System

Abstract

An object of a system according to an embodiment is to automate communication with a debtor and to make a reminder process efficient.SOLUTION: A system includes a chat unit, an analysis unit, a telephone handling unit, and a fund utilization unit. The chat unit receives a response from the debtor. The analysis unit analyzes the response received by the chat unit. The telephone handling unit performs telephone handling on the basis of the response analyzed by the analysis unit. The fund utilization part utilizes the raised fund.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, communication with debtors and the collection process were often done manually, which led to issues of inefficiency.

[0005] The system according to the embodiment aims to automate communication with debtors and streamline the collection process. [Means for solving the problem]

[0006] The system according to the embodiment includes a chat unit, an analysis unit, a telephone response unit, and a fund utilization unit. The chat unit receives responses from debtors. The analysis unit analyzes the responses received by the chat unit. The telephone response unit responds to calls based on the responses analyzed by the analysis unit. The fund utilization unit utilizes the procured funds. [Effects of the Invention]

[0007] The system according to the embodiment can automate communication with debtors and streamline the collection process. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A debt collection system according to an embodiment of the present invention automates communication with debtors to speedily and efficiently execute the debt collection process. The debt collection system includes a chat unit that receives responses from debtors, an analysis unit that analyzes the responses received by the chat unit, a telephone response unit that responds to calls based on the responses analyzed by the analysis unit, and a fund utilization unit that utilizes procured funds. For example, the debt collection system uses a chatbot to send a dunning message to the debtor and receive a response from the debtor. The debt collection system then analyzes the response received by the chatbot and takes appropriate action. For example, if the debtor proposes a payment plan, the chatbot records the proposal and notifies the financial institution as necessary. Furthermore, the debt collection system uses AI to automate telephone responses and streamline telephone interactions with debtors. For example, AI can analyze the debtor's voice and generate appropriate dunning messages. This allows the debt collection system to modernize the debt collection process without relying on traditional methods and optimize corporate profitability and cash flow. This allows the debt collection system to centrally manage communication with debtors and speedily and efficiently execute the dunning process. For example, by utilizing chatbots and AI, the time and cost required for collection work can be reduced, and debt collection can be carried out efficiently. The funds raised will also be used for various purposes, such as strengthening the lending system for main financial institutions and expanding business internationally.

[0029] The debt collection system according to the embodiment includes a chat unit, an analysis unit, a telephone response unit, and a fund utilization unit. The chat unit receives responses from the debtor. Responses from the debtor include, but are not limited to, text messages, voice messages, and the like. The chat unit, for example, sends a dunning message to the debtor and receives a response from the debtor. The chat unit can also estimate the debtor's emotions and adjust the content and timing of the dunning message based on the estimated emotions. For example, if the debtor is feeling stressed, the chat unit can send the dunning message using gentle language and delay the timing of the message. The analysis unit analyzes the responses received by the chat unit. The analysis can be performed using, for example, natural language processing technology or emotion analysis, but is not limited to, these examples. For example, the analysis unit analyzes the content of the debtor's response and takes an appropriate action. The analysis unit can also estimate the debtor's emotions and adjust the analysis method for the response based on the estimated emotions. For example, if the debtor is angry, the response content can be analyzed in detail to encourage the debtor to respond calmly. The telephone response unit responds to the telephone call based on the response analyzed by the analysis unit. The telephone response may be, for example, an automated response using AI or a response by an operator, but is not limited to these examples. For example, the telephone response unit automates telephone responses with debtors using AI. The telephone response unit may also estimate the debtor's emotions and adjust the content and timing of the telephone response based on the estimated debtor's emotions. For example, if the debtor is angry, the telephone response unit adjusts the content of the telephone response to encourage a calm response. The fund utilization unit utilizes the procured funds. Fund utilization may be, for example, for strengthening the loan system for financial institutions or for international business expansion, but is not limited to these examples. For example, the fund utilization unit utilizes the procured funds to strengthen the loan system for financial institutions. The fund utilization unit may also utilize the procured funds for international business expansion. As a result, the debt collection system according to the embodiment automates communication with debtors and enables the collection process to be carried out quickly and effectively.

[0030] The chat unit can send a reminder message to the debtor and accept a response from the debtor. Examples of reminder messages include, but are not limited to, a payment deadline notification and payment method instructions. The chat unit can also send a payment deadline notification to the debtor and accept a response from the debtor. The chat unit can also send payment method instructions to the debtor and accept a response from the debtor. For example, the chat unit can send a message explaining details of the payment method and respond to questions from the debtor. This automates communication with the debtor and enables efficient sending of reminder messages. Some or all of the above-described processing in the chat unit can be performed using, for example, AI, or can be performed without using AI. For example, the chat unit can cause a generation AI to execute a process of sending reminder messages to the debtor.

[0031] The analysis unit can analyze the debtor's response and take appropriate action. Examples of analysis include, but are not limited to, natural language processing technology and sentiment analysis. For example, the analysis unit can analyze the debtor's response using natural language processing technology and take appropriate action. The analysis unit can also analyze the debtor's response using sentiment analysis and take appropriate action. For example, if the debtor proposes a payment plan, the analysis unit records the plan and notifies the financial institution as necessary. If the debtor refuses to pay, the analysis unit can analyze the reason and consider countermeasures. For example, if the debtor promises to pay, the analysis unit analyzes the reliability of the promise. By analyzing the debtor's response and taking appropriate action, efficient collection can be achieved. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the debtor's response to a generation AI and have the generation AI output the analysis results.

[0032] The telephone response unit can use AI to automate telephone responses with debtors. Examples of telephone responses include, but are not limited to, automated responses using AI or responses by operators. The telephone response unit can also use AI to automate telephone responses with debtors. The telephone response unit can also analyze the debtor's voice and generate appropriate dunning messages. For example, the telephone response unit can analyze the debtor's tone of voice and language and respond appropriately. By utilizing AI, this makes it possible to automate and streamline telephone responses with debtors. Some or all of the above-described processing in the telephone response unit can be performed using AI, or can be performed without using AI. For example, the telephone response unit can input the debtor's voice data into a generation AI and have the generation AI generate an appropriate dunning message.

[0033] The fund utilization department can utilize the procured funds to strengthen the lending system for financial institutions and to expand the business internationally. Examples of fund utilization include, but are not limited to, strengthening the lending system for financial institutions and expanding the business internationally. For example, the fund utilization department utilizes the procured funds to strengthen the lending system for financial institutions. The fund utilization department can also utilize the procured funds for expanding the business internationally. For example, the fund utilization department allocates funds to upgrading the lending system for financial institutions and adding new functions. The fund utilization department can also allocate funds to entering new markets and building international partnerships. This effectively utilizes the procured funds to strengthen the lending system for financial institutions and expand the business internationally. Some or all of the above-described processing in the fund utilization department may be performed using, for example, AI, or may be performed without using AI. For example, the fund utilization department can input a fund allocation plan into the generation AI and have the generation AI execute the optimal fund allocation.

[0034] The chat unit can analyze the debtor's past response history and generate a dunning message. Response history includes, but is not limited to, past messages and call records. For example, if the debtor has previously delayed payments, the chat unit can generate a message emphasizing the payment deadline. Furthermore, if the debtor has previously made prompt payments, the chat unit can generate a message expressing gratitude. Furthermore, if the debtor has previously proposed a payment plan, the chat unit can generate a message based on that plan. This enables effective dunning by generating an optimal dunning message based on the past response history. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or without AI. For example, the chat unit can input the debtor's past response history into a generation AI and have the generation AI generate an optimal dunning message.

[0035] The chat unit can customize the content of messages based on the debtor's current financial situation and repayment capacity. Examples of financial situation and repayment capacity include, but are not limited to, income, expenses, and asset status. For example, if the debtor's income is decreasing, the chat unit can send a message proposing a flexible payment plan. Furthermore, if the debtor's repayment capacity is high, the chat unit can also send a message encouraging early payment. Furthermore, if the debtor's financial situation is unstable, the chat unit can also send a message proposing a payment deferral. This enables more effective collection by sending messages tailored to the debtor's financial situation and repayment capacity. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or may be performed without AI. For example, the chat unit can input data on the debtor's financial situation and repayment capacity into the generation AI and have the generation AI customize the messages.

[0036] The chat unit can automatically set the timing for sending the next dunning message based on the debtor's response. Examples of the timing for sending the next dunning message include, but are not limited to, a time period or a day of the week. For example, if the debtor promises to pay, the chat unit can set the timing for sending the next dunning message based on the promised date. Furthermore, if the debtor refuses to pay, the chat unit can set the timing for sending another dunning message after a certain period of time. Furthermore, if the debtor proposes a payment plan, the chat unit can set the timing for sending the next dunning message based on the plan. This enables effective dunning by setting the timing for sending the next dunning message based on the debtor's response. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or without AI. For example, the chat unit can input the debtor's response into a generation AI and have the generation AI set the timing for sending the next dunning message.

[0037] The chat unit can send different dunning messages for each region based on the debtor's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and address information. For example, if the debtor lives in an urban area, the chat unit can send a message that takes into account the economic conditions specific to that area. For example, if the debtor lives in a rural area, the chat unit can send a message that takes into account the economic conditions specific to that area. Furthermore, if the debtor lives overseas, the chat unit can send a message that takes into account the economic conditions and culture of that country. This enables more effective dunning by sending messages that take into account the economic conditions of each region. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or may be performed without AI. For example, the chat unit can input the debtor's geographical location information into a generation AI and have the generation AI generate different dunning messages for each region.

[0038] The chat unit can analyze the debtor's social media activity and customize messages based on relevant information. Social media activity includes, but is not limited to, the content of posts and the number of followers. For example, if the debtor indicates financial difficulties on social media, the chat unit can send a message suggesting a payment deferral. Furthermore, if the debtor indicates on social media that they have gotten a new job, the chat unit can send a message encouraging early payment. Furthermore, if the debtor indicates on social media that they are traveling, the chat unit can send a message encouraging payment after the trip. This allows for more effective collection efforts by customizing messages based on social media activity. Some or all of the above-described processing in the chat unit may be performed using, or without, AI. For example, the chat unit can input data on the debtor's social media activity into a generation AI and have the generation AI customize the messages.

[0039] The chat unit can optimize the content and sending method of messages by reflecting the debtor's past feedback. Examples of feedback include, but are not limited to, surveys and reviews. For example, if the debtor has previously preferred email reminders, the chat unit can send messages by email. Furthermore, if the debtor has previously preferred phone reminders, the chat unit can send messages by phone. Furthermore, if the debtor has previously preferred softer language, the chat unit can send messages that reflect that softer language. This enables more effective reminders by optimizing messages based on past feedback. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or may be performed without AI. For example, the chat unit can input the debtor's past feedback into a generation AI and have the generation AI optimize the messages.

[0040] The analysis unit can analyze the debtor's response content and evaluate the debtor's willingness and ability to pay. Evaluations of willingness and ability to pay include, but are not limited to, past payment history and credit score. For example, if the debtor proposes a payment plan, the analysis unit can analyze in detail the feasibility of the plan. If the debtor refuses to pay, the analysis unit can also analyze in detail the reasons for the refusal and consider countermeasures. Furthermore, if the debtor promises to pay, the analysis unit can also analyze in detail the reliability of the promise. Thus, by analyzing the response content in detail, the debtor's willingness and ability to pay can be accurately evaluated. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the debtor's response content into a generation AI and have the generation AI evaluate the debtor's willingness and ability to pay.

[0041] The analysis unit can classify the debtor's responses into categories and propose appropriate countermeasures. Examples of categories include, but are not limited to, "willing to pay," "unwilling to pay," and "payment plan proposal." For example, the analysis unit can categorize the debtor's responses into categories such as "willing to pay," "unwilling to pay," and "payment plan proposal." The analysis unit can also propose appropriate countermeasures for each category. Furthermore, the analysis unit can analyze the responses for each category and propose optimal countermeasures. By categorizing the responses into categories, optimal countermeasures can be proposed. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the debtor's responses into a generation AI and have the generation AI classify them into categories and propose countermeasures.

[0042] The analysis unit can improve the accuracy of the analysis based on the debtor's past response history. The response history includes, but is not limited to, past messages and call records. For example, the analysis unit analyzes the content of the current response based on the debtor's past response history. The analysis unit can also evaluate the debtor's willingness and ability to pay from the debtor's past response history. Furthermore, the analysis unit can also suggest optimal countermeasures by referring to the debtor's past response history. This enables more accurate responses by improving the accuracy of the analysis based on the past response history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the debtor's past response history into the generation AI and have the generation AI improve the accuracy of the analysis.

[0043] The analysis unit can analyze the debtor's response content in relation to geographical factors. Geographical factors include, but are not limited to, regional economic conditions and cultural background. For example, if the debtor lives in an urban area, the analysis unit can analyze the response content taking into account the economic conditions specific to the urban area. Furthermore, if the debtor lives in a rural area, the analysis unit can analyze the response content taking into account the economic conditions specific to the rural area. Furthermore, if the debtor lives overseas, the analysis unit can analyze the response content taking into account the economic conditions and culture of the country. Thus, analyzing the response content taking into account geographical factors enables more appropriate responses. Some or all of the above-described processing by the analysis unit may be performed, for example, using AI, or may be performed without AI. For example, the analysis unit can input data on the debtor's geographical factors into the generation AI and have the generation AI analyze the response content.

[0044] The analysis unit can improve the accuracy of the analysis by referring to relevant literature and past data on the debtor. Examples of relevant literature and past data include, but are not limited to, academic papers, industry reports, past transaction history, and customer information. The analysis unit, for example, refers to relevant literature on the debtor to analyze the response content in detail. The analysis unit can also refer to past data on the debtor to evaluate the debtor's willingness and ability to repay. Furthermore, the analysis unit can propose optimal countermeasures based on the debtor's relevant literature and past data. By referring to relevant literature and past data, the accuracy of the analysis can be improved, enabling more appropriate responses. Some or all of the above-described processing by the analysis unit can be performed, for example, using AI, or without AI. For example, the analysis unit can input relevant literature and past data on the debtor into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0045] The analysis unit can perform analysis based on the debtor's market value and credit information. Examples of market value and credit information include, but are not limited to, stock prices, industry rankings, credit scores, and credit reports. The analysis unit, for example, evaluates the debtor's market value and analyzes their ability to repay. The analysis unit can also evaluate the debtor's willingness and ability to repay by referring to the debtor's credit information. Furthermore, the analysis unit can propose optimal countermeasures based on the debtor's market value and credit information. This allows for accurate evaluation of the debtor's willingness and ability to repay by taking market value and credit information into consideration. Some or all of the above-described processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can input data on the debtor's market value and credit information into the generation AI and have the generation AI perform the analysis.

[0046] The telephone response unit can analyze the debtor's tone of voice and language and provide an appropriate response. Analysis of tone of voice and language includes, but is not limited to, voice frequency, volume, words used, and grammatical structure. For example, if the debtor's voice tone is high, the telephone response unit can select appropriate language to encourage a calm response. Furthermore, if the debtor's voice tone is low, the telephone response unit can select gentle language to reassure the debtor. Furthermore, if the debtor's language is polite, the telephone response unit can also respond using polite language. Thus, analyzing tone of voice and language enables a more appropriate response. Some or all of the above-described processing in the telephone response unit may be performed using, for example, AI, or may be performed without AI. For example, the telephone response unit can input the debtor's voice data into a generation AI and have the generation AI select an appropriate response.

[0047] The telephone response unit can select the optimal response method by referring to the debtor's past telephone response history. The telephone response history includes, but is not limited to, past call records and response content. For example, if the debtor has made prompt payments in the past, the telephone response unit may respond by expressing gratitude. Furthermore, if the debtor has previously refused to pay, the telephone response unit may select a response method taking into account the reason for the refusal. Furthermore, if the debtor has previously proposed a payment plan, the telephone response unit may respond based on that plan. This enables more effective responses by selecting the optimal response method based on the past telephone response history. Some or all of the above-described processing in the telephone response unit may be performed using, for example, AI, or may be performed without AI. For example, the telephone response unit may input the debtor's past telephone response history into a generation AI and have the generation AI select the optimal response method.

[0048] The telephone response unit can customize the content of the telephone response based on the debtor's current situation. Current situations include, but are not limited to, income and expenditure status. For example, if the debtor's income is decreasing, the telephone response unit can provide a telephone response proposing a flexible payment plan. Furthermore, if the debtor's ability to repay is high, the telephone response unit can also provide a telephone response encouraging early payment. Furthermore, if the debtor's financial situation is unstable, the telephone response unit can provide a telephone response proposing a payment deferral. This enables more effective response by providing a telephone response tailored to the current situation. Some or all of the above-described processing in the telephone response unit may be performed, for example, using AI, or may be performed without AI. For example, the telephone response unit can input data on the debtor's current situation into the generation AI and have the generation AI customize the content of the telephone response.

[0049] The telephone response unit can provide different telephone responses for each region based on the debtor's geographical location information. Geographical location information includes, but is not limited to, GPS data and address information. For example, if the debtor lives in an urban area, the telephone response unit can provide telephone responses that take into account the economic conditions specific to that area. Furthermore, if the debtor lives in a rural area, the telephone response unit can provide telephone responses that take into account the economic conditions specific to that area. Furthermore, if the debtor lives overseas, the telephone response unit can provide telephone responses that take into account the economic conditions and culture of that country. This allows for more effective telephone responses by providing telephone responses that take into account the economic conditions of each region. Some or all of the above-described processing in the telephone response unit may be performed, for example, using AI, or may be performed without AI. For example, the telephone response unit can input the debtor's geographical location information into a generation AI and have the generation AI perform different telephone responses for each region.

[0050] The call handling unit can analyze the debtor's social media activity and customize call responses based on related information. Social media activity includes, but is not limited to, the content of posts and the number of followers. For example, if the debtor indicates financial difficulties on social media, the call handling unit can call the debtor offering a payment deferral. Furthermore, if the debtor indicates on social media that they have found a new job, the call handling unit can call the debtor encouraging early payment. Furthermore, if the debtor indicates on social media that they are traveling, the call handling unit can call the debtor encouraging payment after their trip. Customizing call responses based on social media activity enables more effective responses. Some or all of the above-described processing in the call handling unit may be performed using, for example, AI, or without AI. For example, the call handling unit can input data on the debtor's social media activity into a generation AI and have the generation AI customize the call responses.

[0051] The telephone response unit can optimize the content and method of telephone responses by reflecting the debtor's past feedback. Examples of feedback include, but are not limited to, surveys and reviews. For example, if the debtor has preferred email reminders in the past, the telephone response unit can prioritize email reminders. Furthermore, if the debtor has preferred telephone reminders in the past, the telephone response unit can prioritize telephone reminders. Furthermore, if the debtor has preferred softer language in the past, the telephone response unit can reflect that softer language in its telephone responses. This enables more effective responses by optimizing telephone responses based on past feedback. Some or all of the above-described processing in the telephone response unit may be performed using, for example, AI, or may be performed without AI. For example, the telephone response unit can input the debtor's past feedback into a generation AI and have the generation AI optimize telephone responses.

[0052] The fund utilization unit can formulate a detailed plan for using the procured funds and allocate them optimally. Examples of such plans include, but are not limited to, budget allocations and project plans. For example, the fund utilization unit can formulate a plan for allocating the procured funds to strengthening a lending system for financial institutions. The fund utilization unit can also formulate a plan for allocating the procured funds to the international expansion of the business. Furthermore, the fund utilization unit can also formulate a plan for allocating the procured funds to launching a new business. By formulating a detailed plan for using the funds, optimal allocation of funds becomes possible. Some or all of the above-described processing in the fund utilization unit may be performed using, for example, AI, or without AI. For example, the fund utilization unit can input the procured funds usage plan into a generation AI and have the generation AI execute optimal fund allocation.

[0053] The fund utilization unit can monitor fund usage in real time and make adjustments as necessary. Examples of monitoring include, but are not limited to, real-time data collection and analysis. For example, the fund utilization unit can monitor fund usage in real time and make adjustments if a budget overrun occurs. The fund utilization unit can also monitor fund usage in real time and reallocate unused funds to other projects. Furthermore, the fund utilization unit can monitor fund usage in real time and confirm whether it is progressing as planned. This allows for appropriate fund usage management through real-time monitoring. Some or all of the above-described processing in the fund utilization unit may be performed using, for example, AI, or may be performed without AI. For example, the fund utilization unit can input fund usage data into a generation AI and have the generation AI perform monitoring and adjustments.

[0054] The fund utilization unit can evaluate the effectiveness of fund utilization and reflect it in the next fundraising plan. Examples of evaluations of utilization effectiveness include, but are not limited to, ROI (return on investment) and KPI (key performance indicator). For example, the fund utilization unit can evaluate the effectiveness of fund utilization and prioritize allocation of the next fund to successful projects. The fund utilization unit can also evaluate the effectiveness of fund utilization and implement improvement measures for failed projects. Furthermore, the fund utilization unit can evaluate the effectiveness of fund utilization and reflect it in the next fundraising plan. Thus, by evaluating utilization effectiveness, the next fundraising plan can be optimized. Some or all of the above-described processing in the fund utilization unit may be performed, for example, using AI or without AI. For example, the fund utilization unit can input data on the effectiveness of fund utilization into a generation AI and have the generation AI perform an evaluation and reflect the results in the next fundraising plan.

[0055] The fund utilization unit can collect feedback regarding the use of funds and identify areas for improvement. Examples of feedback include, but are not limited to, surveys and reviews. For example, the fund utilization unit can collect feedback regarding the use of funds and identify areas for improvement. The fund utilization unit can also improve the next fund allocation plan based on the feedback regarding the use of funds. Furthermore, the fund utilization unit can analyze the feedback regarding the use of funds and identify the optimal fund allocation method. In this way, the method of using funds can be improved by collecting feedback. Some or all of the above-mentioned processing in the fund utilization unit may be performed using, for example, AI, or may be performed without using AI. For example, the fund utilization unit can input feedback data into a generation AI and have the generation AI identify areas for improvement.

[0056] The fund utilization unit can diversify the purposes for which the raised funds are used to diversify risk. Examples of purposes for which the funds are used include, but are not limited to, research and development and marketing. For example, the fund utilization unit distributes the raised funds among multiple projects. The fund utilization unit can also distribute the raised funds among different industries or regions. Furthermore, the fund utilization unit can distribute the raised funds among short-term and long-term projects. This enables risk diversification by diversifying the purposes for which the funds are used. Some or all of the above-described processing in the fund utilization unit may be performed using, for example, AI, or may be performed without using AI. For example, the fund utilization unit can input data on the purposes for which the funds are used into the generation AI and have the generation AI execute a risk diversification plan.

[0057] The fund utilization department may prepare detailed reports to increase transparency regarding the use of funds. Evaluation of transparency may include, but is not limited to, the preparation of detailed reports and the scope of public information. For example, the fund utilization department may periodically prepare reports detailing the use of funds. The fund utilization department may also prepare reports that clearly indicate the purpose and effect of the use of funds. Furthermore, the fund utilization department may make the reports public to increase transparency regarding the use of funds. In this way, the preparation of detailed reports improves transparency regarding the use of funds. Some or all of the above-described processing in the fund utilization department may be performed, for example, using AI or may be performed without using AI. For example, the fund utilization department may have a generation AI execute the preparation of the reports.

[0058] The fund utilization department can conduct an external audit on the use of funds to ensure reliability. Examples of external audits include, but are not limited to, the frequency of audits and the items to be audited. For example, the fund utilization department can request an external auditing organization to conduct an audit on the use of funds. The fund utilization department can also identify areas for improvement based on the results of the external audit on the use of funds. Furthermore, the fund utilization department can also make the results of the external audit on the use of funds public to ensure reliability. Thus, conducting an external audit improves reliability on the use of funds. Some or all of the above-described processing in the fund utilization department can be performed, for example, using AI or without AI. For example, the fund utilization department can input the results of the external audit into the generation AI and have the generation AI identify areas for improvement and ensure reliability.

[0059] The fund utilization unit can optimize the next fund utilization plan by reflecting user feedback regarding fund usage. Examples of feedback include, but are not limited to, surveys and reviews. For example, the fund utilization unit collects user feedback and reflects it in the next fund utilization plan. The fund utilization unit can also improve the fund allocation method based on the user feedback. Furthermore, the fund utilization unit can analyze the user feedback and formulate an optimal fund utilization plan. Thus, the next fund utilization plan can be optimized by reflecting the user feedback. Some or all of the above-described processing in the fund utilization unit may be performed, for example, using AI or without AI. For example, the fund utilization unit can input user feedback data into a generation AI and cause the generation AI to optimize the next fund utilization plan.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The debt collection system can further include a credit information acquisition unit that acquires the debtor's credit information. The credit information acquisition unit collects the debtor's credit score and past payment history and provides them to the analysis unit. For example, the credit information acquisition unit acquires the debtor's credit score, and the analysis unit evaluates the debtor's ability to repay based on that information. The credit information acquisition unit can also acquire the debtor's past payment history, and the analysis unit can evaluate the debtor's willingness to repay based on that history. Furthermore, the credit information acquisition unit can acquire the debtor's credit report, and the analysis unit can propose the optimal collection method based on that report. In this way, by utilizing the debtor's credit information, it is possible to more accurately evaluate the debtor's ability and willingness to repay.

[0062] The debt collection system can further include a lifestyle pattern analysis unit that analyzes the debtor's lifestyle patterns. The lifestyle pattern analysis unit analyzes the debtor's lifestyle rhythm and spending patterns and provides the results to the chat unit. For example, the lifestyle pattern analysis unit analyzes the debtor's spending patterns and evaluates their ability to repay. The lifestyle pattern analysis unit can also analyze the debtor's lifestyle rhythm and suggest the optimal timing for sending a reminder message. Furthermore, the lifestyle pattern analysis unit can analyze the debtor's lifestyle situation and suggest a flexible payment plan. This makes it possible to make reminders that take into account the debtor's lifestyle patterns.

[0063] The debt collection system can further include a location information acquisition unit that acquires the debtor's geographic location information. The location information acquisition unit collects the debtor's GPS data and address information and provides it to the analysis unit. For example, if the debtor lives in an urban area, the location information acquisition unit can perform analysis taking into account the economic conditions specific to urban areas. In addition, if the debtor lives in a rural area, the location information acquisition unit can also perform analysis taking into account the economic conditions specific to rural areas. Furthermore, if the debtor lives overseas, the location information acquisition unit can perform analysis taking into account the economic conditions and culture of the country. This makes it possible to perform analysis that takes geographical factors into account.

[0064] The debt collection system can further include a social media analysis unit that analyzes the debtor's social media activity. The social media analysis unit analyzes the content of the debtor's posts and the number of followers, and provides the results to the chat unit. For example, if the social media analysis unit indicates that the debtor is experiencing financial difficulties, it can send a message suggesting a payment deferral. If the social media analysis unit indicates that the debtor has gotten a new job, it can also send a message urging early payment. Furthermore, if the social media analysis unit indicates that the debtor is traveling, it can also send a message urging payment after the debtor has traveled. This makes it possible to send debt collection messages based on social media activity.

[0065] The debt collection system can further include a feedback reflection unit that reflects the debtor's past feedback and optimizes the content and sending method of messages. The feedback reflection unit collects debtor surveys and reviews and provides them to the chat unit. For example, if the debtor has preferred to be reminded by email in the past, the feedback reflection unit can send a message by email. Also, if the debtor has preferred to be reminded by phone in the past, the feedback reflection unit can send a message by phone. Furthermore, if the debtor has preferred softer language in the past, the feedback reflection unit can send a message that reflects that language. This makes it possible to provide optimal reminders based on past feedback.

[0066] The debt collection system can further include a history reference unit that references the debtor's past telephone response history to select the optimal response method. The history reference unit collects the debtor's past call records and response content and provides them to the telephone response unit. For example, if the debtor has made prompt payments in the past, the history reference unit may respond by expressing gratitude. In addition, if the debtor has refused to pay in the past, the history reference unit may select a response method by taking into account the reason. Furthermore, if the debtor has proposed a payment plan in the past, the history reference unit may respond based on that plan. This makes it possible to optimally respond based on the debtor's past telephone response history.

[0067] The debt collection system can further include a situation customization unit that customizes the content of telephone responses based on the debtor's current situation. The situation customization unit collects the debtor's income and expenditure status and provides it to the telephone response unit. For example, if the debtor's income is decreasing, the situation customization unit can respond by phone to propose a flexible payment plan. Also, if the debtor's ability to pay is high, the situation customization unit can respond by phone to encourage early payment. Furthermore, if the debtor's financial situation is unstable, the situation customization unit can respond by phone to propose a payment grace period. This makes it possible to respond by phone according to the current situation.

[0068] The processing flow of the first embodiment will be briefly explained below.

[0069] Step 1: The chat module receives responses from the debtor. Responses from the debtor include text messages and voice messages. The chat module sends a reminder message to the debtor and receives a response from the debtor. The chat module can also estimate the debtor's emotions and adjust the content and timing of the reminder message based on the estimated emotions. Step 2: The analysis unit analyzes the responses received by the chat unit. The analysis is performed using methods such as natural language processing technology and sentiment analysis. The analysis unit analyzes the debtor's responses and takes appropriate action. It can also estimate the debtor's emotions and adjust the analysis method for the responses based on the estimated emotions. Step 3: The telephone response department responds to the call based on the responses analyzed by the analysis department. The call is handled by methods such as an automated response using AI or by an operator. The telephone response department can also estimate the debtor's emotions and adjust the content and timing of the call based on the estimated emotions. Step 4: The Fund Utilization Department utilizes the raised funds. Fund utilization is carried out in ways such as strengthening the lending system for financial institutions and expanding the business internationally. The Fund Utilization Department utilizes the raised funds in ways such as strengthening the lending system for financial institutions and expanding the business internationally.

[0070] (Example 2) A debt collection system according to an embodiment of the present invention automates communication with debtors to speedily and efficiently execute the debt collection process. The debt collection system includes a chat unit that receives responses from debtors, an analysis unit that analyzes the responses received by the chat unit, a telephone response unit that responds to calls based on the responses analyzed by the analysis unit, and a fund utilization unit that utilizes procured funds. For example, the debt collection system uses a chatbot to send a dunning message to the debtor and receive a response from the debtor. The debt collection system then analyzes the response received by the chatbot and takes appropriate action. For example, if the debtor proposes a payment plan, the chatbot records the proposal and notifies the financial institution as necessary. Furthermore, the debt collection system uses AI to automate telephone responses and streamline telephone interactions with debtors. For example, AI can analyze the debtor's voice and generate appropriate dunning messages. This allows the debt collection system to modernize the debt collection process without relying on traditional methods and optimize corporate profitability and cash flow. This allows the debt collection system to centrally manage communication with debtors and speedily and efficiently execute the dunning process. For example, by utilizing chatbots and AI, the time and cost required for collection work can be reduced, and debt collection can be carried out efficiently. The funds raised will also be used for various purposes, such as strengthening the lending system for main financial institutions and expanding business internationally.

[0071] The debt collection system according to the embodiment includes a chat unit, an analysis unit, a telephone response unit, and a fund utilization unit. The chat unit receives responses from the debtor. Responses from the debtor include, but are not limited to, text messages, voice messages, and the like. The chat unit, for example, sends a dunning message to the debtor and receives a response from the debtor. The chat unit can also estimate the debtor's emotions and adjust the content and timing of the dunning message based on the estimated emotions. For example, if the debtor is feeling stressed, the chat unit can send the dunning message using gentle language and delay the timing of the message. The analysis unit analyzes the responses received by the chat unit. The analysis can be performed using, for example, natural language processing technology or emotion analysis, but is not limited to, these examples. For example, the analysis unit analyzes the content of the debtor's response and takes an appropriate action. The analysis unit can also estimate the debtor's emotions and adjust the analysis method for the response based on the estimated emotions. For example, if the debtor is angry, the response content can be analyzed in detail to encourage the debtor to respond calmly. The telephone response unit responds to the telephone call based on the response analyzed by the analysis unit. The telephone response may be, for example, an automated response using AI or a response by an operator, but is not limited to these examples. For example, the telephone response unit automates telephone responses with debtors using AI. The telephone response unit may also estimate the debtor's emotions and adjust the content and timing of the telephone response based on the estimated debtor's emotions. For example, if the debtor is angry, the telephone response unit adjusts the content of the telephone response to encourage a calm response. The fund utilization unit utilizes the procured funds. Fund utilization may be, for example, for strengthening the loan system for financial institutions or for international business expansion, but is not limited to these examples. For example, the fund utilization unit utilizes the procured funds to strengthen the loan system for financial institutions. The fund utilization unit may also utilize the procured funds for international business expansion. As a result, the debt collection system according to the embodiment automates communication with debtors and enables the collection process to be carried out quickly and effectively.

[0072] The chat unit can send a reminder message to the debtor and accept a response from the debtor. Examples of reminder messages include, but are not limited to, a payment deadline notification and payment method instructions. The chat unit can also send a payment deadline notification to the debtor and accept a response from the debtor. The chat unit can also send payment method instructions to the debtor and accept a response from the debtor. For example, the chat unit can send a message explaining details of the payment method and respond to questions from the debtor. This automates communication with the debtor and enables efficient sending of reminder messages. Some or all of the above-described processing in the chat unit can be performed using, for example, AI, or can be performed without using AI. For example, the chat unit can cause a generation AI to execute a process of sending reminder messages to the debtor.

[0073] The analysis unit can analyze the debtor's response and take appropriate action. Examples of analysis include, but are not limited to, natural language processing technology and sentiment analysis. For example, the analysis unit can analyze the debtor's response using natural language processing technology and take appropriate action. The analysis unit can also analyze the debtor's response using sentiment analysis and take appropriate action. For example, if the debtor proposes a payment plan, the analysis unit records the plan and notifies the financial institution as necessary. If the debtor refuses to pay, the analysis unit can analyze the reason and consider countermeasures. For example, if the debtor promises to pay, the analysis unit analyzes the reliability of the promise. By analyzing the debtor's response and taking appropriate action, efficient collection can be achieved. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the debtor's response to a generation AI and have the generation AI output the analysis results.

[0074] The telephone response unit can use AI to automate telephone responses with debtors. Examples of telephone responses include, but are not limited to, automated responses using AI or responses by operators. The telephone response unit can also use AI to automate telephone responses with debtors. The telephone response unit can also analyze the debtor's voice and generate appropriate dunning messages. For example, the telephone response unit can analyze the debtor's tone of voice and language and respond appropriately. By utilizing AI, this makes it possible to automate and streamline telephone responses with debtors. Some or all of the above-described processing in the telephone response unit can be performed using AI, or can be performed without using AI. For example, the telephone response unit can input the debtor's voice data into a generation AI and have the generation AI generate an appropriate dunning message.

[0075] The fund utilization department can utilize the procured funds to strengthen the lending system for financial institutions and to expand the business internationally. Examples of fund utilization include, but are not limited to, strengthening the lending system for financial institutions and expanding the business internationally. For example, the fund utilization department utilizes the procured funds to strengthen the lending system for financial institutions. The fund utilization department can also utilize the procured funds for expanding the business internationally. For example, the fund utilization department allocates funds to upgrading the lending system for financial institutions and adding new functions. The fund utilization department can also allocate funds to entering new markets and building international partnerships. This effectively utilizes the procured funds to strengthen the lending system for financial institutions and expand the business internationally. Some or all of the above-described processing in the fund utilization department may be performed using, for example, AI, or may be performed without using AI. For example, the fund utilization department can input a fund allocation plan into the generation AI and have the generation AI execute the optimal fund allocation.

[0076] The chat unit can estimate the debtor's emotions and adjust the content and timing of sending a reminder message based on the estimated debtor's emotions. Emotion estimation includes, but is not limited to, text analysis and voice analysis. For example, the chat unit analyzes the debtor's text messages to estimate emotions. The chat unit can also analyze the debtor's voice messages to estimate emotions. For example, if the debtor is stressed, the chat unit can send a reminder message using gentle language and delay the timing of sending. If the debtor is relaxed, the chat unit can send a message proposing a detailed payment plan and speed up the timing of sending. Furthermore, if the debtor is in a hurry, the chat unit can send a message encouraging a concise and prompt response and send it immediately. This enables more effective reminder messages by adjusting the content and timing of sending a reminder message based on the debtor's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the chat section may be performed using AI, or may be performed without AI. For example, the chat section may input the debtor's text message into the generation AI and have the generation AI estimate the debtor's emotions.

[0077] The chat unit can analyze the debtor's past response history and generate a dunning message. Response history includes, but is not limited to, past messages and call records. For example, if the debtor has previously delayed payments, the chat unit can generate a message emphasizing the payment deadline. Furthermore, if the debtor has previously made prompt payments, the chat unit can generate a message expressing gratitude. Furthermore, if the debtor has previously proposed a payment plan, the chat unit can generate a message based on that plan. This enables effective dunning by generating an optimal dunning message based on the past response history. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or without AI. For example, the chat unit can input the debtor's past response history into a generation AI and have the generation AI generate an optimal dunning message.

[0078] The chat unit can customize the content of messages based on the debtor's current financial situation and repayment capacity. Examples of financial situation and repayment capacity include, but are not limited to, income, expenses, and asset status. For example, if the debtor's income is decreasing, the chat unit can send a message proposing a flexible payment plan. Furthermore, if the debtor's repayment capacity is high, the chat unit can also send a message encouraging early payment. Furthermore, if the debtor's financial situation is unstable, the chat unit can also send a message proposing a payment deferral. This enables more effective collection by sending messages tailored to the debtor's financial situation and repayment capacity. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or may be performed without AI. For example, the chat unit can input data on the debtor's financial situation and repayment capacity into the generation AI and have the generation AI customize the messages.

[0079] The chat unit can automatically set the timing for sending the next dunning message based on the debtor's response. Examples of the timing for sending the next dunning message include, but are not limited to, a time period or a day of the week. For example, if the debtor promises to pay, the chat unit can set the timing for sending the next dunning message based on the promised date. Furthermore, if the debtor refuses to pay, the chat unit can set the timing for sending another dunning message after a certain period of time. Furthermore, if the debtor proposes a payment plan, the chat unit can set the timing for sending the next dunning message based on the plan. This enables effective dunning by setting the timing for sending the next dunning message based on the debtor's response. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or without AI. For example, the chat unit can input the debtor's response into a generation AI and have the generation AI set the timing for sending the next dunning message.

[0080] The summary generation unit generates a summary that captures the emotional nuances of the answer and can reflect the emotional elements in the evaluation. For example, the summary generation unit captures the emotional nuances of the answer when the generation AI summarizes. For example, the summary generation unit generates a summary based on an emotional score. The summary generation unit can also build a system in which the generation AI reflects the emotional elements of the answer in the evaluation. For example, the summary generation unit performs the evaluation based on the emotional score. The summary generation unit can also develop an algorithm for the generation AI to generate a summary that captures the emotional nuances of the answer. For example, the summary generation unit generates a summary based on the emotional score and reflects it in the evaluation. In this way, by generating a summary that captures the emotional nuances, the emotional elements can also be reflected in the evaluation. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Furthermore, the summary generation unit can combine multiple emotion estimation technologies to capture emotional nuances. For example, the summary generation unit can combine technologies such as facial expression recognition, speech analysis, and text analysis to more accurately capture emotional nuances. The summary generation unit can also establish a feedback loop to reflect emotional elements in the evaluation. For example, the summary generation unit evaluates the emotional elements of the generated summary and updates the emotion estimation algorithm based on the evaluation results. This allows the summary generation unit to always provide summaries that capture emotional nuances based on the latest emotion estimation technology. Furthermore, the summary generation unit has a function to visually display emotional elements. For example, the summary generation unit can display emotion scores as graphs or charts to provide them in a visually easy-to-understand format. The summary generation unit can also provide feedback to point out areas for improvement in the answer based on the emotional elements. For example, the summary generation unit can identify areas where emotional nuances are lacking or excessive and suggest specific areas for improvement. This not only allows the system to provide summaries that capture emotional nuances but also provides feedback to improve the quality of the answer.

[0081] The chat unit can send different dunning messages for each region based on the debtor's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and address information. For example, if the debtor lives in an urban area, the chat unit can send a message that takes into account the economic conditions specific to that area. For example, if the debtor lives in a rural area, the chat unit can send a message that takes into account the economic conditions specific to that area. Furthermore, if the debtor lives overseas, the chat unit can send a message that takes into account the economic conditions and culture of that country. This enables more effective dunning by sending messages that take into account the economic conditions of each region. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or may be performed without AI. For example, the chat unit can input the debtor's geographical location information into a generation AI and have the generation AI generate different dunning messages for each region.

[0082] The chat unit can analyze the debtor's social media activity and customize messages based on relevant information. Social media activity includes, but is not limited to, the content of posts and the number of followers. For example, if the debtor indicates financial difficulties on social media, the chat unit can send a message suggesting a payment deferral. Furthermore, if the debtor indicates on social media that they have gotten a new job, the chat unit can send a message encouraging early payment. Furthermore, if the debtor indicates on social media that they are traveling, the chat unit can send a message encouraging payment after the trip. This allows for more effective collection efforts by customizing messages based on social media activity. Some or all of the above-described processing in the chat unit may be performed using, or without, AI. For example, the chat unit can input data on the debtor's social media activity into a generation AI and have the generation AI customize the messages.

[0083] The chat unit can optimize the content and sending method of messages by reflecting the debtor's past feedback. Examples of feedback include, but are not limited to, surveys and reviews. For example, if the debtor has previously preferred email reminders, the chat unit can send messages by email. Furthermore, if the debtor has previously preferred phone reminders, the chat unit can send messages by phone. Furthermore, if the debtor has previously preferred softer language, the chat unit can send messages that reflect that softer language. This enables more effective reminders by optimizing messages based on past feedback. Some or all of the above-described processing in the chat unit may be performed using, for example, AI, or may be performed without AI. For example, the chat unit can input the debtor's past feedback into a generation AI and have the generation AI optimize the messages.

[0084] The analysis unit can estimate the debtor's emotions and adjust the analysis method of the response content based on the estimated debtor's emotions. Emotion estimation includes, but is not limited to, text analysis and voice analysis. For example, the analysis unit analyzes the debtor's text messages to estimate emotions. The analysis unit can also analyze the debtor's voice messages to estimate emotions. For example, if the debtor is angry, the analysis unit can analyze the response content in detail to encourage a calm response. If the debtor is relaxed, the analysis unit can perform a concise analysis and respond quickly. Furthermore, if the debtor is anxious, the analysis unit can carefully analyze the response content to reassure the debtor. This allows for more appropriate responses by adjusting the analysis method according to the debtor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the debtor's text message into the generation AI and have the generation AI estimate the debtor's emotions.

[0085] The analysis unit can analyze the debtor's response content and evaluate the debtor's willingness and ability to pay. Evaluations of willingness and ability to pay include, but are not limited to, past payment history and credit score. For example, if the debtor proposes a payment plan, the analysis unit can analyze in detail the feasibility of the plan. If the debtor refuses to pay, the analysis unit can also analyze in detail the reasons for the refusal and consider countermeasures. Furthermore, if the debtor promises to pay, the analysis unit can also analyze in detail the reliability of the promise. Thus, by analyzing the response content in detail, the debtor's willingness and ability to pay can be accurately evaluated. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the debtor's response content into a generation AI and have the generation AI evaluate the debtor's willingness and ability to pay.

[0086] The analysis unit can classify the debtor's responses into categories and propose appropriate countermeasures. Examples of categories include, but are not limited to, "willing to pay," "unwilling to pay," and "payment plan proposal." For example, the analysis unit can categorize the debtor's responses into categories such as "willing to pay," "unwilling to pay," and "payment plan proposal." The analysis unit can also propose appropriate countermeasures for each category. Furthermore, the analysis unit can analyze the responses for each category and propose optimal countermeasures. By categorizing the responses into categories, optimal countermeasures can be proposed. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the debtor's responses into a generation AI and have the generation AI classify them into categories and propose countermeasures.

[0087] The analysis unit can improve the accuracy of the analysis based on the debtor's past response history. The response history includes, but is not limited to, past messages and call records. For example, the analysis unit analyzes the content of the current response based on the debtor's past response history. The analysis unit can also evaluate the debtor's willingness and ability to pay from the debtor's past response history. Furthermore, the analysis unit can also suggest optimal countermeasures by referring to the debtor's past response history. This enables more accurate responses by improving the accuracy of the analysis based on the past response history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the debtor's past response history into the generation AI and have the generation AI improve the accuracy of the analysis.

[0088] The analysis unit can estimate the debtor's emotions and adjust the display method of the analysis results based on the estimated debtor's emotions. Emotion estimation includes, but is not limited to, text analysis and voice analysis. For example, the analysis unit analyzes the debtor's text messages to estimate emotions. The analysis unit can also analyze the debtor's voice messages to estimate emotions. For example, if the debtor is angry, the analysis results can be displayed in detail to encourage a calm response. If the debtor is relaxed, the analysis results can be displayed concisely. Furthermore, if the debtor is anxious, the analysis results can be displayed in a detailed manner to reassure the debtor. This allows for more appropriate responses by adjusting the display method of the analysis results according to the debtor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the debtor's text message into the generation AI and have the generation AI estimate emotions and adjust the way the analysis results are displayed.

[0089] The analysis unit can analyze the debtor's response content in relation to geographical factors. Geographical factors include, but are not limited to, regional economic conditions and cultural background. For example, if the debtor lives in an urban area, the analysis unit can analyze the response content taking into account the economic conditions specific to the urban area. Furthermore, if the debtor lives in a rural area, the analysis unit can analyze the response content taking into account the economic conditions specific to the rural area. Furthermore, if the debtor lives overseas, the analysis unit can analyze the response content taking into account the economic conditions and culture of the country. Thus, analyzing the response content taking into account geographical factors enables more appropriate responses. Some or all of the above-described processing by the analysis unit may be performed, for example, using AI, or may be performed without AI. For example, the analysis unit can input data on the debtor's geographical factors into the generation AI and have the generation AI analyze the response content.

[0090] The analysis unit can improve the accuracy of the analysis by referring to relevant literature and past data on the debtor. Examples of relevant literature and past data include, but are not limited to, academic papers, industry reports, past transaction history, and customer information. The analysis unit, for example, refers to relevant literature on the debtor to analyze the response content in detail. The analysis unit can also refer to past data on the debtor to evaluate the debtor's willingness and ability to repay. Furthermore, the analysis unit can propose optimal countermeasures based on the debtor's relevant literature and past data. By referring to relevant literature and past data, the accuracy of the analysis can be improved, enabling more appropriate responses. Some or all of the above-described processing by the analysis unit can be performed, for example, using AI, or without AI. For example, the analysis unit can input relevant literature and past data on the debtor into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0091] The analysis unit can perform analysis based on the debtor's market value and credit information. Examples of market value and credit information include, but are not limited to, stock prices, industry rankings, credit scores, and credit reports. The analysis unit, for example, evaluates the debtor's market value and analyzes their ability to repay. The analysis unit can also evaluate the debtor's willingness and ability to repay by referring to the debtor's credit information. Furthermore, the analysis unit can propose optimal countermeasures based on the debtor's market value and credit information. This allows for accurate evaluation of the debtor's willingness and ability to repay by taking market value and credit information into consideration. Some or all of the above-described processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can input data on the debtor's market value and credit information into the generation AI and have the generation AI perform the analysis.

[0092] The telephone response unit can estimate the debtor's emotions and adjust the content and timing of the telephone response based on the estimated debtor's emotions. Emotion estimation includes, but is not limited to, voice analysis and text analysis. For example, the telephone response unit analyzes the debtor's tone of voice and vocabulary to estimate emotions. The telephone response unit can also analyze the debtor's text messages to estimate emotions. For example, if the debtor is angry, the telephone response unit can adjust the content of the telephone response to encourage a calm response. If the debtor is relaxed, the telephone response unit can propose a detailed payment plan. Furthermore, if the debtor is anxious, the telephone response unit can carefully adjust the content of the telephone response to reassure the debtor. This enables more effective responses by adjusting the content and timing of the telephone response according to the debtor's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the telephone response unit may be performed using, for example, AI, or without AI. For example, the telephone response department can input the debtor's voice data into the generation AI and have the generation AI estimate the debtor's emotions and adjust the content and timing of the telephone response.

[0093] The telephone response unit can analyze the debtor's tone of voice and language and provide an appropriate response. Analysis of tone of voice and language includes, but is not limited to, voice frequency, volume, words used, and grammatical structure. For example, if the debtor's voice tone is high, the telephone response unit can select appropriate language to encourage a calm response. Furthermore, if the debtor's voice tone is low, the telephone response unit can select gentle language to reassure the debtor. Furthermore, if the debtor's language is polite, the telephone response unit can also respond using polite language. Thus, analyzing tone of voice and language enables a more appropriate response. Some or all of the above-described processing in the telephone response unit may be performed using, for example, AI, or may be performed without AI. For example, the telephone response unit can input the debtor's voice data into a generation AI and have the generation AI select an appropriate response.

[0094] The telephone response unit can select the optimal response method by referring to the debtor's past telephone response history. The telephone response history includes, but is not limited to, past call records and response content. For example, if the debtor has made prompt payments in the past, the telephone response unit may respond by expressing gratitude. Furthermore, if the debtor has previously refused to pay, the telephone response unit may select a response method taking into account the reason for the refusal. Furthermore, if the debtor has previously proposed a payment plan, the telephone response unit may respond based on that plan. This enables more effective responses by selecting the optimal response method based on the past telephone response history. Some or all of the above-described processing in the telephone response unit may be performed using, for example, AI, or may be performed without AI. For example, the telephone response unit may input the debtor's past telephone response history into a generation AI and have the generation AI select the optimal response method.

[0095] The telephone response unit can customize the content of the telephone response based on the debtor's current situation. Current situations include, but are not limited to, income and expenditure status. For example, if the debtor's income is decreasing, the telephone response unit can provide a telephone response proposing a flexible payment plan. Furthermore, if the debtor's ability to repay is high, the telephone response unit can also provide a telephone response encouraging early payment. Furthermore, if the debtor's financial situation is unstable, the telephone response unit can provide a telephone response proposing a payment deferral. This enables more effective response by providing a telephone response tailored to the current situation. Some or all of the above-described processing in the telephone response unit may be performed, for example, using AI, or may be performed without AI. For example, the telephone response unit can input data on the debtor's current situation into the generation AI and have the generation AI customize the content of the telephone response.

[0096] The telephone response unit can estimate the debtor's emotions and determine the priority of telephone responses based on the estimated debtor's emotions. Emotion estimation includes, but is not limited to, voice analysis and text analysis. For example, the telephone response unit can analyze the debtor's tone of voice and vocabulary to estimate emotions. The telephone response unit can also analyze the debtor's text messages to estimate emotions. For example, if the debtor is angry, the telephone response priority can be set high to respond quickly. If the debtor is relaxed, other urgent responses can be prioritized and the call can be handled later. Furthermore, if the debtor is anxious, the telephone response priority can be set medium to reassure the debtor. This enables prompt and appropriate responses by determining the priority of telephone responses according to the debtor's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the telephone response unit can be performed using, for example, AI, or without AI. For example, the telephone response department can input data of the debtor's voice into the generation AI and have the generation AI estimate emotions and determine the priority of the telephone response.

[0097] The telephone response unit can provide different telephone responses for each region based on the debtor's geographical location information. Geographical location information includes, but is not limited to, GPS data and address information. For example, if the debtor lives in an urban area, the telephone response unit can provide telephone responses that take into account the economic conditions specific to that area. Furthermore, if the debtor lives in a rural area, the telephone response unit can provide telephone responses that take into account the economic conditions specific to that area. Furthermore, if the debtor lives overseas, the telephone response unit can provide telephone responses that take into account the economic conditions and culture of that country. This allows for more effective telephone responses by providing telephone responses that take into account the economic conditions of each region. Some or all of the above-described processing in the telephone response unit may be performed, for example, using AI, or may be performed without AI. For example, the telephone response unit can input the debtor's geographical location information into a generation AI and have the generation AI perform different telephone responses for each region.

[0098] The call handling unit can analyze the debtor's social media activity and customize call responses based on related information. Social media activity includes, but is not limited to, the content of posts and the number of followers. For example, if the debtor indicates financial difficulties on social media, the call handling unit can call the debtor offering a payment deferral. Furthermore, if the debtor indicates on social media that they have found a new job, the call handling unit can call the debtor encouraging early payment. Furthermore, if the debtor indicates on social media that they are traveling, the call handling unit can call the debtor encouraging payment after their trip. Customizing call responses based on social media activity enables more effective responses. Some or all of the above-described processing in the call handling unit may be performed using, for example, AI, or without AI. For example, the call handling unit can input data on the debtor's social media activity into a generation AI and have the generation AI customize the call responses.

[0099] The telephone response unit can optimize the content and method of telephone responses by reflecting the debtor's past feedback. Examples of feedback include, but are not limited to, surveys and reviews. For example, if the debtor has preferred email reminders in the past, the telephone response unit can prioritize email reminders. Furthermore, if the debtor has preferred telephone reminders in the past, the telephone response unit can prioritize telephone reminders. Furthermore, if the debtor has preferred softer language in the past, the telephone response unit can reflect that softer language in its telephone responses. This enables more effective responses by optimizing telephone responses based on past feedback. Some or all of the above-described processing in the telephone response unit may be performed using, for example, AI, or may be performed without AI. For example, the telephone response unit can input the debtor's past feedback into a generation AI and have the generation AI optimize telephone responses.

[0100] The fund utilization unit can formulate a detailed plan for using the procured funds and allocate them optimally. Examples of such plans include, but are not limited to, budget allocations and project plans. For example, the fund utilization unit can formulate a plan for allocating the procured funds to strengthening a lending system for financial institutions. The fund utilization unit can also formulate a plan for allocating the procured funds to the international expansion of the business. Furthermore, the fund utilization unit can also formulate a plan for allocating the procured funds to launching a new business. By formulating a detailed plan for using the funds, optimal allocation of funds becomes possible. Some or all of the above-described processing in the fund utilization unit may be performed using, for example, AI, or without AI. For example, the fund utilization unit can input the procured funds usage plan into a generation AI and have the generation AI execute optimal fund allocation.

[0101] The fund utilization unit can monitor fund usage in real time and make adjustments as necessary. Examples of monitoring include, but are not limited to, real-time data collection and analysis. For example, the fund utilization unit can monitor fund usage in real time and make adjustments if a budget overrun occurs. The fund utilization unit can also monitor fund usage in real time and reallocate unused funds to other projects. Furthermore, the fund utilization unit can monitor fund usage in real time and confirm whether it is progressing as planned. This allows for appropriate fund usage management through real-time monitoring. Some or all of the above-described processing in the fund utilization unit may be performed using, for example, AI, or may be performed without AI. For example, the fund utilization unit can input fund usage data into a generation AI and have the generation AI perform monitoring and adjustments.

[0102] The fund utilization unit can evaluate the effectiveness of fund utilization and reflect it in the next fundraising plan. Examples of evaluations of utilization effectiveness include, but are not limited to, ROI (return on investment) and KPI (key performance indicator). For example, the fund utilization unit can evaluate the effectiveness of fund utilization and prioritize allocation of the next fund to successful projects. The fund utilization unit can also evaluate the effectiveness of fund utilization and implement improvement measures for failed projects. Furthermore, the fund utilization unit can evaluate the effectiveness of fund utilization and reflect it in the next fundraising plan. Thus, by evaluating utilization effectiveness, the next fundraising plan can be optimized. Some or all of the above-described processing in the fund utilization unit may be performed, for example, using AI or without AI. For example, the fund utilization unit can input data on the effectiveness of fund utilization into a generation AI and have the generation AI perform an evaluation and reflect the results in the next fundraising plan.

[0103] The fund utilization unit can collect feedback regarding the use of funds and identify areas for improvement. Examples of feedback include, but are not limited to, surveys and reviews. For example, the fund utilization unit can collect feedback regarding the use of funds and identify areas for improvement. The fund utilization unit can also improve the next fund allocation plan based on the feedback regarding the use of funds. Furthermore, the fund utilization unit can analyze the feedback regarding the use of funds and identify the optimal fund allocation method. In this way, the method of using funds can be improved by collecting feedback. Some or all of the above-mentioned processing in the fund utilization unit may be performed using, for example, AI, or may be performed without using AI. For example, the fund utilization unit can input feedback data into a generation AI and have the generation AI identify areas for improvement.

[0104] The fund utilization unit can diversify the purposes for which the raised funds are used to diversify risk. Examples of purposes for which the funds are used include, but are not limited to, research and development and marketing. For example, the fund utilization unit distributes the raised funds among multiple projects. The fund utilization unit can also distribute the raised funds among different industries or regions. Furthermore, the fund utilization unit can distribute the raised funds among short-term and long-term projects. This enables risk diversification by diversifying the purposes for which the funds are used. Some or all of the above-described processing in the fund utilization unit may be performed using, for example, AI, or may be performed without using AI. For example, the fund utilization unit can input data on the purposes for which the funds are used into the generation AI and have the generation AI execute a risk diversification plan.

[0105] The fund utilization department may prepare detailed reports to increase transparency regarding the use of funds. Evaluation of transparency may include, but is not limited to, the preparation of detailed reports and the scope of public information. For example, the fund utilization department may periodically prepare reports detailing the use of funds. The fund utilization department may also prepare reports that clearly indicate the purpose and effect of the use of funds. Furthermore, the fund utilization department may make the reports public to increase transparency regarding the use of funds. In this way, the preparation of detailed reports improves transparency regarding the use of funds. Some or all of the above-described processing in the fund utilization department may be performed, for example, using AI or may be performed without using AI. For example, the fund utilization department may have a generation AI execute the preparation of the reports.

[0106] The fund utilization department can conduct an external audit on the use of funds to ensure reliability. Examples of external audits include, but are not limited to, the frequency of audits and the items to be audited. For example, the fund utilization department can request an external auditing organization to conduct an audit on the use of funds. The fund utilization department can also identify areas for improvement based on the results of the external audit on the use of funds. Furthermore, the fund utilization department can also make the results of the external audit on the use of funds public to ensure reliability. Thus, conducting an external audit improves reliability on the use of funds. Some or all of the above-described processing in the fund utilization department can be performed, for example, using AI or without AI. For example, the fund utilization department can input the results of the external audit into the generation AI and have the generation AI identify areas for improvement and ensure reliability.

[0107] The fund utilization unit can optimize the next fund utilization plan by reflecting user feedback regarding fund usage. Examples of feedback include, but are not limited to, surveys and reviews. For example, the fund utilization unit collects user feedback and reflects it in the next fund utilization plan. The fund utilization unit can also improve the fund allocation method based on the user feedback. Furthermore, the fund utilization unit can analyze the user feedback and formulate an optimal fund utilization plan. Thus, the next fund utilization plan can be optimized by reflecting the user feedback. Some or all of the above-described processing in the fund utilization unit may be performed, for example, using AI or without AI. For example, the fund utilization unit can input user feedback data into a generation AI and cause the generation AI to optimize the next fund utilization plan. === Hard Collateral 1-1 === Each of the multiple elements including the chat unit, analysis unit, telephone response unit, and fund utilization unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the chat unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the telephone response unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the fund utilization unit is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the chat unit, analysis unit, telephone response unit, and fund utilization unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the chat unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the telephone response unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the fund utilization unit is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the chat unit, analysis unit, telephone response unit, and fund utilization unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the chat unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the telephone response unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the fund utilization unit is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the chat unit, analysis unit, telephone response unit, and fund utilization unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the chat unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12. For example, the telephone response unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the fund utilization unit is realized by the specific processing unit 290 of the data processing device 12.

[0108] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0109] The debt collection system can further include a credit information acquisition unit that acquires the debtor's credit information. The credit information acquisition unit collects the debtor's credit score and past payment history and provides them to the analysis unit. For example, the credit information acquisition unit acquires the debtor's credit score, and the analysis unit evaluates the debtor's ability to repay based on that information. The credit information acquisition unit can also acquire the debtor's past payment history, and the analysis unit can evaluate the debtor's willingness to repay based on that history. Furthermore, the credit information acquisition unit can acquire the debtor's credit report, and the analysis unit can propose the optimal collection method based on that report. In this way, by utilizing the debtor's credit information, it is possible to more accurately evaluate the debtor's ability and willingness to repay.

[0110] The debt collection system can further include a lifestyle pattern analysis unit that analyzes the debtor's lifestyle patterns. The lifestyle pattern analysis unit analyzes the debtor's lifestyle rhythm and spending patterns and provides the results to the chat unit. For example, the lifestyle pattern analysis unit analyzes the debtor's spending patterns and evaluates their ability to repay. The lifestyle pattern analysis unit can also analyze the debtor's lifestyle rhythm and suggest the optimal timing for sending a reminder message. Furthermore, the lifestyle pattern analysis unit can analyze the debtor's lifestyle situation and suggest a flexible payment plan. This makes it possible to make reminders that take into account the debtor's lifestyle patterns.

[0111] The debt collection system can further include an emotion adjustment unit that estimates the debtor's emotions and adjusts the content of the reminder message based on the estimated emotions. The emotion adjustment unit analyzes the debtor's text messages and voice messages to estimate the emotions. For example, if the debtor is feeling stressed, the emotion adjustment unit can send the debtor a reminder message using gentle language. If the debtor is relaxed, the emotion adjustment unit can also send the debtor a message proposing a detailed payment plan. Furthermore, if the debtor is in a hurry, the emotion adjustment unit can send the debtor a message encouraging a concise and prompt response. This allows for more effective reminder collection by adjusting the content of the reminder message according to the debtor's emotions.

[0112] The debt collection system can further include a location information acquisition unit that acquires the debtor's geographic location information. The location information acquisition unit collects the debtor's GPS data and address information and provides it to the analysis unit. For example, if the debtor lives in an urban area, the location information acquisition unit can perform analysis taking into account the economic conditions specific to urban areas. In addition, if the debtor lives in a rural area, the location information acquisition unit can also perform analysis taking into account the economic conditions specific to rural areas. Furthermore, if the debtor lives overseas, the location information acquisition unit can perform analysis taking into account the economic conditions and culture of the country. This makes it possible to perform analysis that takes geographical factors into account.

[0113] The debt collection system can further include a social media analysis unit that analyzes the debtor's social media activity. The social media analysis unit analyzes the content of the debtor's posts and the number of followers, and provides the results to the chat unit. For example, if the social media analysis unit indicates that the debtor is experiencing financial difficulties, it can send a message suggesting a payment deferral. If the social media analysis unit indicates that the debtor has gotten a new job, it can also send a message urging early payment. Furthermore, if the social media analysis unit indicates that the debtor is traveling, it can also send a message urging payment after the debtor has traveled. This makes it possible to send debt collection messages based on social media activity.

[0114] The debt collection system can further include a feedback reflection unit that reflects the debtor's past feedback and optimizes the content and sending method of messages. The feedback reflection unit collects debtor surveys and reviews and provides them to the chat unit. For example, if the debtor has preferred to be reminded by email in the past, the feedback reflection unit can send a message by email. Also, if the debtor has preferred to be reminded by phone in the past, the feedback reflection unit can send a message by phone. Furthermore, if the debtor has preferred softer language in the past, the feedback reflection unit can send a message that reflects that language. This makes it possible to provide optimal reminders based on past feedback.

[0115] The debt collection system can further include an emotion response unit that estimates the debtor's emotions and adjusts the content and timing of telephone conversations based on the estimated emotions. The emotion response unit analyzes the debtor's tone of voice and language to estimate emotions. For example, if the debtor is angry, the emotion response unit adjusts the content of the telephone conversation to encourage a calm response. If the debtor is relaxed, the emotion response unit can also conduct a telephone conversation that proposes a detailed payment plan. Furthermore, if the debtor is feeling anxious, the emotion response unit can carefully adjust the content of the telephone conversation to reassure the debtor. This makes it possible to respond to telephone conversations according to the debtor's emotions.

[0116] The debt collection system can further include a history reference unit that references the debtor's past telephone response history to select the optimal response method. The history reference unit collects the debtor's past call records and response content and provides them to the telephone response unit. For example, if the debtor has made prompt payments in the past, the history reference unit may respond by expressing gratitude. In addition, if the debtor has refused to pay in the past, the history reference unit may select a response method by taking into account the reason. Furthermore, if the debtor has proposed a payment plan in the past, the history reference unit may respond based on that plan. This makes it possible to optimally respond based on the debtor's past telephone response history.

[0117] The debt collection system can further include a situation customization unit that customizes the content of telephone responses based on the debtor's current situation. The situation customization unit collects the debtor's income and expenditure status and provides it to the telephone response unit. For example, if the debtor's income is decreasing, the situation customization unit can respond by phone to propose a flexible payment plan. Also, if the debtor's ability to pay is high, the situation customization unit can respond by phone to encourage early payment. Furthermore, if the debtor's financial situation is unstable, the situation customization unit can respond by phone to propose a payment grace period. This makes it possible to respond by phone according to the current situation.

[0118] The debt collection system may further include a priority determination unit that estimates the debtor's emotions and determines the priority of telephone responses based on the estimated emotions. The priority determination unit analyzes the debtor's tone of voice and language to estimate the emotions. For example, if the debtor is angry, the priority determination unit may set the priority of the telephone response high in order to respond quickly. Also, if the debtor is relaxed, the priority determination unit may prioritize other urgent responses and respond later. Furthermore, if the debtor is feeling anxious, the priority determination unit may set the priority of the telephone response to medium in order to reassure the debtor. This allows the priority of telephone responses to be determined according to the debtor's emotions, enabling a quick and appropriate response.

[0119] The processing flow of the second embodiment will be briefly explained below.

[0120] Step 1: The chat module receives responses from the debtor. Responses from the debtor include text messages and voice messages. The chat module sends a reminder message to the debtor and receives a response from the debtor. The chat module can also estimate the debtor's emotions and adjust the content and timing of the reminder message based on the estimated emotions. Step 2: The analysis unit analyzes the responses received by the chat unit. The analysis is performed using methods such as natural language processing technology and sentiment analysis. The analysis unit analyzes the debtor's responses and takes appropriate action. It can also estimate the debtor's emotions and adjust the analysis method for the responses based on the estimated emotions. Step 3: The telephone response department responds to the call based on the responses analyzed by the analysis department. The call is handled by methods such as an automated response using AI or by an operator. The telephone response department can also estimate the debtor's emotions and adjust the content and timing of the call based on the estimated emotions. Step 4: The Fund Utilization Department utilizes the raised funds. Fund utilization is carried out in ways such as strengthening the lending system for financial institutions and expanding the business internationally. The Fund Utilization Department utilizes the raised funds in ways such as strengthening the lending system for financial institutions and expanding the business internationally.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0126] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0127] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0128] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0129] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0131] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0132] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] 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.

[0134] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0135] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0136] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0142] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] 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.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0158] 7, a 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.

[0159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0164] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0165] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] 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.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0168] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0174] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0175] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0176] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0177] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0178] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0179] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0180] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0181] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0182] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0183] 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.

[0184] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0185] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0186] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0187] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0188] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0189] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0190] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0191] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0192] [Explanation of symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a chat section for receiving responses from debtors; an analysis unit that analyzes responses received by the chat unit; a telephone response unit that responds to telephone calls based on the response analyzed by the analysis unit; Establish a fund utilization department to utilize the funds raised A system characterized by:

2. The chat section Sending reminder messages to debtors and accepting responses from debtors 2. The system of claim 1.

3. The analysis unit Analyze the debtor's response and take action 2. The system of claim 1.

4. The telephone response unit Using AI to automate telephone responses to debtors 2. The system of claim 1.

5. The Fund Utilization Department: The funds raised will be used to strengthen the lending system for financial institutions and to expand business internationally.

2. The system of claim 1.

6. The chat section Estimate the debtor's emotions and adjust the content and timing of sending reminder messages based on the estimated emotions of the debtor.

2. The system of claim 1.

7. The chat section Analyze the debtor's past response history and generate reminder messages 2. The system of claim 1.

8. The chat section Customize the message based on the debtor's current financial situation and ability to pay 2. The system of claim 1.

9. The chat section Automatically schedule the next dunning message based on the debtor's response 2. The system of claim 1.

10. The chat section Estimate the debtor's feelings and prioritize responses based on the estimated debtor's feelings 2. The system of claim 1.

Images