest implementing a special campaign during that period or automating business processes. The input includes the results of the data analysis. The output generates specific improvement suggestions (e.g., "Since the default rate is high from June to August, increase the frequency of customer contact during this period").

[1427] Step 5:

[1428] The server notifies the user of the generated improvement suggestions. Specifically, it sends a message containing the improvement suggestions to the user using a chat tool (e.g., Slack API). The input includes the generated improvement suggestions. The output is a notification displayed in the user's chat tool.

[1429] Step 6:

[1430] Users provide feedback on the suggested improvements. Specifically, they enter a comment such as "Implementing a special campaign is difficult due to budget constraints" into the feedback form on their device and click the submit button. The input includes the user's feedback. The output is the feedback content sent to the server.

[1431] Step 7:

[1432] The server receives feedback sent from users. Specifically, it analyzes the feedback content, re-runs the analysis algorithm, and generates new improvement suggestions. For example, it might generate "holding an online seminar that can be implemented without budgeting" as an alternative suggestion. The input includes the feedback received from users. The output is a revised improvement suggestion.

[1433] Step 8:

[1434] The server will notify the user again of the revised improvement plan via the chat tool. The user can review the new improvement plan and provide further feedback. The input will include the revised improvement plan. The output will be the new improvement plan notified to the user.

[1435] (Application Example 1)

[1436] 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".

[1437] Conventional credit management systems have functions to analyze user credit information and business performance data and provide improvement suggestions, but they lack real-time fraud detection and warning functions using transaction data. This creates a risk that fraudulent transactions requiring immediate action may be overlooked. Solving this problem is essential.

[1438] 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.

[1439] In this invention, the server includes means for receiving user credit information and business status data, means for analyzing this data, means for generating improvement plans based on the analysis results, means for notifying the user of the improvement plans, means for receiving feedback from the user, means for readjusting the improvement plans based on the feedback, means for analyzing user transaction data and detecting the possibility of fraudulent transactions, means for generating warnings based on the detected possibility of fraudulent transactions, and means for notifying the user of the warnings in real time. This enables real-time detection and warning of fraudulent transactions simultaneously with credit management, making it possible to take appropriate measures immediately.

[1440] "User credit information" refers to historical data such as each user's past financial transactions and utility bill payments, and is used to assess their creditworthiness and risk.

[1441] "Business status data" refers to information such as the progress, efficiency, and procedures of the tasks that users are currently performing, and this data is used to analyze and improve business processes.

[1442] "Methods for analyzing data" refers to the process of analyzing credit information and business performance data collected from users using algorithms and statistical models to identify important trends and outliers.

[1443] "Means for generating improvement plans" refers to a function that automatically creates specific suggestions and countermeasures to reduce problems and risks faced by users, based on analysis results.

[1444] "Means for notifying users of improvement suggestions" refers to a function for communicating created improvement suggestions to users in real time through electronic means (e.g., chat tools or notification systems).

[1445] "Means of receiving feedback" refers to a function that allows users to input their opinions and comments on suggested improvements into the system and receive them.

[1446] "Methods for readjusting improvement proposals" refers to the process of re-analyzing the received feedback, reviewing the initial improvement proposals, and generating more appropriate suggestions.

[1447] "User transaction data" refers to the individual transaction history of each user related to electronic payments and financial transactions, and this data is used to detect fraudulent transactions.

[1448] "Means for detecting potential fraudulent transactions" refer to algorithms and methods for analyzing user transaction data to identify potentially fraudulent transactions.

[1449] "Warning generation mechanism" refers to a function that automatically creates warning messages to inform users of potential risks based on detected fraudulent transactions.

[1450] "Means of notifying users of warnings in real time" refers to electronic means (e.g., real-time chat notifications) for immediately conveying generated warnings to users.

[1451] This invention is a system for enhancing credit information management and fraud detection in electronic payment services. This system generates improvement suggestions based on the analysis of users' credit information and business status data, and also has the function of detecting potential fraudulent transactions in real time and notifying warnings.

[1452] System Configuration

[1453] 1. Data entry

[1454] User actions:

[1455] Users input credit information, business status data, and transaction data using their smartphones. The interface is built with React Native and Flutter. This allows users to easily input their past credit history and current transaction information.

[1456] 2. Data reception and storage

[1457] server:

[1458] The server receives input data via a REST API and securely stores it in a database (MySQL or PostgreSQL). The server is built using Flask or Django, which properly parses HTTP requests and writes them to the database.

[1459] 3. Data Analysis

[1460] server:

[1461] This system analyzes credit information, business status data, and transaction data stored in a database. Machine learning libraries such as Sci-kit Learn and TensorFlow are used for the analysis. From the analysis results, trends in credit risk and fraudulent transaction risks at specific time periods are extracted.

[1462] 4. Generating improvement plans

[1463] server:

[1464] Based on the analysis results, the system automatically generates improvement plans to reduce credit risk. These plans can include suggestions for implementing special campaigns during months when specific risks are higher.

[1465] 5. Warning generation and notification

[1466] Server and user operations:

[1467] If a transaction with a high probability of being fraudulent is detected, the server immediately generates an alert and sends a real-time notification to your smartphone. The notification uses Twilio or the Slack API. For example, a message such as "The specified transaction is suspicious and requires additional authentication" will be sent.

[1468] 6. Receiving user feedback

[1469] User actions:

[1470] Users provide feedback on suggestions for improvement and warnings through the interface. This feedback is sent to the server.

[1471] 7. Readjustment of the improvement plan

[1472] server:

[1473] Based on feedback received from users, the analysis algorithm is re-executed and improvement suggestions are readjusted. This provides the optimal improvement suggestions tailored to the user's needs and circumstances.

[1474] 8.Renotification

[1475] Server and user operations:

[1476] The user will be notified again with the adjusted improvement suggestions and regenerated warnings. The user can again provide feedback as needed.

[1477] These processes enable real-time reduction of credit risk and detection of fraudulent transactions, allowing for efficient business operations.

[1478] Specific examples and prompt statements

[1479] Specific example

[1480] Example 1: If a user frequently makes high-value transactions, the system may determine that these transactions are highly likely to be fraudulent, and a notification will be sent recommending additional authentication steps before the transaction.

[1481] Example 2: If a user's transaction history indicates a high credit risk during a specific period, a recommendation will be sent to activate a special monitoring mode during that period.

[1482] Example of a prompt

[1483] Prompt: Analyze the transaction history for the past 6 months and identify patterns that are likely to indicate fraudulent transactions. Based on the results, provide specific countermeasures.

[1484] The above describes specific embodiments for implementing the present invention. The system of the present invention allows users to enjoy flexible credit risk management and fraud prevention measures based on their actual needs.

[1485] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1486] Step 1:

[1487] Users input credit information, business status data, and transaction data through a smartphone interface. The software used is built with React Native or Flutter. The data entered includes past credit history (e.g., credit score and payment history) and current transaction information (e.g., transaction amount and date / time). After input, this data is temporarily stored in the smartphone's memory.

[1488] Step 2:

[1489] Credit information, business status data, and transaction data are sent from the smartphone to the server via a REST API. The server is configured using either Flask or Django. Here, the server parses the HTTP request and stores the received data in a database such as MySQL or PostgreSQL.

[1490] Step 3:

[1491] The server analyzes credit information, business status data, and transaction data stored in the database. Machine learning libraries such as Sci-kit Learn and TensorFlow are used for the analysis. Time series analysis and anomaly detection algorithms are implemented to extract user credit risk trends and potential fraudulent transactions.

[1492] Step 4:

[1493] The server generates improvement suggestions to reduce credit risk based on the analysis results. For example, if there is a tendency for credit risk to increase in a particular month, it will generate a suggestion to implement a special campaign during that month. The generated improvement suggestions are stored on the server.

[1494] Step 5:

[1495] The server detects transactions that are highly likely to be fraudulent based on the analysis results and generates a warning. For example, if a series of high-value transactions occur, the anomaly detection algorithm will be activated and a warning message such as "This transaction is suspicious. Additional authentication is required" will be generated. The warning is stored on the server.

[1496] Step 6:

[1497] The server notifies users in real time of any improvement suggestions and warnings it generates. Twilio and the Slack API are used for notifications. Users can view improvement suggestions and warnings on their smartphones.

[1498] Step 7:

[1499] Users provide feedback on improvement suggestions and warnings they receive. This feedback is submitted using a smartphone interface.

[1500] Step 8:

[1501] Feedback is sent to the server via a REST API. The server reruns the analysis algorithm based on the received feedback and readjusts the suggested improvements. For example, if a special campaign cannot be implemented due to budget constraints, a new suggestion such as "hold an online seminar" will be generated.

[1502] Step 9:

[1503] The server regenerates revised improvement suggestions and warnings, and notifies the user in real time. The user can then provide further feedback. By repeating this process, the user's credit risk management and fraud prevention are optimized.

[1504] This series of processes allows users to efficiently manage their credit information, detect fraudulent transactions, and take appropriate measures immediately.

[1505] 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.

[1506] This invention relates to a system that analyzes a user's credit information and business performance data, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on user feedback and sentiment. Specific embodiments of this system are described in detail below.

[1507] 1. Data input from the user

[1508] User actions:

[1509] Users input credit information and business status data using a terminal interface. For example, users input the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow.

[1510] 2. Receiving and storing data

[1511] server:

[1512] The server receives data sent by the user and stores it in the database. The server parses the HTTP request and writes it to the database in the appropriate format.

[1513] 3. Data Analysis

[1514] server:

[1515] The server analyzes credit information and business status data stored in the database. Specifically, it plots past default rate data over time and uses algorithms to identify outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[1516] 4. Recognition of emotions

[1517] Server (emotion engine):

[1518] The system incorporates an emotion engine to analyze emotions from text data entered by the user. The emotion engine analyzes the user's input and feedback to recognize emotions (e.g., joy, anger, sadness, satisfaction, etc.).

[1519] 5. Generating improvement plans

[1520] server:

[1521] Based on the analysis results and the output of the emotion engine, the server generates improvement suggestions. For example, if the emotion engine detects stress or dissatisfaction from user feedback, it will consider improvement measures corresponding to those emotions. It will generate action plans such as "Consider a special campaign during June-August when the default rate is high."

[1522] 6. Notification of proposed improvements

[1523] Server and user operations:

[1524] A chat tool is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. For example, a message might be displayed suggesting, "Since the default rate is high from June to August, increase the frequency of customer contact during this period."

[1525] 7. Receiving feedback and re-recognizing emotions

[1526] User actions:

[1527] Users provide feedback on suggested improvements. For example, they might enter specific comments such as, "Implementing a special campaign is difficult due to budget constraints," into the feedback form on their device.

[1528] Server (emotion engine):

[1529] The server receives feedback from the user and analyzes it again using the emotion engine. It monitors changes in the user's emotions and readjusts improvement plans based on the emotional feedback.

[1530] 8. Re-adjustment and re-notification of improvement proposals

[1531] server:

[1532] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending money" and send it to the chat tool.

[1533] User actions:

[1534] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[1535] As described above, the system of the present invention efficiently supports users' credit risk management through a series of processes including data input from the user, data analysis, sentiment recognition, generation and notification of improvement suggestions, feedback and sentiment reconfirmation, and readjustment of improvement suggestions. This system enables users to manage their credit flexibly based on their actual needs and emotions, thereby reducing bad debt rates and improving operational efficiency.

[1536] The following describes the processing flow.

[1537] Step 1: Data Input

[1538] The user uses a terminal to enter credit information and business status data.

[1539] For example, the user enters the default rate for each month (e.g., January 2022: 2%, February 2022: 1.8%) and the current debt collection workflow into a form on the terminal and clicks the submit button.

[1540] Step 2: Receiving and saving data

[1541] The server receives data sent by the user.

[1542] The server parses the HTTP request and inserts the received data into the database.

[1543] Step 3: Data Analysis

[1544] The server analyzes credit information and business status data stored in the database.

[1545] The server plots historical default rate data over time and runs algorithms to identify outliers and trends.

[1546] The server evaluates the debt collection workflow from an efficiency standpoint and identifies any shortcomings.

[1547] Step 4: Recognizing Emotions

[1548] The server uses an emotion engine to analyze the user's emotions from their text input.

[1549] For example, in response to a user's comment, "Special campaigns are difficult to budget for," the sentiment engine detects "dissatisfaction."

[1550] Step 5: Generating improvement proposals

[1551] The server generates improvement suggestions based on the analysis results and the output of the emotion engine.

[1552] For example, the server might propose "holding an online seminar that can be implemented without incurring a budget" to create improvement plans that address user dissatisfaction.

[1553] Step 6: Notification of proposed improvements

[1554] A chat tool will be used to notify users in real time of improvement suggestions generated by the server.

[1555] The server sends improvement suggestions as text messages via the chat API.

[1556] The user reviews the suggested improvements notified within the chat tool.

[1557] Step 7: Receiving feedback and re-evaluating emotions

[1558] Users provide feedback on suggested improvements via their device.

[1559] For example, a user might enter a comment in the feedback form saying, "The online seminar proposal is a good idea, but the date and time don't work for me," and submit it.

[1560] The server receives the feedback and the sentiment engine analyzes it again. For example, it might determine that "the user is satisfied with the comment, but has concerns about the date and time."

[1561] Step 8: Readjust and re-notify the proposed improvements.

[1562] The server generates refined improvement suggestions based on feedback and the output of the emotion engine.

[1563] For example, "Holding online seminars with flexible scheduling options" could be generated as a new improvement suggestion.

[1564] The server sends the revised improvement suggestions to the chat tool for the user to review.

[1565] If users provide further feedback, that feedback will be used to make further adjustments.

[1566] Through these steps, the system of the present invention efficiently and flexibly supports the user's credit risk management by receiving data input from the user, analyzing the data and emotions, generating and notifying improvement suggestions, providing feedback and reassessing emotions, and readjusting the improvement suggestions.

[1567] (Example 2)

[1568] 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".

[1569] Conventional credit information and business management systems lack the appropriate data analysis and readjustment functions to efficiently and flexibly support users' credit risk management. Furthermore, they often unilaterally provide standard improvement suggestions without considering user sentiment, making it difficult to provide optimal solutions tailored to users' specific needs and feelings. This results in users being unable to effectively manage credit risk based on actual business situations and emotions.

[1570] 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.

[1571] In this invention, the server includes means for receiving credit information and business management information from a user; means for storing the credit information and business management information in a database; means for analyzing the credit information and business management information; means for recognizing the user's emotions based on the analysis results; means for generating improvement proposals based on the analysis results and recognized emotions; means for notifying the user of the improvement proposals; means for receiving feedback from the user; and means for readjusting the improvement proposals based on the feedback. This enables the server to efficiently and flexibly support the user's credit risk management and provide optimal solutions tailored to the user's emotions and specific needs.

[1572] "Credit information" refers to data about the creditworthiness of a user or company, including information such as default rates and payment history.

[1573] "Business management information" refers to data related to the business processes performed by a user or company and their efficiency, including business flow procedures and task progress.

[1574] A "database" is a system that systematically stores information and allows it to be retrieved later; software such as MySQL is an example of this.

[1575] "Analysis" refers to the process of using specific algorithms and methods to identify the meaning, trends, and outliers of collected data.

[1576] "Recognizing emotions" means using a natural language processing model to identify the user's emotions from the text data they input.

[1577] A "proposal for improvement" refers to a specific action plan or measure proposed to improve user credit risk and operational efficiency based on analysis results and emotion recognition results.

[1578] A "chat tool" is software used for exchanging messages in real time; examples include Slack and Microsoft Teams.

[1579] "Feedback" refers to specific opinions and comments that users provide regarding suggestions for improvement from the server.

[1580] "Readjustment" is the process of reviewing existing improvement proposals and changing them to more appropriate ones based on feedback received from users and sentiment recognition results.

[1581] This invention is a system that analyzes a user's credit information and business management information, generates improvement proposals based on the analysis results, notifies the user, and readjusts the proposals based on the user's feedback and sentiment. Specific embodiments of this system are described in detail below.

[1582] Data input from users

[1583] User actions:

[1584] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate in January 2022 was 2%, and the default rate in February 2022 was 1.8%," and also input the current debt collection workflow.

[1585] Receiving and storing data

[1586] server:

[1587] The server receives data sent by the user and stores it in a database. Specifically, it parses the HTTP request from the terminal, converts the data into the appropriate format, and stores it in the database (e.g., MySQL). After the data is saved, the server sends a confirmation message to the terminal.

[1588] Data analysis

[1589] server:

[1590] The system retrieves and analyzes stored credit and business management information. Specifically, it uses a time-series analysis algorithm implemented in Python to plot historical default rate data over time and detect outliers and trends. It also evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[1591] Recognition of emotions

[1592] Server (emotion engine):

[1593] The server is equipped with an emotion engine (e.g., a natural language processing model) that analyzes emotions from the user's input text data. As a result of the analysis, emotions such as "joy," "anger," "sadness," and "satisfaction" are tagged.

[1594] Generating improvement plans

[1595] server:

[1596] The server generates improvement suggestions based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "anxiety" from user feedback, the server will consider specific action plans such as "implement a special campaign during June to August when the default rate is high."

[1597] Notification of improvement proposals

[1598] Server and user operations:

[1599] A chat tool (e.g., Slack, Microsoft Teams) is used to notify users in real time of improvement suggestions generated by the server. Users check the improvement suggestions notified through the chat tool. Specifically, a message such as "The default rate is high from June to August, so we suggest increasing the frequency of customer contact during this period" will be displayed.

[1600] Receiving feedback and re-recognizing emotions

[1601] User actions:

[1602] Users provide feedback on the proposed improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[1603] Server (emotion engine):

[1604] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[1605] Re-adjustment and re-notification of improvement proposals

[1606] server:

[1607] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. For example, it might generate a new improvement suggestion such as "Hold an online seminar that can be conducted without spending a budget" and send it to the chat tool.

[1608] User actions:

[1609] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary. The server repeats this process to ensure the user receives the best possible solution.

[1610] Specific examples and prompt statements

[1611] As a concrete example, if a user submits feedback stating, "It's difficult to run a special campaign because the default rate in June is high," the server receives this input and uses its emotion engine to recognize the emotion of "dissatisfaction." Next, the server generates a new improvement suggestion, "Hold an online seminar that can be implemented without incurring a budget," and notifies the user again.

[1612] Examples of prompt statements to input into a generative AI model are as follows:

[1613] "Please propose effective improvement measures for months when the loan default rate is high."

[1614] "Please tell me how to streamline our current debt collection process."

[1615] In this way, the system can efficiently and flexibly support users' credit risk management and provide optimal solutions tailored to users' emotions and specific needs.

[1616] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1617] Step 1:

[1618] User data input

[1619] Users input credit information and business management information through a terminal interface. For example, a user might input "The default rate for January 2022 was 2%, and the default rate for February 2022 was 1.8%," and similarly input the current debt collection workflow procedure. This becomes the input data.

[1620] Input: Credit information and business management information (e.g., default rate, business flow procedures)

[1621] Output: HTTP request sent from the terminal

[1622] Step 2:

[1623] Receiving and storing data

[1624] The server receives data sent by the user and stores it in a database. The server parses the HTTP request, converts the data into the appropriate format, and stores it in the database (e.g., MySQL). After saving the data, the server sends a confirmation message to the terminal.

[1625] Specific actions:

[1626] The server parses the HTTP request and extracts credit information and business management information. It then generates and executes an SQL query to write the extracted data to the database.

[1627] Input: HTTP request from terminal (credit information and business management information)

[1628] Output: Credit information and business management information stored in the database, and a confirmation message.

[1629] Step 3:

[1630] Data analysis

[1631] The server retrieves and analyzes stored credit and business management information. Specifically, it uses a time-series analysis algorithm implemented in Python to plot historical default rate data over time and detect outliers and trends. Furthermore, it evaluates the efficiency of each step in the current debt collection workflow and identifies shortcomings.

[1632] Specific actions:

[1633] The server retrieves the necessary data from the database and inputs it into a time-series analysis algorithm. Furthermore, an efficiency evaluation model is used for each step in the workflow to analyze the performance of each step.

[1634] Input: Credit information and business management information stored in the database

[1635] Output: Analysis results (anomaly detection, trend analysis, efficiency evaluation)

[1636] Step 4:

[1637] Recognition of emotions

[1638] Server (emotion engine):

[1639] The server uses an emotion engine (e.g., a natural language processing model) to analyze the user's input text data to determine their emotions. The analysis results in emotions such as "joy," "anger," "sadness," and "satisfaction."

[1640] Specific actions:

[1641] The server inputs text data from the user into the sentiment engine, and a natural language processing model analyzes the text and labels it with emotions.

[1642] Input: User's text data

[1643] Output: Sentiment analysis results (sentiment labels)

[1644] Step 5:

[1645] Generating improvement plans

[1646] The server generates improvement suggestions based on the analysis results and the output of the emotion engine. For example, if the emotion engine detects "anxiety" from user feedback, it will generate improvement suggestions such as "implement a special campaign during June to August when the default rate is high" as a specific action plan.

[1647] Specific actions:

[1648] The server receives the analysis results and emotion labels as input, and uses prompt sentences to generate improvement suggestions into the AI ​​model. At this time, it determines whether the generated improvement suggestions are best suited to the user's needs.

[1649] Input: Analysis results, emotion labels

[1650] Output: Improvement plan

[1651] Step 6:

[1652] Notification of improvement proposals

[1653] To notify users in real time of improvement suggestions generated by the server, a chat tool (e.g., Slack, Microsoft Teams) is used. Users can review the improvement suggestions through the chat tool and take specific actions.

[1654] Specific actions:

[1655] The server uses the chat tool's API to send the generated improvement suggestions as a message. The user receives and acknowledges the notification in the chat tool.

[1656] Input: Improvement proposal

[1657] Output: Suggestions for improving the message format sent to the user

[1658] Step 7:

[1659] Receiving feedback and re-recognizing emotions

[1660] User actions:

[1661] Users provide feedback on the suggested improvements. Specifically, they enter specific comments, such as "Implementing a special campaign is difficult from a budgetary standpoint," into the feedback form on their device.

[1662] server:

[1663] The server receives feedback from the user and analyzes it again using the emotion engine. The server monitors changes in the user's emotions and readjusts improvement suggestions based on the emotional feedback.

[1664] Specific actions:

[1665] The server parses the feedback, inputs it into the emotion engine for analysis, and then saves the analysis results for use in the next step.

[1666] Input: User feedback

[1667] Output: Feedback analysis results, emotion labels

[1668] Step 8:

[1669] Re-adjustment and re-notification of improvement proposals

[1670] The server generates refined improvement suggestions based on feedback and the output of the emotion engine. Specifically, it generates new improvement suggestions such as "Hold an online seminar that can be conducted without spending a budget" and sends them to the chat tool.

[1671] User:

[1672] Users review the revised improvement suggestions within the chat tool and provide further feedback if necessary.

[1673] Specific actions:

[1674] The server incorporates the feedback into its analysis results, inputs new prompts into the generating AI model, and generates a revised improvement plan. The user is then notified again via the chat tool.

[1675] Input: Feedback analysis results, emotion labels

[1676] Output: Revised improvement proposals, re-notified messages

[1677] (Application Example 2)

[1678] 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".

[1679] Conventional credit risk management systems are effective in analyzing user credit information and business performance data to generate improvement plans, but they have the drawback of not being able to consider user emotions and thus failing to adequately reduce user stress and dissatisfaction. Therefore, there is a need to improve the user experience and generate more accurate improvement plans.

[1680] 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. In this invention, the server includes means for receiving credit information and business status data from a user, means for analyzing the credit information and business status data, means for generating improvement proposals based on the analysis results, means for notifying the user of the improvement proposals, means for receiving feedback from the user, means for readjusting the improvement proposals based on the feedback, means for analyzing the sentiment of the user's feedback, and means for generating and notifying improvement proposals based on the sentiment analysis results. This makes it possible to generate and notify highly accurate improvement proposals that take the user's sentiment into consideration.

[1681] "Credit information" refers to data used to assess a user's credit risk, and specifically includes information such as default rates and payment history.

[1682] "Work status data" refers to data used to evaluate the progress and efficiency of a user's work, and specifically includes the progress and procedures of debt collection tasks.

[1683] "Data analysis" refers to the process of analyzing received credit information and business status data using statistical and machine learning methods to identify outliers and trends.

[1684] "Generating improvement plans" refers to devising specific action plans to improve operational efficiency and reduce credit risk, based on data analysis results and user sentiment analysis results.

[1685] "Notification means" refers to a means of communicating generated improvement suggestions to users, and includes chat tools and notification applications.

[1686] "Receiving feedback" refers to collecting opinions and comments that users provide regarding the improvement suggestions they have been notified about.

[1687] "Sentiment analysis" refers to the process of analyzing user feedback and comments using natural language processing technology to identify emotions (such as joy, anger, sadness, satisfaction, etc.).

[1688] "Readjustment" refers to reviewing initial improvement proposals based on user feedback and sentiment analysis results, and generating more appropriate new improvement proposals.

[1689] The system of this invention is designed to support users in managing their credit risk. Specifically, it has the function of analyzing users' credit information and work status data, and generating and notifying improvement suggestions based on user feedback and sentiment analysis results. The detailed configuration for implementing this system is described below.

[1690] Program processing and the hardware / software used

[1691] 1. User data input

[1692] Users input credit information and business performance data using a smartphone app. This data is used to evaluate business efficiency and credit risk. The terminal interface is intuitive and easy to use, for example, by providing input forms and dropdown menus.

[1693] 2. Receiving and storing data

[1694] The terminal sends the entered data to the server, which receives the HTTP request and writes it to the database. This allows for centralized data management.

[1695] 3. Data Analysis

[1696] The server analyzes the received data. Specifically, it uses Python and the Flask framework to identify anomalies and trends from the data using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, making it easy to spot anomalies at a glance.

[1697] 4. Feedback and Recognition of Emotions

[1698] The server receives user feedback and analyzes its content using a sentiment analysis engine (e.g., TextBlob library). It identifies positive and negative emotions from the comments and feedback entered by the user.

[1699] 5. Generating improvement plans

[1700] Based on the analysis results and sentiment analysis results, the server generates improvement suggestions. Using an AI model, it provides concrete and realistic solutions to the user's challenges. Action plans such as "Consider a special campaign during June-August when the default rate is high" are generated.

[1701] 6. Notification of proposed improvements

[1702] The generated improvement suggestions are notified to the user in real time. The notification method uses a chat tool within the smartphone app. Users can check the notification and take action.

[1703] 7. Receiving and readjusting feedback

[1704] The user submits feedback on the suggested improvements. The server receives this feedback and performs sentiment analysis again to understand the user's feelings and opinions. Based on the results, it regenerates and notifies the user of even more appropriate improvement suggestions.

[1705] Examples of specific cases and prompt statements

[1706] For example, if a user provides feedback stating that "implementing the campaign is financially difficult," a process is initiated to generate new improvement proposals based on that feedback. The sentiment analysis engine uses this feedback to understand the user's realistic constraints and proposes a readjusted improvement proposal such as "holding an online seminar that can be implemented without incurring a budget."

[1707] Example of a prompt

[1708] User input: The campaign is a good idea, but it's not practical.

[1709] Prompt to the generated AI: Users rate the campaign as "good" but find it "difficult." Please suggest realistic and actionable improvements.

[1710] In this way, the system analyzes user data from multiple perspectives and provides optimal solutions while considering user sentiment, thereby achieving more effective credit risk management.

[1711] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1712] Step 1:

[1713] Users input credit information and business status data through a terminal interface. This data includes default rates, payment history, and the progress of debt collection efforts. Detailed business data is then transmitted to the server.

[1714] Step 2:

[1715] The server receives data sent by the user and stores it in the database. This process involves parsing the HTTP request and writing the data to the database in the appropriate format. Input data is sent to the server in JSON format and stored in the database.

[1716] Step 3:

[1717] The server analyzes data stored in the database. Specifically, it uses Python and the Flask framework to identify outliers and trends using statistical methods. For example, it uses the matplotlib library to create time-series graphs of the data, visualizing them so that anomalies can be easily detected.

[1718] Step 4:

[1719] Users input feedback using their devices. This feedback includes suggestions for improvement and expressions of emotion. The user then sends their opinion on the improvement suggestions provided by the system to the server.

[1720] Step 5:

[1721] The server receives user feedback and analyzes its content using an emotion analysis engine. Specifically, it uses the TextBlob library to identify emotions from text data. This analysis extracts positive and negative emotions.

[1722] Step 6:

[1723] The server generates improvement suggestions based on data analysis and sentiment analysis results. Using an AI model, it generates the optimal action plan based on the user's emotions and credit information. For example, if the emotion of the feedback is negative, it will suggest an alternative improvement that is less burdensome.

[1724] Step 7:

[1725] The server notifies users in real time of the improvement suggestions it generates. A chat tool is used for notifications, and users check the notifications on their devices. The chat tool displays specific improvement suggestions to the user.

[1726] Step 8:

[1727] The user submits feedback again using their device. If the suggested improvements are not realistic, new feedback is submitted.

[1728] Step 9:

[1729] The server receives new feedback and performs sentiment analysis again. It monitors changes in sentiment and uses the AI ​​model to readjust existing improvement suggestions. For example, in response to feedback that it is difficult due to budget constraints, new improvement suggestions such as online seminars are generated.

[1730] Step 10:

[1731] The server then notifies the user again of the revised improvement plan. The user then reviews the new improvement plan on their device via the chat tool. This completes the notification of the final improvement plan to the user.

[1732] The input data and feedback are analyzed sequentially, and flexible improvement suggestions that take user sentiment into account are provided, thereby improving operational efficiency and credit risk management.

[1733] 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.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] 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.

[1739] 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.

[1740] 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 based, for example, 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.

[1741] 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."

[1742] 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.

[1743] 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.

[1744] 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.

[1745] 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.

[1746] 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.

[1747] 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.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] 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.

[1753] 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 to be incorporated by reference.

[1754] The following is further disclosed regarding the embodiments described above.

[1755] (Claim 1)

[1756] A means of receiving credit information and business status data from users,

[1757] Means for analyzing the aforementioned credit information and business status data,

[1758] A means for generating improvement proposals based on analysis results,

[1759] A means for notifying the user of the aforementioned improvement proposal,

[1760] A means of receiving user feedback,

[1761] Means for readjusting the proposed improvements based on the aforementioned feedback,

[1762] A system that includes this.

[1763] (Claim 2)

[1764] The system according to claim 1, wherein the means for notifying the user of improvement suggestions is to notify the user in real time via chat.

[1765] (Claim 3)

[1766] The system according to claim 1, wherein the credit information received from the user includes time-series data.

[1767] "Example 1"

[1768] (Claim 1)

[1769] A means of obtaining credit data and work status data from users,

[1770] Means for storing the aforementioned credit data and work status data,

[1771] Means for analyzing the aforementioned data,

[1772] A means of generating improvement plans based on the analysis results,

[1773] A means of presenting the aforementioned improvement proposal to the user,

[1774] A means of receiving responses from users,

[1775] Means for redefining the proposed improvement based on the aforementioned response,

[1776] A system that includes this.

[1777] (Claim 2)

[1778] The system according to claim 1, wherein the means of presenting improvement proposals is to quickly notify users using a chat tool.

[1779] (Claim 3)

[1780] The system according to claim 1, wherein the credit data obtained from the user includes time-series data.

[1781] "Application Example 1"

[1782] (Claim 1)

[1783] A means of receiving credit information and business status data from users,

[1784] Means for analyzing the aforementioned credit information and business status data,

[1785] A means for generating improvement proposals based on analysis results,

[1786] A means for notifying the user of the aforementioned improvement proposal,

[1787] A means of receiving user feedback,

[1788] Means for readjusting the proposed improvements based on the aforementioned feedback,

[1789] A means of analyzing user transaction data and detecting the possibility of fraudulent transactions,

[1790] A means of generating a warning based on the detected potential for fraudulent transactions,

[1791] A means for notifying the user of the aforementioned warning in real time,

[1792] A system that includes this.

[1793] (Claim 2)

[1794] The system according to claim 1, wherein the means for notifying the user of improvement suggestions and warnings is a means for notifying the user in real time via chat.

[1795] (Claim 3)

[1796] The system according to claim 1, wherein the credit information and transaction data received from the user include time-series data.

[1797] "Example 2 of combining an emotion engine"

[1798] (Claim 1)

[1799] A means of receiving credit information and business management information from users,

[1800] Means for storing the aforementioned credit information and business management information in a database,

[1801] Means for analyzing the aforementioned credit information and business management information,

[1802] A means of recognizing user emotions based on analysis results,

[1803] A means for generating improvement plans based on the aforementioned analysis results and recognized emotions,

[1804] A means for notifying the user of the aforementioned improvement proposal,

[1805] A means of receiving user feedback,

[1806] Means for readjusting the proposed improvements based on the aforementioned feedback,

[1807] A system that includes this.

[1808] (Claim 2)

[1809] The system according to claim 1, which is a means of notifying users of improvement suggestions in real time via a chat tool.

[1810] (Claim 3)

[1811] The system according to claim 1, wherein the aforementioned credit information and business management information include time-series data.

[1812] (Claim 4)

[1813] The system according to claim 1, wherein the analysis means uses an algorithm for detecting outliers or trends.

[1814] (Claim 5)

[1815] The system according to claim 1, wherein the means for analyzing the user's emotions uses a natural language processing model.

[1816] (Claim 6)

[1817] The system according to claim 1, further comprising means for notifying the user again of the readjusted improvement plan.

[1818] "Application example 2 when combining with an emotional engine"

[1819] (Claim 1)

[1820] A means of receiving credit information and business status data from users,

[1821] Means for analyzing the aforementioned credit information and business status data,

[1822] A means for generating improvement proposals based on analysis results,

[1823] A means for notifying the user of the aforementioned improvement proposal,

[1824] A means of receiving user feedback,

[1825] Means for readjusting the proposed improvements based on the aforementioned feedback,

[1826] A means of analyzing the sentiment behind user feedback,

[1827] A means of generating and notifying improvement suggestions based on the results of sentiment analysis,

[1828] A system that includes this.

[1829] (Claim 2)

[1830] The system according to claim 1, wherein the means for notifying the user of improvement suggestions is to notify the user in real time via chat.

[1831] (Claim 3)

[1832] The system according to claim 1, wherein the credit information received from the user includes time-series data. [Explanation of symbols]

[1833] 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. A means of receiving credit information and business status data from users, Means for analyzing the aforementioned credit information and business status data, A means for generating improvement proposals based on analysis results, A means for notifying the user of the aforementioned improvement proposal, A means of receiving user feedback, Means for readjusting the proposed improvements based on the aforementioned feedback, A system that includes this.

2. The system according to claim 1, wherein the means for notifying the user of improvement suggestions is to notify the user in real time via chat.

3. The system according to claim 1, wherein the credit information received from the user includes time-series data.

Images