System

Abstract

An object of a system according to an embodiment is to simplify an application process of a medical expense support system according to a situation of an applicant.SOLUTION: A system according to an embodiment includes a reception unit, a proposal unit, and a generation unit. The reception unit inputs a situation of the applicant. The proposal unit proposes the subsidy system based on the information input by the reception unit. The generation unit automatically generates a necessary document based on the subsidy system proposed by the proposal unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the application process for medical expense subsidies was complicated, placing a heavy burden on elderly people and people with disabilities in particular.

[0005] The system according to the embodiment aims to simplify the application process for the medical expense subsidy system according to the applicant's circumstances. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a proposal unit, and a generation unit. The reception unit inputs the applicant's situation. The proposal unit proposes a subsidy program based on the information input by the reception unit. The generation unit automatically generates the necessary documents based on the subsidy program proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to the embodiment can simplify the application process for medical expense subsidy programs depending on the applicant's circumstances. [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 medical expense subsidy application support system according to an embodiment of the present invention automatically assesses the applicant's situation, proposes the optimal subsidy program, and automatically generates the necessary documents. In this system, the applicant inputs their personal information, and a generation AI analyzes that information to propose the optimal subsidy program and automatically generate the necessary documents. For example, when the applicant inputs their place of residence, financial situation, and medical expenses, the generation AI proposes the optimal subsidy program based on that information. Furthermore, the generation AI automatically generates templates for the application form and required attachments based on the proposed subsidy program. This saves the applicant the trouble of creating complex documents. Furthermore, by utilizing multimodal generation AI, communication can be achieved not only through text but also through voice and images. For example, when the applicant inputs a question by voice, the generation AI can provide a voice response. This also enables support for people with visual or hearing impairments. This simplifies the application process and reduces barriers, especially for the elderly and people with disabilities. For example, if an applicant simply inputs their own circumstances, the generative AI will suggest the most suitable grant program and automatically generate the necessary documents, making the application process go more smoothly. In addition, communication via voice and images is possible, making it possible to support people with a variety of circumstances.

[0029] A medical expense subsidy application support system according to an embodiment includes a reception unit, a proposal unit, and a generation unit. The reception unit inputs the applicant's circumstances. The applicant's circumstances include, but are not limited to, for example, their place of residence, financial situation, and medical expense burden. The reception unit provides, for example, an interface for the applicant to input their place of residence, financial situation, and medical expense burden. The reception unit can also support voice input and image input. For example, when the applicant inputs information by voice, the voice input can be converted into text data using voice recognition technology. The proposal unit proposes an optimal subsidy system for the applicant based on the information input by the reception unit. The proposal unit proposes an optimal subsidy system based on the applicant's circumstances, for example, using a generation AI. The generation AI analyzes the applicant's place of residence, financial situation, and medical expense burden and executes an algorithm to propose an optimal subsidy system. For example, the generation AI proposes medical expense subsidy systems available in a specific area to an elderly person living in that area. The generation unit generates templates for an application form and necessary attached documents based on the subsidy system proposed by the proposal unit. The generation unit automatically generates templates for application forms and required attached documents using, for example, a generation AI. The generation AI executes an algorithm that generates the format of the required documents based on the applicant's situation. For example, the generation AI generates templates for application forms and required attached documents in PDF or Word format. As a result, the medical expense subsidy application support system according to the embodiment can simplify the application process by proposing the optimal subsidy system based on the applicant's situation and automatically generating the required documents.

[0030] The reception unit can input information about the applicant's place of residence, financial situation, and medical expense burden. The reception unit, for example, provides an interface for the applicant to input information about the place of residence, financial situation, and medical expense burden. For example, when the applicant inputs their place of residence, the reception unit can provide options such as country, state, city, town, etc. When inputting the applicant's place of residence, the reception unit can provide fields for inputting information such as income, assets, and liabilities. When inputting the applicant's medical expense burden, the reception unit can provide fields for inputting information such as annual medical expenses and insurance coverage. This allows for a detailed understanding of the applicant's situation, making it possible to propose a more appropriate subsidy system. Some or all of the above-described processing in the reception unit can be performed, for example, using AI, or can be performed without AI. For example, the reception unit can input the information input by the applicant into AI, which can analyze the information and provide appropriate fields.

[0031] The proposal unit can propose a subsidy program suitable for the applicant based on the information input by the reception unit. The proposal unit, for example, uses a generation AI to propose the optimal subsidy program based on the applicant's situation. The generation AI analyzes the applicant's place of residence, economic situation, and medical expense burden and executes an algorithm to propose the optimal subsidy program. For example, the generation AI proposes medical expense subsidy programs available in a specific area to elderly people living in that area. The generation AI can also propose subsidy programs based on the applicant's income and assets based on the applicant's economic situation. Furthermore, the generation AI can propose subsidy programs based on the applicant's annual medical expenses and insurance coverage based on the applicant's medical expense burden. This can streamline the application process by proposing the optimal subsidy program for the applicant. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the applicant's situation into AI, which then proposes the optimal subsidy program.

[0032] The generation unit can generate formats for application forms and required attached documents based on the grant program proposed by the proposal unit. The generation unit, for example, uses a generation AI to automatically generate templates for application forms and required attached documents. The generation AI executes an algorithm to generate formats for required documents based on the applicant's situation. For example, the generation AI generates templates for application forms and required attached documents in PDF or Word format. The generation unit can also provide an interface for providing the generated documents to the applicant. For example, the generation unit can provide the generated documents as download links. Furthermore, the generation unit can also have a function for sending the generated documents by email. This reduces the applicant's workload by automatically generating templates for application forms and required attached documents. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the applicant's situation into AI, which then generates formats for the required documents.

[0033] The medical expense subsidy application support system includes a voice input unit that enables an applicant to input questions by voice. The voice input unit, for example, provides an interface for the applicant to input questions by voice. The voice input unit converts the applicant's voice into text data using voice recognition technology. For example, the voice input unit can allow the applicant to input questions using a microphone and convert the voice into text data in real time. The voice input unit can also analyze the information input by voice by the applicant and provide appropriate feedback. For example, the voice input unit can generate answers to questions input by voice by the applicant using a generation AI and provide feedback by voice. This enables voice input to support applicants with visual impairments. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input the applicant's voice into AI, which can analyze the voice and convert it into text data.

[0034] The medical expense subsidy application support system includes an audio output unit that enables the generation AI to provide answers via voice. The audio output unit, for example, provides an interface for the generation AI to provide answers via voice. The audio output unit converts text data generated by the generation AI into voice using voice synthesis technology. For example, the audio output unit can convert answers generated by the generation AI into voice data using voice synthesis technology and provide the data to the applicant through a speaker. The audio output unit can also adjust the tone and speed of the voice depending on the applicant's situation. For example, the audio output unit can provide information in a calm tone if the applicant is stressed, and provide quick and concise voice output if the applicant is in a hurry. This enables audio output to support applicants with hearing impairments. Some or all of the above-described processing in the audio output unit may be performed using, for example, AI, or may be performed without AI. For example, the audio output unit can input text data generated by the generation AI into AI, which then converts the data into voice data.

[0035] The medical expense subsidy application support system includes an image input unit that allows applicants to input information via images. The image input unit, for example, provides an interface for applicants to input information via images. The image input unit uses image recognition technology to analyze the image data entered by the applicant and extract necessary information. For example, the image input unit allows applicants to take a photo of a document using a smartphone camera and upload the image data. The image input unit can also analyze the uploaded image data and convert the necessary information into text data. For example, the image input unit can use OCR technology to extract text information from the image data and convert it into text data. This enables image input, making it possible to submit an application using visual information. Some or all of the above-described processing in the image input unit may be performed using, for example, AI, or may be performed without AI. For example, the image input unit can input image data uploaded by the applicant into AI, which then analyzes the image data and extracts necessary information.

[0036] The medical expense subsidy application support system includes an image output unit that enables the generation AI to provide information in the form of images. The image output unit, for example, provides an interface through which the generation AI provides information in the form of images. The image output unit converts the information generated by the generation AI into image data using image generation technology. For example, the image output unit can provide information in a visual format, such as a graph or chart, based on the information generated by the generation AI. The image output unit can also adjust the design and layout of the image depending on the applicant's situation. For example, the image output unit can provide an image with calm colors when the applicant is stressed, and an image with bright colors when the applicant is relaxed. This enables image output, enabling applications to be submitted using visual information. Some or all of the above-described processing in the image output unit may be performed using, for example, AI, or may be performed without AI. For example, the image output unit can input the information generated by the generation AI into AI, which then converts the information into image data.

[0037] The reception unit can analyze the applicant's past application history and select the optimal input method. The reception unit, for example, uses an algorithm for analyzing the applicant's past application history. The algorithm analyzes the applicant's past application content and results and selects the optimal input method. For example, the reception unit can prioritize and suggest input methods (voice, text, etc.) that the applicant has used in the past. The reception unit can also predict and suggest input methods to be used during specific time periods based on the applicant's past application history. Furthermore, the reception unit can automatically display information that the applicant has frequently entered in the past as candidates. In this way, by analyzing the past application history, the optimal input method can be provided to the applicant. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's past application history into AI, which then selects the optimal input method.

[0038] The reception unit may filter information based on the applicant's current living situation and areas of interest when inputting the information. The reception unit may, for example, use an algorithm for analyzing the applicant's current living situation and areas of interest. The algorithm filters relevant information based on the applicant's living situation and areas of interest. For example, the reception unit may prioritize input of relevant information based on the applicant's current living situation (e.g., whether or not the applicant has a job, their family situation, etc.). The reception unit may also filter and input relevant information based on the applicant's areas of interest (e.g., health, education, etc.). Furthermore, the reception unit may exclude unnecessary information and input only necessary information based on the applicant's living situation and areas of interest. In this way, by filtering information based on the applicant's living situation and areas of interest, only necessary information can be input. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the applicant's living situation and areas of interest into AI, which then filters the information.

[0039] When inputting information, the reception unit can select the optimal input means depending on the applicant's input method. The reception unit, for example, uses an algorithm to select the optimal input means depending on the applicant's input method (voice, text, image, etc.). The algorithm selects the optimal input means based on the applicant's input method. For example, if the applicant desires voice input, the reception unit can prioritize voice input. Also, if the applicant desires text input, the reception unit can prioritize text input. Furthermore, if the applicant desires image input, the reception unit can prioritize image input. This improves input efficiency by selecting the optimal input means depending on the applicant's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's input method into AI, which can select the optimal input means.

[0040] When inputting information, the reception unit can prioritize inputting highly relevant information by taking into account the applicant's geographical location information. The reception unit, for example, uses an algorithm for analyzing the applicant's geographical location information. The algorithm prioritizes inputting relevant information based on the applicant's geographical location information. For example, the reception unit can prioritize inputting information about region-specific subsidy programs based on the applicant's place of residence. The reception unit can also prioritize inputting information about nearby medical institutions based on the applicant's current location. Furthermore, the reception unit can filter and input information about related regions based on the applicant's geographical location information. This allows highly relevant information to be prioritized by taking into account the applicant's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's geographical location information into AI, which can analyze the information and prioritize inputting highly relevant information.

[0041] The reception unit can analyze the applicant's social media activity and input relevant information when inputting information. The reception unit, for example, uses an algorithm for analyzing the applicant's social media activity. The algorithm inputs relevant information based on the applicant's social media activity. For example, the reception unit can input information about relevant grant programs based on information shared by the applicant on social media. The reception unit can also analyze the applicant's social media activity and input relevant information preferentially. Furthermore, the reception unit can input relevant information based on the activity of the applicant's friends on social media. In this way, relevant information can be input efficiently by analyzing the applicant's social media activity. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's social media activity into AI, which analyzes the information and inputs relevant information.

[0042] The reception unit can customize the input method by reflecting the applicant's past feedback when entering information. The reception unit, for example, uses an algorithm for reflecting the applicant's past feedback. The algorithm customizes the input method based on the applicant's past feedback. For example, the reception unit can suggest the optimal input method based on feedback provided by the applicant in the past. The reception unit can also preferentially provide a specific input method based on the applicant's past feedback. Furthermore, the reception unit can customize the input method by reflecting the applicant's feedback and provide a more user-friendly interface. In this way, a more user-friendly input method can be provided by reflecting the applicant's past feedback. Some or all of the above-described processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the applicant's past feedback into AI, which can analyze the feedback and customize the input method.

[0043] The proposal unit can adjust the level of detail of the proposal based on the importance of the subsidy program when making a proposal. The proposal unit, for example, uses an algorithm for evaluating the importance of the subsidy program. The algorithm adjusts the level of detail of the proposal based on the importance of the subsidy program. For example, the proposal unit can provide detailed information for subsidy programs with high importance. The proposal unit can also provide concise information for subsidy programs with low importance. Furthermore, the proposal unit can adjust the level of detail of the proposal according to the importance of the subsidy program and provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the proposal based on the importance of the subsidy program. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input the importance of the subsidy program into AI, which can analyze the information and adjust the level of detail of the proposal.

[0044] The proposal unit can apply different proposal algorithms depending on the category of the subsidy program when making a proposal. The proposal unit, for example, constructs a system for applying different proposal algorithms depending on the category of the subsidy program. The system selects the optimal proposal algorithm based on the category of the subsidy program. For example, the proposal unit can apply a medical-related algorithm to a proposal regarding a medical expense subsidy program. The proposal unit can also apply a lifestyle-related algorithm to a proposal regarding a living assistance subsidy program. Furthermore, the proposal unit can apply an education-related algorithm to a proposal regarding an education subsidy program. This enables more appropriate proposals by applying different proposal algorithms depending on the category of the subsidy program. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the category of the subsidy program into AI, which can select the optimal proposal algorithm.

[0045] When making a proposal, the proposal unit can improve the accuracy of the proposal by referring to the applicant's past proposal results. The proposal unit, for example, uses an algorithm for analyzing the applicant's past proposal results. The algorithm improves the accuracy of the proposal based on the applicant's past proposal results. For example, the proposal unit can make an optimal proposal based on the proposal results received by the applicant in the past. The proposal unit can also preferentially provide successful proposals from the applicant's past proposal results. Furthermore, the proposal unit can analyze the applicant's past proposal results and improve the accuracy of the proposal. In this way, the accuracy of the proposal is improved by referring to the applicant's past proposal results. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the applicant's past proposal results into AI, which can analyze the information and improve the accuracy of the proposal.

[0046] The proposal unit can determine the priority of proposals based on the submission timing of the grant programs when they are submitted. The proposal unit, for example, uses an algorithm for evaluating the submission timing of the grant programs. The algorithm determines the priority of proposals based on the submission timing of the grant programs. For example, the proposal unit can prioritize proposals with an upcoming submission deadline. The proposal unit can also postpone proposals with a distant submission deadline. Furthermore, the proposal unit can adjust the priority of proposals based on the submission timing of the grant programs. In this way, by determining the priority of proposals based on the submission timing of the grant programs, proposals can be made at the optimal time. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI, or may be performed without using AI. For example, the proposal unit can input the submission timing of the grant programs into AI, which can analyze the information and determine the priority of proposals.

[0047] The proposal unit can adjust the order of proposals based on the relevance of the grant programs when making proposals. The proposal unit, for example, uses an algorithm for evaluating the relevance of the grant programs. The algorithm adjusts the order of proposals based on the relevance of the grant programs. For example, the proposal unit can first propose the grant program that is most relevant to the applicant's situation. The proposal unit can also propose grant programs that are less relevant to the applicant's situation later. Furthermore, the proposal unit can adjust the order of proposals based on the relevance of the grant programs. In this way, by adjusting the order of proposals based on the relevance of the grant programs, the most relevant information can be provided preferentially. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI, or may be performed without using AI. For example, the proposal unit can input the relevance of the grant programs into AI, which can analyze the information and adjust the order of proposals.

[0048] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal depending on the applicant's level of expertise. The suggestion unit, for example, uses an algorithm to evaluate the applicant's level of expertise. The algorithm adjusts the use of technical terminology in the proposal based on the applicant's level of expertise. For example, if the applicant has technical expertise, the suggestion unit can make a proposal that uses a lot of technical terminology. Also, if the applicant does not have technical expertise, the suggestion unit can make a proposal in easy-to-understand language. Furthermore, the suggestion unit can adjust the use of technical terminology in the proposal depending on the applicant's level of expertise. This allows for a more understandable proposal by adjusting the use of technical terminology depending on the applicant's level of expertise. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terminology in the proposal.

[0049] The generation unit can adjust the level of detail of the document based on the importance of the grant program when generating the document. The generation unit, for example, uses an algorithm for evaluating the importance of the grant program. The algorithm adjusts the level of detail of the document based on the importance of the grant program. For example, the generation unit can generate detailed documents for grant programs with high importance. The generation unit can also generate concise documents for grant programs with low importance. Furthermore, the generation unit can adjust the level of detail of the document according to the importance of the grant program to generate an optimal document. In this way, an optimal document is generated by adjusting the level of detail of the document based on the importance of the grant program. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the importance of the grant program into AI, which can analyze the information and adjust the level of detail of the document.

[0050] The generation unit can apply different generation algorithms depending on the category of the subsidy program when generating documents. The generation unit, for example, builds a system for applying different generation algorithms depending on the category of the subsidy program. The system selects the optimal generation algorithm based on the category of the subsidy program. For example, the generation unit can apply a medical-related generation algorithm to documents related to medical expense subsidy programs. The generation unit can also apply a lifestyle-related generation algorithm to documents related to living assistance subsidy programs. Furthermore, the generation unit can apply an education-related generation algorithm to documents related to education expense subsidy programs. In this way, by applying different generation algorithms depending on the category of the subsidy program, more appropriate documents are generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of the subsidy program into AI, which can select the optimal generation algorithm.

[0051] When generating documents, the generation unit can improve the accuracy of generation by referring to the applicant's past document generation results. The generation unit, for example, uses an algorithm for analyzing the applicant's past document generation results. The algorithm improves the accuracy of generation based on the applicant's past document generation results. For example, the generation unit can generate an optimal document based on documents previously generated by the applicant. The generation unit can also prioritize generating successful documents from the applicant's past document generation results. Furthermore, the generation unit can analyze the applicant's past document generation results to improve the accuracy of generation. In this way, the accuracy of generation is improved by referring to the applicant's past document generation results. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the applicant's past document generation results into AI, which analyzes the information to improve the accuracy of generation.

[0052] When generating documents, the generation unit can determine the priority of documents based on the submission date for the grant program. The generation unit, for example, uses an algorithm for evaluating the submission date for the grant program. The algorithm determines the priority of documents based on the submission date for the grant program. For example, the generation unit can prioritize generating documents for grant programs with upcoming submission deadlines. The generation unit can also postpone generating documents for grant programs with distant submission deadlines. Furthermore, the generation unit can adjust the priority of documents based on the submission date for the grant program. In this way, by determining the priority of documents based on the submission date for the grant program, documents are generated at the optimal time. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the submission date for the grant program into AI, which can analyze the information and determine the priority of documents.

[0053] The generation unit can adjust the order of documents based on the relevance of the grant program when generating documents. The generation unit, for example, uses an algorithm for evaluating the relevance of the grant program. The algorithm adjusts the order of documents based on the relevance of the grant program. For example, the generation unit can first generate documents for grant programs that are most relevant to the applicant's situation. The generation unit can also generate documents for grant programs that are less relevant to the applicant's situation later. Furthermore, the generation unit can adjust the order of documents based on the relevance of the grant program. In this way, by adjusting the order of documents based on the relevance of the grant program, the most relevant documents can be generated preferentially. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the relevance of the grant program into AI, which can analyze the information and adjust the order of the documents.

[0054] When generating a document, the generation unit can adjust the use of technical terminology in the document according to the applicant's level of expertise. The generation unit, for example, uses an algorithm to evaluate the applicant's level of expertise. The algorithm adjusts the use of technical terminology in the document based on the applicant's level of expertise. For example, if the applicant has technical expertise, the generation unit can generate a document that uses a lot of technical terminology. Alternatively, if the applicant does not have technical expertise, the generation unit can generate a document in easy-to-understand language. Furthermore, the generation unit can adjust the use of technical terminology in the document according to the applicant's level of expertise. In this way, by adjusting the use of technical terminology according to the applicant's level of expertise, a document that is easier to understand is generated. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terminology in the document.

[0055] The voice input unit can analyze the applicant's past voice input history and select the optimal input method when inputting voice data. The voice input unit, for example, uses an algorithm for analyzing the applicant's past voice input history. The algorithm analyzes the applicant's past voice input content and input frequency to select the optimal input method. For example, the voice input unit can prioritize and suggest voice input methods used by the applicant in the past. The voice input unit can also predict and suggest voice input methods to be used during specific time periods based on the applicant's past voice input history. Furthermore, the voice input unit can automatically display information frequently input by the applicant in the past as candidates. In this way, by analyzing the past voice input history, the optimal voice input method can be provided to the applicant. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without AI. For example, the voice input unit can input the applicant's past voice input history into AI, which can select the optimal input method.

[0056] The voice input unit can filter the voice input based on the applicant's current living situation and areas of interest. The voice input unit, for example, uses an algorithm for analyzing the applicant's current living situation and areas of interest. The algorithm filters relevant information based on the applicant's living situation and areas of interest. For example, the voice input unit can prioritize input of relevant information based on the applicant's current living situation (e.g., whether or not the applicant has a job, their family situation, etc.). The voice input unit can also filter and input relevant information based on the applicant's areas of interest (e.g., health, education, etc.). Furthermore, the voice input unit can exclude unnecessary information and input only necessary information based on the applicant's living situation and areas of interest. In this way, by filtering information based on the applicant's living situation and areas of interest, only necessary information can be input. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without AI. For example, the voice input unit can input the applicant's living situation and areas of interest to AI, which then filters the information.

[0057] The voice input unit can prioritize inputting highly relevant information by taking into account the applicant's geographical location information during voice input. The voice input unit, for example, uses an algorithm for analyzing the applicant's geographical location information. The algorithm prioritizes inputting relevant information based on the applicant's geographical location information. For example, the voice input unit can prioritize inputting information about region-specific subsidy programs based on the applicant's place of residence. The voice input unit can also prioritize inputting information about nearby medical institutions based on the applicant's current location. Furthermore, the voice input unit can filter and input information about related regions based on the applicant's geographical location information. This allows highly relevant information to be prioritized by taking the applicant's geographical location information into account. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without AI. For example, the voice input unit can input the applicant's geographical location information to AI, which can analyze the information and prioritize inputting highly relevant information.

[0058] The voice input unit can analyze the applicant's social media activity and input relevant information during voice input. The voice input unit, for example, uses an algorithm for analyzing the applicant's social media activity. The algorithm inputs relevant information based on the applicant's social media activity. For example, the voice input unit can input information about relevant grant programs based on information shared by the applicant on social media. The voice input unit can also analyze the applicant's social media activity and prioritize input of relevant information. Furthermore, the voice input unit can input relevant information based on the activity of the applicant's friends on social media. In this way, relevant information can be efficiently input by analyzing the applicant's social media activity. Some or all of the above-described processing in the voice input unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice input unit can input the applicant's social media activity into AI, which can analyze the information and input relevant information.

[0059] The audio output unit can adjust the level of detail of the output based on the importance of the subsidy program when outputting audio. The audio output unit uses, for example, an algorithm for evaluating the importance of the subsidy program. The algorithm adjusts the level of detail of the output based on the importance of the subsidy program. For example, the audio output unit can provide detailed information by audio for subsidy programs with high importance. The audio output unit can also provide concise information by audio for subsidy programs with low importance. Furthermore, the audio output unit can adjust the level of detail of the output according to the importance of the subsidy program and provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the output based on the importance of the subsidy program. Some or all of the above-mentioned processing in the audio output unit may be performed using, for example, AI, or may be performed without using AI. For example, the audio output unit can input the importance of the subsidy program into AI, which can analyze the information and adjust the level of detail of the output.

[0060] The audio output unit can apply different output algorithms depending on the category of the subsidy program when outputting audio. The audio output unit, for example, constructs a system for applying different output algorithms depending on the category of the subsidy program. The system selects an optimal output algorithm based on the category of the subsidy program. For example, the audio output unit can apply a medical-related output algorithm to information related to medical expense subsidy programs. The audio output unit can also apply a lifestyle-related output algorithm to information related to living assistance subsidy programs. Furthermore, the audio output unit can also apply an education-related output algorithm to information related to education expense subsidy programs. This makes it possible to provide more appropriate information by applying different output algorithms depending on the category of the subsidy program. Some or all of the above-mentioned processing in the audio output unit may be performed using, for example, AI, or may be performed without using AI. For example, the audio output unit can input the category of the subsidy program into AI, which can select the optimal output algorithm.

[0061] When outputting voice, the voice output unit can improve the accuracy of the output by referring to the applicant's past voice output results. The voice output unit, for example, uses an algorithm for analyzing the applicant's past voice output results. The algorithm improves the accuracy of the output based on the applicant's past voice output results. For example, the voice output unit can provide optimal voice output based on the voice output results received by the applicant in the past. The voice output unit can also prioritize successful voice output from the applicant's past voice output results. Furthermore, the voice output unit can analyze the applicant's past voice output results and improve the accuracy of the output. As a result, the accuracy of the output is improved by referring to the applicant's past voice output results. Some or all of the above-described processing in the voice output unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice output unit can input the applicant's past voice output results into AI, which can analyze the information and improve the accuracy of the output.

[0062] The audio output unit can determine the output priority based on the submission date of the grant application when outputting the audio. The audio output unit, for example, uses an algorithm for evaluating the submission date of the grant application. The algorithm determines the output priority based on the submission date of the grant application. For example, the audio output unit can prioritize providing audio information about grant applications with upcoming submission deadlines. The audio output unit can also provide audio information about grant applications with more distant submission deadlines at a later date. Furthermore, the audio output unit can adjust the audio output priority based on the submission date of the grant application. This allows information to be provided at the optimal time by determining the output priority based on the submission date of the grant application. Some or all of the above-described processing in the audio output unit may be performed using, for example, AI, or may be performed without AI. For example, the audio output unit can input the submission date of the grant application into AI, which can analyze the information and determine the output priority.

[0063] The audio output unit can adjust the order of output based on the relevance of the subsidy programs when outputting audio. The audio output unit uses, for example, an algorithm for evaluating the relevance of the subsidy programs. The algorithm adjusts the order of output based on the relevance of the subsidy programs. For example, the audio output unit can first provide, by audio, information about the subsidy program that is most relevant to the applicant's situation. The audio output unit can also provide, by audio, information about the subsidy program that is less relevant to the applicant's situation later. Furthermore, the audio output unit can adjust the order of audio output based on the relevance of the subsidy programs. In this way, by adjusting the order of output based on the relevance of the subsidy programs, the most relevant information can be provided preferentially. Some or all of the above-described processing in the audio output unit may be performed using, for example, AI, or may be performed without using AI. For example, the audio output unit can input the relevance of the subsidy programs into AI, which can analyze the information and adjust the order of output.

[0064] The audio output unit can adjust the use of technical terms in the audio output according to the applicant's level of expertise when outputting audio. The audio output unit, for example, uses an algorithm for evaluating the applicant's level of expertise. The algorithm adjusts the use of technical terms in the audio output based on the applicant's level of expertise. For example, if the applicant has technical expertise, the audio output unit can provide audio output that uses a lot of technical terms. Alternatively, if the applicant does not have technical expertise, the audio output unit can provide audio output in easy-to-understand language. Furthermore, the audio output unit can adjust the use of technical terms in the audio output according to the applicant's level of expertise. This allows for the provision of information that is easier to understand by adjusting the use of technical terms according to the applicant's level of expertise. Some or all of the above-described processing in the audio output unit can be performed, for example, using AI, or can be performed without AI. For example, the audio output unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terms in the audio output.

[0065] When inputting an image, the image input unit can analyze the applicant's past image input history and select the optimal input method. The image input unit, for example, uses an algorithm to analyze the applicant's past image input history. The algorithm analyzes the applicant's past image input content and input frequency to select the optimal input method. For example, the image input unit can prioritize and suggest image input methods used by the applicant in the past. The image input unit can also predict and suggest image input methods to be used during specific time periods based on the applicant's past image input history. Furthermore, the image input unit can automatically display information that the applicant has frequently input in the past as candidates. In this way, by analyzing the past image input history, the optimal image input method can be provided to the applicant. Some or all of the above-described processing in the image input unit may be performed using, for example, AI, or may be performed without AI. For example, the image input unit can input the applicant's past image input history into AI, which can select the optimal input method.

[0066] The image input unit can filter the image based on the applicant's current living situation and areas of interest when inputting the image. The image input unit, for example, uses an algorithm for analyzing the applicant's current living situation and areas of interest. The algorithm filters relevant information based on the applicant's living situation and areas of interest. For example, the image input unit can prioritize input of relevant information based on the applicant's current living situation (e.g., whether or not the applicant has a job, their family situation, etc.). The image input unit can also filter and input relevant information based on the applicant's areas of interest (e.g., health, education, etc.). Furthermore, the image input unit can exclude unnecessary information and input only necessary information based on the applicant's living situation and areas of interest. In this way, by filtering information based on the applicant's living situation and areas of interest, only necessary information can be input. Some or all of the above-described processing in the image input unit can be performed using, for example, AI, or without AI. For example, the image input unit can input the applicant's living situation and areas of interest into AI, which then filters the information.

[0067] When inputting an image, the image input unit can prioritize inputting highly relevant information by taking into account the applicant's geographical location information. The image input unit, for example, uses an algorithm for analyzing the applicant's geographical location information. The algorithm prioritizes inputting relevant information based on the applicant's geographical location information. For example, the image input unit can prioritize inputting information about region-specific subsidy programs based on the applicant's place of residence. The image input unit can also prioritize inputting information about nearby medical institutions based on the applicant's current location. Furthermore, the image input unit can filter and input information about related regions based on the applicant's geographical location information. This allows highly relevant information to be prioritized by taking into account the applicant's geographical location information. Some or all of the above-described processing in the image input unit may be performed using, for example, AI, or may be performed without AI. For example, the image input unit can input the applicant's geographical location information into AI, which can analyze the information and prioritize inputting highly relevant information.

[0068] The image input unit can analyze the applicant's social media activity and input relevant information when inputting an image. The image input unit, for example, uses an algorithm for analyzing the applicant's social media activity. The algorithm inputs relevant information based on the applicant's social media activity. For example, the image input unit can input information about related grant programs based on information shared by the applicant on social media. The image input unit can also analyze the applicant's social media activity and prioritize input of relevant information. Furthermore, the image input unit can input relevant information based on the activity of the applicant's friends on social media. In this way, relevant information can be efficiently input by analyzing the applicant's social media activity. Some or all of the above-described processing in the image input unit can be performed, for example, using AI, or can be performed without using AI. For example, the image input unit can input the applicant's social media activity into AI, which can analyze the information and input relevant information.

[0069] The image output unit can adjust the level of detail of the output based on the importance of the subsidy program when outputting an image. The image output unit, for example, uses an algorithm for evaluating the importance of the subsidy program. The algorithm adjusts the level of detail of the output based on the importance of the subsidy program. For example, the image output unit can provide detailed images for subsidy programs with high importance. The image output unit can also provide simple images for subsidy programs with low importance. Furthermore, the image output unit can adjust the level of detail of the output according to the importance of the subsidy program and provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the output based on the importance of the subsidy program. Some or all of the above-mentioned processing in the image output unit may be performed using, for example, AI, or may be performed without using AI. For example, the image output unit can input the importance of the subsidy program into AI, which analyzes the information and adjusts the level of detail of the output.

[0070] The image output unit can apply different output algorithms depending on the category of the subsidy program when outputting an image. The image output unit, for example, constructs a system for applying different output algorithms depending on the category of the subsidy program. The system selects an optimal output algorithm based on the category of the subsidy program. For example, the image output unit can apply a medical-related output algorithm to information related to medical expense subsidy programs. The image output unit can also apply a lifestyle-related output algorithm to information related to living assistance subsidy programs. Furthermore, the image output unit can also apply an education-related output algorithm to information related to education expense subsidy programs. This makes it possible to provide more appropriate information by applying different output algorithms depending on the category of the subsidy program. Some or all of the above-mentioned processing in the image output unit can be performed using, for example, AI, or without AI. For example, the image output unit can input the category of the subsidy program into AI, which can select the optimal output algorithm.

[0071] When outputting an image, the image output unit can improve the accuracy of the output by referring to the applicant's past image output results. The image output unit, for example, uses an algorithm for analyzing the applicant's past image output results. The algorithm improves the accuracy of the output based on the applicant's past image output results. For example, the image output unit can provide an optimal image based on the applicant's past image output results. The image output unit can also prioritize successful images from the applicant's past image output results. Furthermore, the image output unit can analyze the applicant's past image output results and improve the accuracy of the output. As a result, the accuracy of the output is improved by referring to the applicant's past image output results. Some or all of the above-described processing in the image output unit may be performed, for example, using AI, or may be performed without AI. For example, the image output unit can input the applicant's past image output results into AI, which can analyze the information and improve the accuracy of the output.

[0072] The image output unit can determine the output priority based on the submission date of the grant program when outputting the image. The image output unit, for example, uses an algorithm for evaluating the submission date of the grant program. The algorithm determines the output priority based on the submission date of the grant program. For example, the image output unit can prioritize providing information on grant programs with upcoming submission deadlines as images. The image output unit can also postpone providing information on grant programs with distant submission deadlines as images. Furthermore, the image output unit can adjust the image output priority based on the submission date of the grant program. In this way, by determining the output priority based on the submission date of the grant program, information can be provided at the optimal time. Some or all of the above-mentioned processing in the image output unit may be performed, for example, using AI, or may be performed without using AI. For example, the image output unit can input the submission date of the grant program into AI, which analyzes the information and determines the output priority.

[0073] The image output unit can adjust the output order based on the relevance of the subsidy programs when outputting images. The image output unit, for example, uses an algorithm for evaluating the relevance of the subsidy programs. The algorithm adjusts the output order based on the relevance of the subsidy programs. For example, the image output unit can first provide information on the subsidy programs most relevant to the applicant's situation in the form of images. The image output unit can also provide information on subsidy programs less relevant to the applicant's situation in the form of images later. Furthermore, the image output unit can adjust the image output order based on the relevance of the subsidy programs. In this way, by adjusting the output order based on the relevance of the subsidy programs, the most relevant information can be provided preferentially. Some or all of the above-described processing in the image output unit may be performed using, for example, AI, or may be performed without using AI. For example, the image output unit can input the relevance of the subsidy programs into AI, which can analyze the information and adjust the output order.

[0074] When outputting an image, the image output unit can adjust the use of technical terms in the image output according to the applicant's level of expertise. The image output unit, for example, uses an algorithm to evaluate the applicant's level of expertise. The algorithm adjusts the use of technical terms in the image output based on the applicant's level of expertise. For example, if the applicant has technical expertise, the image output unit can provide an image that uses a lot of technical terms. Alternatively, if the applicant does not have technical expertise, the image output unit can provide an image in easy-to-understand language. Furthermore, the image output unit can adjust the use of technical terms in the image output according to the applicant's level of expertise. This allows for the provision of information that is easier to understand by adjusting the use of technical terms according to the applicant's level of expertise. Some or all of the above-described processing in the image output unit can be performed, for example, using AI, or can be performed without AI. For example, the image output unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terms in the image output.

[0075] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0076] The reception unit can also analyze the applicant's past application history and select the optimal input method. For example, it can prioritize and suggest input methods (voice, text, etc.) that the applicant has used in the past. It can also predict and suggest input methods to be used at specific times based on the applicant's past application history. It can also automatically display information that the applicant has frequently entered in the past as candidates. In this way, it is possible to provide the applicant with the optimal input method by analyzing their past application history.

[0077] The proposal unit can also adjust the level of detail of the proposal based on the importance of the grant program. For example, detailed information can be provided for grant programs with high importance. Concise information can also be provided for grant programs with low importance. Furthermore, the level of detail of the proposal can be adjusted according to the importance of the grant program to provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the proposal based on the importance of the grant program.

[0078] The proposal unit can also apply different proposal algorithms depending on the category of the subsidy program. For example, a medical-related algorithm can be applied to a proposal regarding a medical expense subsidy program. A lifestyle-related algorithm can be applied to a proposal regarding a living assistance subsidy program. Furthermore, an education-related algorithm can be applied to a proposal regarding an education expense subsidy program. This allows for more appropriate proposals to be made by applying different proposal algorithms depending on the category of the subsidy program.

[0079] When generating documents, the generation unit can also determine the priority of documents based on the submission date for the grant program. For example, documents for grant programs with upcoming submission deadlines can be generated with priority. Documents for grant programs with more distant submission deadlines can also be generated at a later date. Furthermore, the priority of documents can also be adjusted based on the submission date for the grant program. In this way, by determining the priority of documents based on the submission date for the grant program, documents can be generated at the optimal time.

[0080] The processing flow of the first embodiment will be briefly explained below.

[0081] Step 1: The reception unit inputs the applicant's information, including the applicant's place of residence, financial situation, and medical expenses. The reception unit provides an interface for the applicant to input this information and also supports voice and image input. For example, voice input can be converted into text data using voice recognition technology. Step 2: The proposal unit proposes the most suitable subsidy system for the applicant based on the information entered by the reception unit. Using generative AI, the proposal unit analyzes the applicant's place of residence, financial situation, and medical expenses burden, and executes an algorithm to propose the most suitable subsidy system. For example, for elderly people living in a specific area, the proposal proposes medical expense subsidy systems available in that area. Step 3: The generation unit generates templates for the application form and required attached documents based on the grant system proposed by the proposal unit. The generation unit uses generation AI to automatically generate templates for the application form and required attached documents. The generation AI runs an algorithm to generate the format of the required documents based on the applicant's situation, and generates them in PDF or Word format.

[0082] (Example 2) A medical expense subsidy application support system according to an embodiment of the present invention automatically assesses the applicant's situation, proposes the optimal subsidy program, and automatically generates the necessary documents. In this system, the applicant inputs their personal information, and a generation AI analyzes that information to propose the optimal subsidy program and automatically generate the necessary documents. For example, when the applicant inputs their place of residence, financial situation, and medical expenses, the generation AI proposes the optimal subsidy program based on that information. Furthermore, the generation AI automatically generates templates for the application form and required attachments based on the proposed subsidy program. This saves the applicant the trouble of creating complex documents. Furthermore, by utilizing multimodal generation AI, communication can be achieved not only through text but also through voice and images. For example, when the applicant inputs a question by voice, the generation AI can provide a voice response. This also enables support for people with visual or hearing impairments. This simplifies the application process and reduces barriers, especially for the elderly and people with disabilities. For example, if an applicant simply inputs their own circumstances, the generative AI will suggest the most suitable grant program and automatically generate the necessary documents, making the application process go more smoothly. In addition, communication via voice and images is possible, making it possible to support people with a variety of circumstances.

[0083] A medical expense subsidy application support system according to an embodiment includes a reception unit, a proposal unit, and a generation unit. The reception unit inputs the applicant's circumstances. The applicant's circumstances include, but are not limited to, for example, their place of residence, financial situation, and medical expense burden. The reception unit provides, for example, an interface for the applicant to input their place of residence, financial situation, and medical expense burden. The reception unit can also support voice input and image input. For example, when the applicant inputs information by voice, the voice input can be converted into text data using voice recognition technology. The proposal unit proposes an optimal subsidy system for the applicant based on the information input by the reception unit. The proposal unit proposes an optimal subsidy system based on the applicant's circumstances, for example, using a generation AI. The generation AI analyzes the applicant's place of residence, financial situation, and medical expense burden and executes an algorithm to propose an optimal subsidy system. For example, the generation AI proposes medical expense subsidy systems available in a specific area to an elderly person living in that area. The generation unit generates templates for an application form and necessary attached documents based on the subsidy system proposed by the proposal unit. The generation unit automatically generates templates for application forms and required attached documents using, for example, a generation AI. The generation AI executes an algorithm that generates the format of the required documents based on the applicant's situation. For example, the generation AI generates templates for application forms and required attached documents in PDF or Word format. As a result, the medical expense subsidy application support system according to the embodiment can simplify the application process by proposing the optimal subsidy system based on the applicant's situation and automatically generating the required documents.

[0084] The reception unit can input information about the applicant's place of residence, financial situation, and medical expense burden. The reception unit, for example, provides an interface for the applicant to input information about the place of residence, financial situation, and medical expense burden. For example, when the applicant inputs their place of residence, the reception unit can provide options such as country, state, city, town, etc. When inputting the applicant's place of residence, the reception unit can provide fields for inputting information such as income, assets, and liabilities. When inputting the applicant's medical expense burden, the reception unit can provide fields for inputting information such as annual medical expenses and insurance coverage. This allows for a detailed understanding of the applicant's situation, making it possible to propose a more appropriate subsidy system. Some or all of the above-described processing in the reception unit can be performed, for example, using AI, or can be performed without AI. For example, the reception unit can input the information input by the applicant into AI, which can analyze the information and provide appropriate fields.

[0085] The proposal unit can propose a subsidy program suitable for the applicant based on the information input by the reception unit. The proposal unit, for example, uses a generation AI to propose the optimal subsidy program based on the applicant's situation. The generation AI analyzes the applicant's place of residence, economic situation, and medical expense burden and executes an algorithm to propose the optimal subsidy program. For example, the generation AI proposes medical expense subsidy programs available in a specific area to elderly people living in that area. The generation AI can also propose subsidy programs based on the applicant's income and assets based on the applicant's economic situation. Furthermore, the generation AI can propose subsidy programs based on the applicant's annual medical expenses and insurance coverage based on the applicant's medical expense burden. This can streamline the application process by proposing the optimal subsidy program for the applicant. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the applicant's situation into AI, which then proposes the optimal subsidy program.

[0086] The generation unit can generate formats for application forms and required attached documents based on the grant program proposed by the proposal unit. The generation unit, for example, uses a generation AI to automatically generate templates for application forms and required attached documents. The generation AI executes an algorithm to generate formats for required documents based on the applicant's situation. For example, the generation AI generates templates for application forms and required attached documents in PDF or Word format. The generation unit can also provide an interface for providing the generated documents to the applicant. For example, the generation unit can provide the generated documents as download links. Furthermore, the generation unit can also have a function for sending the generated documents by email. This reduces the applicant's workload by automatically generating templates for application forms and required attached documents. Some or all of the above-described processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the applicant's situation into AI, which then generates formats for the required documents.

[0087] The medical expense subsidy application support system includes a voice input unit that enables an applicant to input questions by voice. The voice input unit, for example, provides an interface for the applicant to input questions by voice. The voice input unit converts the applicant's voice into text data using voice recognition technology. For example, the voice input unit can allow the applicant to input questions using a microphone and convert the voice into text data in real time. The voice input unit can also analyze the information input by voice by the applicant and provide appropriate feedback. For example, the voice input unit can generate answers to questions input by voice by the applicant using a generation AI and provide feedback by voice. This enables voice input to support applicants with visual impairments. Some or all of the above-described processing in the voice input unit may be performed using AI, for example, or without AI. For example, the voice input unit can input the applicant's voice into AI, which can analyze the voice and convert it into text data.

[0088] The medical expense subsidy application support system includes an audio output unit that enables the generation AI to provide answers via voice. The audio output unit, for example, provides an interface for the generation AI to provide answers via voice. The audio output unit converts text data generated by the generation AI into voice using voice synthesis technology. For example, the audio output unit can convert answers generated by the generation AI into voice data using voice synthesis technology and provide the data to the applicant through a speaker. The audio output unit can also adjust the tone and speed of the voice depending on the applicant's situation. For example, the audio output unit can provide information in a calm tone if the applicant is stressed, and provide quick and concise voice output if the applicant is in a hurry. This enables audio output to support applicants with hearing impairments. Some or all of the above-described processing in the audio output unit may be performed using, for example, AI, or may be performed without AI. For example, the audio output unit can input text data generated by the generation AI into AI, which then converts the data into voice data.

[0089] The medical expense subsidy application support system includes an image input unit that allows applicants to input information via images. The image input unit, for example, provides an interface for applicants to input information via images. The image input unit uses image recognition technology to analyze the image data entered by the applicant and extract necessary information. For example, the image input unit allows applicants to take a photo of a document using a smartphone camera and upload the image data. The image input unit can also analyze the uploaded image data and convert the necessary information into text data. For example, the image input unit can use OCR technology to extract text information from the image data and convert it into text data. This enables image input, making it possible to submit an application using visual information. Some or all of the above-described processing in the image input unit may be performed using, for example, AI, or may be performed without AI. For example, the image input unit can input image data uploaded by the applicant into AI, which then analyzes the image data and extracts necessary information.

[0090] The medical expense subsidy application support system includes an image output unit that enables the generation AI to provide information in the form of images. The image output unit, for example, provides an interface through which the generation AI provides information in the form of images. The image output unit converts the information generated by the generation AI into image data using image generation technology. For example, the image output unit can provide information in a visual format, such as a graph or chart, based on the information generated by the generation AI. The image output unit can also adjust the design and layout of the image depending on the applicant's situation. For example, the image output unit can provide an image with calm colors when the applicant is stressed, and an image with bright colors when the applicant is relaxed. This enables image output, enabling applications to be submitted using visual information. Some or all of the above-described processing in the image output unit may be performed using, for example, AI, or may be performed without AI. For example, the image output unit can input the information generated by the generation AI into AI, which then converts the information into image data.

[0091] The reception unit can analyze the applicant's emotions and adjust the timing of information input based on the analyzed emotions. The reception unit, for example, uses an emotion estimation algorithm to analyze the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is feeling stressed, the reception unit can delay the timing of information input to provide a relaxing environment. Furthermore, if the applicant is relaxed, the reception unit can speed up the timing of information input to efficiently complete the input. Furthermore, if the applicant is in a hurry, the reception unit can optimize the timing of information input to quickly complete the input. This reduces the burden on the applicant by adjusting the timing of information input according to the applicant'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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or without AI. For example, the reception department can input the applicant's emotional data into AI, which can then analyze the emotions and adjust the timing of information input.

[0092] The reception unit can analyze the applicant's past application history and select the optimal input method. The reception unit, for example, uses an algorithm for analyzing the applicant's past application history. The algorithm analyzes the applicant's past application content and results and selects the optimal input method. For example, the reception unit can prioritize and suggest input methods (voice, text, etc.) that the applicant has used in the past. The reception unit can also predict and suggest input methods to be used during specific time periods based on the applicant's past application history. Furthermore, the reception unit can automatically display information that the applicant has frequently entered in the past as candidates. In this way, by analyzing the past application history, the optimal input method can be provided to the applicant. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's past application history into AI, which then selects the optimal input method.

[0093] The reception unit may filter information based on the applicant's current living situation and areas of interest when inputting the information. The reception unit may, for example, use an algorithm for analyzing the applicant's current living situation and areas of interest. The algorithm filters relevant information based on the applicant's living situation and areas of interest. For example, the reception unit may prioritize input of relevant information based on the applicant's current living situation (e.g., whether or not the applicant has a job, their family situation, etc.). The reception unit may also filter and input relevant information based on the applicant's areas of interest (e.g., health, education, etc.). Furthermore, the reception unit may exclude unnecessary information and input only necessary information based on the applicant's living situation and areas of interest. In this way, by filtering information based on the applicant's living situation and areas of interest, only necessary information can be input. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input the applicant's living situation and areas of interest into AI, which then filters the information.

[0094] When inputting information, the reception unit can select the optimal input means depending on the applicant's input method. The reception unit, for example, uses an algorithm to select the optimal input means depending on the applicant's input method (voice, text, image, etc.). The algorithm selects the optimal input means based on the applicant's input method. For example, if the applicant desires voice input, the reception unit can prioritize voice input. Also, if the applicant desires text input, the reception unit can prioritize text input. Furthermore, if the applicant desires image input, the reception unit can prioritize image input. This improves input efficiency by selecting the optimal input means depending on the applicant's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's input method into AI, which can select the optimal input means.

[0095] The reception unit can estimate the applicant's emotions and determine the priority of information to be entered based on the estimated emotions. The reception unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is feeling stressed, the reception unit can prioritize input of important information and postpone input of other information. Furthermore, if the applicant is relaxed, the reception unit can input all information evenly. Furthermore, if the applicant is in a hurry, the reception unit can input the most important information first and quickly proceed with processing. This allows important information to be prioritized by determining the priority of information according to the applicant'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 reception unit may be performed using, for example, AI, or without AI. For example, the reception department can input the applicant's emotional data into AI, which can then analyze the emotions and determine the priority of the information.

[0096] When inputting information, the reception unit can prioritize inputting highly relevant information by taking into account the applicant's geographical location information. The reception unit, for example, uses an algorithm for analyzing the applicant's geographical location information. The algorithm prioritizes inputting relevant information based on the applicant's geographical location information. For example, the reception unit can prioritize inputting information about region-specific subsidy programs based on the applicant's place of residence. The reception unit can also prioritize inputting information about nearby medical institutions based on the applicant's current location. Furthermore, the reception unit can filter and input information about related regions based on the applicant's geographical location information. This allows highly relevant information to be prioritized by taking into account the applicant's geographical location information. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's geographical location information into AI, which can analyze the information and prioritize inputting highly relevant information.

[0097] The reception unit can analyze the applicant's social media activity and input relevant information when inputting information. The reception unit, for example, uses an algorithm for analyzing the applicant's social media activity. The algorithm inputs relevant information based on the applicant's social media activity. For example, the reception unit can input information about relevant grant programs based on information shared by the applicant on social media. The reception unit can also analyze the applicant's social media activity and input relevant information preferentially. Furthermore, the reception unit can input relevant information based on the activity of the applicant's friends on social media. In this way, relevant information can be input efficiently by analyzing the applicant's social media activity. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the applicant's social media activity into AI, which analyzes the information and inputs relevant information.

[0098] The reception unit can customize the input method by reflecting the applicant's past feedback when entering information. The reception unit, for example, uses an algorithm for reflecting the applicant's past feedback. The algorithm customizes the input method based on the applicant's past feedback. For example, the reception unit can suggest the optimal input method based on feedback provided by the applicant in the past. The reception unit can also preferentially provide a specific input method based on the applicant's past feedback. Furthermore, the reception unit can customize the input method by reflecting the applicant's feedback and provide a more user-friendly interface. In this way, a more user-friendly input method can be provided by reflecting the applicant's past feedback. Some or all of the above-described processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the applicant's past feedback into AI, which can analyze the feedback and customize the input method.

[0099] The suggestion unit can estimate the applicant's emotions and adjust the way the proposal is presented based on the estimated emotions. The suggestion unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is stressed, the suggestion unit can use a simple and easy-to-understand expression. If the applicant is relaxed, the suggestion unit can use an expression that includes detailed information. If the applicant is in a hurry, the suggestion unit can use a concise expression that focuses on the main points. This allows for a more appropriate proposal by adjusting the way the proposal is presented based on the applicant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be 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 suggestion unit can be performed, for example, using AI or without AI. For example, the proposal department can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the way the proposal is presented.

[0100] The proposal unit can adjust the level of detail of the proposal based on the importance of the subsidy program when making a proposal. The proposal unit, for example, uses an algorithm for evaluating the importance of the subsidy program. The algorithm adjusts the level of detail of the proposal based on the importance of the subsidy program. For example, the proposal unit can provide detailed information for subsidy programs with high importance. The proposal unit can also provide concise information for subsidy programs with low importance. Furthermore, the proposal unit can adjust the level of detail of the proposal according to the importance of the subsidy program and provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the proposal based on the importance of the subsidy program. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input the importance of the subsidy program into AI, which can analyze the information and adjust the level of detail of the proposal.

[0101] The proposal unit can apply different proposal algorithms depending on the category of the subsidy program when making a proposal. The proposal unit, for example, constructs a system for applying different proposal algorithms depending on the category of the subsidy program. The system selects the optimal proposal algorithm based on the category of the subsidy program. For example, the proposal unit can apply a medical-related algorithm to a proposal regarding a medical expense subsidy program. The proposal unit can also apply a lifestyle-related algorithm to a proposal regarding a living assistance subsidy program. Furthermore, the proposal unit can apply an education-related algorithm to a proposal regarding an education subsidy program. This enables more appropriate proposals by applying different proposal algorithms depending on the category of the subsidy program. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the category of the subsidy program into AI, which can select the optimal proposal algorithm.

[0102] When making a proposal, the proposal unit can improve the accuracy of the proposal by referring to the applicant's past proposal results. The proposal unit, for example, uses an algorithm for analyzing the applicant's past proposal results. The algorithm improves the accuracy of the proposal based on the applicant's past proposal results. For example, the proposal unit can make an optimal proposal based on the proposal results received by the applicant in the past. The proposal unit can also preferentially provide successful proposals from the applicant's past proposal results. Furthermore, the proposal unit can analyze the applicant's past proposal results and improve the accuracy of the proposal. In this way, the accuracy of the proposal is improved by referring to the applicant's past proposal results. Some or all of the above-mentioned processing in the proposal unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal unit can input the applicant's past proposal results into AI, which can analyze the information and improve the accuracy of the proposal.

[0103] The suggestion unit can estimate the applicant's emotions and adjust the length of the proposal based on the estimated emotions. The suggestion unit uses, for example, an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, the suggestion unit can make a short, concise proposal if the applicant is stressed. Alternatively, the suggestion unit can make a longer proposal including detailed information if the applicant is relaxed. Furthermore, the suggestion unit can make a quick, concise proposal if the applicant is in a hurry. This allows for more appropriate proposals by adjusting the length of the proposal according to the applicant's emotions. The emotion estimation is realized 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 suggestion unit can be performed using, for example, an AI, or without an AI. For example, the proposal department can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the length of the proposal.

[0104] The proposal unit can determine the priority of proposals based on the submission timing of the grant programs when they are submitted. The proposal unit, for example, uses an algorithm for evaluating the submission timing of the grant programs. The algorithm determines the priority of proposals based on the submission timing of the grant programs. For example, the proposal unit can prioritize proposals with an upcoming submission deadline. The proposal unit can also postpone proposals with a distant submission deadline. Furthermore, the proposal unit can adjust the priority of proposals based on the submission timing of the grant programs. In this way, by determining the priority of proposals based on the submission timing of the grant programs, proposals can be made at the optimal time. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI, or may be performed without using AI. For example, the proposal unit can input the submission timing of the grant programs into AI, which can analyze the information and determine the priority of proposals.

[0105] The proposal unit can adjust the order of proposals based on the relevance of the grant programs when making proposals. The proposal unit, for example, uses an algorithm for evaluating the relevance of the grant programs. The algorithm adjusts the order of proposals based on the relevance of the grant programs. For example, the proposal unit can first propose the grant program that is most relevant to the applicant's situation. The proposal unit can also propose grant programs that are less relevant to the applicant's situation later. Furthermore, the proposal unit can adjust the order of proposals based on the relevance of the grant programs. In this way, by adjusting the order of proposals based on the relevance of the grant programs, the most relevant information can be provided preferentially. Some or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI, or may be performed without using AI. For example, the proposal unit can input the relevance of the grant programs into AI, which can analyze the information and adjust the order of proposals.

[0106] When making a proposal, the suggestion unit can adjust the use of technical terminology in the proposal depending on the applicant's level of expertise. The suggestion unit, for example, uses an algorithm to evaluate the applicant's level of expertise. The algorithm adjusts the use of technical terminology in the proposal based on the applicant's level of expertise. For example, if the applicant has technical expertise, the suggestion unit can make a proposal that uses a lot of technical terminology. Also, if the applicant does not have technical expertise, the suggestion unit can make a proposal in easy-to-understand language. Furthermore, the suggestion unit can adjust the use of technical terminology in the proposal depending on the applicant's level of expertise. This allows for a more understandable proposal by adjusting the use of technical terminology depending on the applicant's level of expertise. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without AI. For example, the suggestion unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terminology in the proposal.

[0107] The generation unit can estimate the applicant's emotions and adjust the expression method of the generated document based on the estimated emotions. The generation unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is stressed, the generation unit can use a simple and easy-to-understand expression method. If the applicant is relaxed, the generation unit can use an expression method that includes detailed information. If the applicant is in a hurry, the generation unit can use a concise expression method that focuses on the main points. This allows the document expression method to be adjusted according to the applicant's emotions, resulting in the generation of a more appropriate document. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be 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-mentioned processing in the generation unit can be performed using, for example, AI, or without AI. For example, the generation unit can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the way the document is presented.

[0108] The generation unit can adjust the level of detail of the document based on the importance of the grant program when generating the document. The generation unit, for example, uses an algorithm for evaluating the importance of the grant program. The algorithm adjusts the level of detail of the document based on the importance of the grant program. For example, the generation unit can generate detailed documents for grant programs with high importance. The generation unit can also generate concise documents for grant programs with low importance. Furthermore, the generation unit can adjust the level of detail of the document according to the importance of the grant program to generate an optimal document. In this way, an optimal document is generated by adjusting the level of detail of the document based on the importance of the grant program. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the importance of the grant program into AI, which can analyze the information and adjust the level of detail of the document.

[0109] The generation unit can apply different generation algorithms depending on the category of the subsidy program when generating documents. The generation unit, for example, builds a system for applying different generation algorithms depending on the category of the subsidy program. The system selects the optimal generation algorithm based on the category of the subsidy program. For example, the generation unit can apply a medical-related generation algorithm to documents related to medical expense subsidy programs. The generation unit can also apply a lifestyle-related generation algorithm to documents related to living assistance subsidy programs. Furthermore, the generation unit can apply an education-related generation algorithm to documents related to education expense subsidy programs. In this way, by applying different generation algorithms depending on the category of the subsidy program, more appropriate documents are generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the category of the subsidy program into AI, which can select the optimal generation algorithm.

[0110] When generating documents, the generation unit can improve the accuracy of generation by referring to the applicant's past document generation results. The generation unit, for example, uses an algorithm for analyzing the applicant's past document generation results. The algorithm improves the accuracy of generation based on the applicant's past document generation results. For example, the generation unit can generate an optimal document based on documents previously generated by the applicant. The generation unit can also prioritize generating successful documents from the applicant's past document generation results. Furthermore, the generation unit can analyze the applicant's past document generation results to improve the accuracy of generation. In this way, the accuracy of generation is improved by referring to the applicant's past document generation results. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the applicant's past document generation results into AI, which analyzes the information to improve the accuracy of generation.

[0111] The generation unit can estimate the applicant's emotions and adjust the length of the document to be generated based on the estimated emotions. The generation unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, the generation unit can generate a short, concise document if the applicant is stressed. The generation unit can generate a longer document containing detailed information if the applicant is relaxed. Furthermore, the generation unit can generate a quick, concise document if the applicant is in a hurry. This allows the length of the document to be adjusted according to the applicant's emotions, resulting in the generation of a more appropriate document. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 generation unit may be performed using, for example, AI, or without AI. For example, the generation unit can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the length of the document.

[0112] When generating documents, the generation unit can determine the priority of documents based on the submission date for the grant program. The generation unit, for example, uses an algorithm for evaluating the submission date for the grant program. The algorithm determines the priority of documents based on the submission date for the grant program. For example, the generation unit can prioritize generating documents for grant programs with upcoming submission deadlines. The generation unit can also postpone generating documents for grant programs with distant submission deadlines. Furthermore, the generation unit can adjust the priority of documents based on the submission date for the grant program. In this way, by determining the priority of documents based on the submission date for the grant program, documents are generated at the optimal time. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the submission date for the grant program into AI, which can analyze the information and determine the priority of documents.

[0113] The generation unit can adjust the order of documents based on the relevance of the grant program when generating documents. The generation unit, for example, uses an algorithm for evaluating the relevance of the grant program. The algorithm adjusts the order of documents based on the relevance of the grant program. For example, the generation unit can first generate documents for grant programs that are most relevant to the applicant's situation. The generation unit can also generate documents for grant programs that are less relevant to the applicant's situation later. Furthermore, the generation unit can adjust the order of documents based on the relevance of the grant program. In this way, by adjusting the order of documents based on the relevance of the grant program, the most relevant documents can be generated preferentially. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input the relevance of the grant program into AI, which can analyze the information and adjust the order of the documents.

[0114] When generating a document, the generation unit can adjust the use of technical terminology in the document according to the applicant's level of expertise. The generation unit, for example, uses an algorithm to evaluate the applicant's level of expertise. The algorithm adjusts the use of technical terminology in the document based on the applicant's level of expertise. For example, if the applicant has technical expertise, the generation unit can generate a document that uses a lot of technical terminology. Alternatively, if the applicant does not have technical expertise, the generation unit can generate a document in easy-to-understand language. Furthermore, the generation unit can adjust the use of technical terminology in the document according to the applicant's level of expertise. In this way, by adjusting the use of technical terminology according to the applicant's level of expertise, a document that is easier to understand is generated. Some or all of the above-described processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terminology in the document.

[0115] The voice input unit can estimate the applicant's emotions and adjust the timing of the voice input based on the estimated emotions. The voice input unit uses, for example, an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is feeling stressed, the voice input unit can delay the timing of the voice input to provide a relaxing environment. Furthermore, if the applicant is relaxed, the voice input unit can accelerate the timing of the voice input to efficiently proceed with input. Furthermore, if the applicant is in a hurry, the voice input unit can optimize the timing of the voice input to quickly complete input. This reduces the burden on the applicant by adjusting the timing of the voice input according to the applicant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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-mentioned processing in the voice input unit may be performed, for example, using AI or without AI. For example, the voice input unit can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the timing of the voice input.

[0116] The voice input unit can analyze the applicant's past voice input history and select the optimal input method when inputting voice data. The voice input unit, for example, uses an algorithm for analyzing the applicant's past voice input history. The algorithm analyzes the applicant's past voice input content and input frequency to select the optimal input method. For example, the voice input unit can prioritize and suggest voice input methods used by the applicant in the past. The voice input unit can also predict and suggest voice input methods to be used during specific time periods based on the applicant's past voice input history. Furthermore, the voice input unit can automatically display information frequently input by the applicant in the past as candidates. In this way, by analyzing the past voice input history, the optimal voice input method can be provided to the applicant. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without AI. For example, the voice input unit can input the applicant's past voice input history into AI, which can select the optimal input method.

[0117] The voice input unit can filter the voice input based on the applicant's current living situation and areas of interest. The voice input unit, for example, uses an algorithm for analyzing the applicant's current living situation and areas of interest. The algorithm filters relevant information based on the applicant's living situation and areas of interest. For example, the voice input unit can prioritize input of relevant information based on the applicant's current living situation (e.g., whether or not the applicant has a job, their family situation, etc.). The voice input unit can also filter and input relevant information based on the applicant's areas of interest (e.g., health, education, etc.). Furthermore, the voice input unit can exclude unnecessary information and input only necessary information based on the applicant's living situation and areas of interest. In this way, by filtering information based on the applicant's living situation and areas of interest, only necessary information can be input. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without AI. For example, the voice input unit can input the applicant's living situation and areas of interest to AI, which then filters the information.

[0118] The voice input unit can estimate the applicant's emotions and prioritize voice inputs based on the estimated emotions. The voice input unit uses, for example, an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is feeling stressed, the voice input unit can prioritize inputting important information and postpone inputting other information. Furthermore, if the applicant is relaxed, the voice input unit can input all information evenly. Furthermore, if the applicant is in a hurry, the voice input unit can input the most important information first and quickly proceed with processing. Thus, by prioritizing voice inputs according to the applicant's emotions, important information can be input preferentially. Emotion estimation is achieved using an emotion estimation function, for example, using 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 voice input unit may be performed using, for example, an AI, or without an AI. For example, the voice input unit can input the applicant's emotional data into the AI, which can then analyze the emotions and determine the priority of the voice input.

[0119] The voice input unit can prioritize inputting highly relevant information by taking into account the applicant's geographical location information during voice input. The voice input unit, for example, uses an algorithm for analyzing the applicant's geographical location information. The algorithm prioritizes inputting relevant information based on the applicant's geographical location information. For example, the voice input unit can prioritize inputting information about region-specific subsidy programs based on the applicant's place of residence. The voice input unit can also prioritize inputting information about nearby medical institutions based on the applicant's current location. Furthermore, the voice input unit can filter and input information about related regions based on the applicant's geographical location information. This allows highly relevant information to be prioritized by taking the applicant's geographical location information into account. Some or all of the above-described processing in the voice input unit may be performed using, for example, AI, or may be performed without AI. For example, the voice input unit can input the applicant's geographical location information to AI, which can analyze the information and prioritize inputting highly relevant information.

[0120] The voice input unit can analyze the applicant's social media activity and input relevant information during voice input. The voice input unit, for example, uses an algorithm for analyzing the applicant's social media activity. The algorithm inputs relevant information based on the applicant's social media activity. For example, the voice input unit can input information about relevant grant programs based on information shared by the applicant on social media. The voice input unit can also analyze the applicant's social media activity and prioritize input of relevant information. Furthermore, the voice input unit can input relevant information based on the activity of the applicant's friends on social media. In this way, relevant information can be efficiently input by analyzing the applicant's social media activity. Some or all of the above-described processing in the voice input unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice input unit can input the applicant's social media activity into AI, which can analyze the information and input relevant information.

[0121] The voice output unit can estimate the applicant's emotions and adjust the voice output expression method based on the estimated emotions. The voice output unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, the voice output unit can provide information in a calm voice if the applicant is stressed. Furthermore, the voice output unit can provide information in a cheerful voice if the applicant is relaxed. Furthermore, the voice output unit can provide quick and concise voice output if the applicant is in a hurry. This allows for more appropriate information provision by adjusting the voice output expression method according to the applicant'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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the voice output unit may be performed, for example, using AI or without AI. For example, the voice output unit can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the way the voice output is expressed.

[0122] The audio output unit can adjust the level of detail of the output based on the importance of the subsidy program when outputting audio. The audio output unit uses, for example, an algorithm for evaluating the importance of the subsidy program. The algorithm adjusts the level of detail of the output based on the importance of the subsidy program. For example, the audio output unit can provide detailed information by audio for subsidy programs with high importance. The audio output unit can also provide concise information by audio for subsidy programs with low importance. Furthermore, the audio output unit can adjust the level of detail of the output according to the importance of the subsidy program and provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the output based on the importance of the subsidy program. Some or all of the above-mentioned processing in the audio output unit may be performed using, for example, AI, or may be performed without using AI. For example, the audio output unit can input the importance of the subsidy program into AI, which can analyze the information and adjust the level of detail of the output.

[0123] The audio output unit can apply different output algorithms depending on the category of the subsidy program when outputting audio. The audio output unit, for example, constructs a system for applying different output algorithms depending on the category of the subsidy program. The system selects an optimal output algorithm based on the category of the subsidy program. For example, the audio output unit can apply a medical-related output algorithm to information related to medical expense subsidy programs. The audio output unit can also apply a lifestyle-related output algorithm to information related to living assistance subsidy programs. Furthermore, the audio output unit can also apply an education-related output algorithm to information related to education expense subsidy programs. This makes it possible to provide more appropriate information by applying different output algorithms depending on the category of the subsidy program. Some or all of the above-mentioned processing in the audio output unit may be performed using, for example, AI, or may be performed without using AI. For example, the audio output unit can input the category of the subsidy program into AI, which can select the optimal output algorithm.

[0124] When outputting voice, the voice output unit can improve the accuracy of the output by referring to the applicant's past voice output results. The voice output unit, for example, uses an algorithm for analyzing the applicant's past voice output results. The algorithm improves the accuracy of the output based on the applicant's past voice output results. For example, the voice output unit can provide optimal voice output based on the voice output results received by the applicant in the past. The voice output unit can also prioritize successful voice output from the applicant's past voice output results. Furthermore, the voice output unit can analyze the applicant's past voice output results and improve the accuracy of the output. As a result, the accuracy of the output is improved by referring to the applicant's past voice output results. Some or all of the above-described processing in the voice output unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice output unit can input the applicant's past voice output results into AI, which can analyze the information and improve the accuracy of the output.

[0125] The voice output unit can estimate the applicant's emotions and adjust the length of the voice output based on the estimated emotions. The voice output unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, the voice output unit can provide short, to-the-point voice output when the applicant is stressed. Furthermore, the voice output unit can provide longer voice output containing detailed information when the applicant is relaxed. Furthermore, the voice output unit can provide quick, concise voice output when the applicant is in a hurry. This allows for more appropriate information provision by adjusting the length of the voice output according to the applicant's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be 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 voice output unit can be performed, for example, using AI, or without AI. For example, the voice output unit can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the length of the voice output.

[0126] The audio output unit can determine the output priority based on the submission date of the grant application when outputting the audio. The audio output unit, for example, uses an algorithm for evaluating the submission date of the grant application. The algorithm determines the output priority based on the submission date of the grant application. For example, the audio output unit can prioritize providing audio information about grant applications with upcoming submission deadlines. The audio output unit can also provide audio information about grant applications with more distant submission deadlines at a later date. Furthermore, the audio output unit can adjust the audio output priority based on the submission date of the grant application. This allows information to be provided at the optimal time by determining the output priority based on the submission date of the grant application. Some or all of the above-described processing in the audio output unit may be performed using, for example, AI, or may be performed without AI. For example, the audio output unit can input the submission date of the grant application into AI, which can analyze the information and determine the output priority.

[0127] The audio output unit can adjust the order of output based on the relevance of the subsidy programs when outputting audio. The audio output unit uses, for example, an algorithm for evaluating the relevance of the subsidy programs. The algorithm adjusts the order of output based on the relevance of the subsidy programs. For example, the audio output unit can first provide, by audio, information about the subsidy program that is most relevant to the applicant's situation. The audio output unit can also provide, by audio, information about the subsidy program that is less relevant to the applicant's situation later. Furthermore, the audio output unit can adjust the order of audio output based on the relevance of the subsidy programs. In this way, by adjusting the order of output based on the relevance of the subsidy programs, the most relevant information can be provided preferentially. Some or all of the above-described processing in the audio output unit may be performed using, for example, AI, or may be performed without using AI. For example, the audio output unit can input the relevance of the subsidy programs into AI, which can analyze the information and adjust the order of output.

[0128] The audio output unit can adjust the use of technical terms in the audio output according to the applicant's level of expertise when outputting audio. The audio output unit, for example, uses an algorithm for evaluating the applicant's level of expertise. The algorithm adjusts the use of technical terms in the audio output based on the applicant's level of expertise. For example, if the applicant has technical expertise, the audio output unit can provide audio output that uses a lot of technical terms. Alternatively, if the applicant does not have technical expertise, the audio output unit can provide audio output in easy-to-understand language. Furthermore, the audio output unit can adjust the use of technical terms in the audio output according to the applicant's level of expertise. This allows for the provision of information that is easier to understand by adjusting the use of technical terms according to the applicant's level of expertise. Some or all of the above-described processing in the audio output unit can be performed, for example, using AI, or can be performed without AI. For example, the audio output unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terms in the audio output.

[0129] The image input unit can estimate the applicant's emotions and adjust the timing of image input based on the estimated emotions. The image input unit uses, for example, an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is feeling stressed, the image input unit can delay the timing of image input to provide a relaxing environment. Furthermore, if the applicant is relaxed, the image input unit can accelerate the timing of image input to efficiently proceed with input. Furthermore, if the applicant is in a hurry, the image input unit can optimize the timing of image input to quickly complete input. This reduces the burden on the applicant by adjusting the timing of image input according to the applicant'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, 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 image input unit may be performed using, for example, AI, or without AI. For example, the image input unit can input the applicant's emotional data into the AI, which can then analyze the emotions and adjust the timing of image input.

[0130] When inputting an image, the image input unit can analyze the applicant's past image input history and select the optimal input method. The image input unit, for example, uses an algorithm to analyze the applicant's past image input history. The algorithm analyzes the applicant's past image input content and input frequency to select the optimal input method. For example, the image input unit can prioritize and suggest image input methods used by the applicant in the past. The image input unit can also predict and suggest image input methods to be used during specific time periods based on the applicant's past image input history. Furthermore, the image input unit can automatically display information that the applicant has frequently input in the past as candidates. In this way, by analyzing the past image input history, the optimal image input method can be provided to the applicant. Some or all of the above-described processing in the image input unit may be performed using, for example, AI, or may be performed without AI. For example, the image input unit can input the applicant's past image input history into AI, which can select the optimal input method.

[0131] The image input unit can filter the image based on the applicant's current living situation and areas of interest when inputting the image. The image input unit, for example, uses an algorithm for analyzing the applicant's current living situation and areas of interest. The algorithm filters relevant information based on the applicant's living situation and areas of interest. For example, the image input unit can prioritize input of relevant information based on the applicant's current living situation (e.g., whether or not the applicant has a job, their family situation, etc.). The image input unit can also filter and input relevant information based on the applicant's areas of interest (e.g., health, education, etc.). Furthermore, the image input unit can exclude unnecessary information and input only necessary information based on the applicant's living situation and areas of interest. In this way, by filtering information based on the applicant's living situation and areas of interest, only necessary information can be input. Some or all of the above-described processing in the image input unit can be performed using, for example, AI, or without AI. For example, the image input unit can input the applicant's living situation and areas of interest into AI, which then filters the information.

[0132] The image input unit can estimate the applicant's emotions and determine the priority of image input based on the estimated emotions. The image input unit uses, for example, an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, if the applicant is feeling stressed, the image input unit can prioritize input of important information and postpone other information. Furthermore, if the applicant is relaxed, the image input unit can input all information evenly. Furthermore, if the applicant is in a hurry, the image input unit can input the most important information first and proceed quickly. This allows important information to be input preferentially by determining the priority of image input according to the applicant'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, 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 image input unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the image input unit can input the applicant's emotional data into AI, which can then analyze the emotions and determine the priority of image input.

[0133] When inputting an image, the image input unit can prioritize inputting highly relevant information by taking into account the applicant's geographical location information. The image input unit, for example, uses an algorithm for analyzing the applicant's geographical location information. The algorithm prioritizes inputting relevant information based on the applicant's geographical location information. For example, the image input unit can prioritize inputting information about region-specific subsidy programs based on the applicant's place of residence. The image input unit can also prioritize inputting information about nearby medical institutions based on the applicant's current location. Furthermore, the image input unit can filter and input information about related regions based on the applicant's geographical location information. This allows highly relevant information to be prioritized by taking into account the applicant's geographical location information. Some or all of the above-described processing in the image input unit may be performed using, for example, AI, or may be performed without AI. For example, the image input unit can input the applicant's geographical location information into AI, which can analyze the information and prioritize inputting highly relevant information.

[0134] The image input unit can analyze the applicant's social media activity and input relevant information when inputting an image. The image input unit, for example, uses an algorithm for analyzing the applicant's social media activity. The algorithm inputs relevant information based on the applicant's social media activity. For example, the image input unit can input information about related grant programs based on information shared by the applicant on social media. The image input unit can also analyze the applicant's social media activity and prioritize input of relevant information. Furthermore, the image input unit can input relevant information based on the activity of the applicant's friends on social media. In this way, relevant information can be efficiently input by analyzing the applicant's social media activity. Some or all of the above-described processing in the image input unit can be performed, for example, using AI, or can be performed without using AI. For example, the image input unit can input the applicant's social media activity into AI, which can analyze the information and input relevant information.

[0135] The image output unit can estimate the applicant's emotions and adjust the image output presentation method based on the estimated emotions. The image output unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, the image output unit can provide images with calm colors when the applicant is stressed. The image output unit can provide images with bright colors when the applicant is relaxed. Furthermore, the image output unit can provide quick and concise images when the applicant is in a hurry. This allows for more appropriate information provision by adjusting the image output presentation method according to the applicant'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 a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the image output unit may be performed using, for example, AI, or without AI. For example, the image output unit can input the applicant's emotional data into AI, which can then analyze the emotions and adjust the way the image is expressed.

[0136] The image output unit can adjust the level of detail of the output based on the importance of the subsidy program when outputting an image. The image output unit, for example, uses an algorithm for evaluating the importance of the subsidy program. The algorithm adjusts the level of detail of the output based on the importance of the subsidy program. For example, the image output unit can provide detailed images for subsidy programs with high importance. The image output unit can also provide simple images for subsidy programs with low importance. Furthermore, the image output unit can adjust the level of detail of the output according to the importance of the subsidy program and provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the output based on the importance of the subsidy program. Some or all of the above-mentioned processing in the image output unit may be performed using, for example, AI, or may be performed without using AI. For example, the image output unit can input the importance of the subsidy program into AI, which analyzes the information and adjusts the level of detail of the output.

[0137] The image output unit can apply different output algorithms depending on the category of the subsidy program when outputting an image. The image output unit, for example, constructs a system for applying different output algorithms depending on the category of the subsidy program. The system selects an optimal output algorithm based on the category of the subsidy program. For example, the image output unit can apply a medical-related output algorithm to information related to medical expense subsidy programs. The image output unit can also apply a lifestyle-related output algorithm to information related to living assistance subsidy programs. Furthermore, the image output unit can also apply an education-related output algorithm to information related to education expense subsidy programs. This makes it possible to provide more appropriate information by applying different output algorithms depending on the category of the subsidy program. Some or all of the above-mentioned processing in the image output unit can be performed using, for example, AI, or without AI. For example, the image output unit can input the category of the subsidy program into AI, which can select the optimal output algorithm.

[0138] When outputting an image, the image output unit can improve the accuracy of the output by referring to the applicant's past image output results. The image output unit, for example, uses an algorithm for analyzing the applicant's past image output results. The algorithm improves the accuracy of the output based on the applicant's past image output results. For example, the image output unit can provide an optimal image based on the applicant's past image output results. The image output unit can also prioritize successful images from the applicant's past image output results. Furthermore, the image output unit can analyze the applicant's past image output results and improve the accuracy of the output. As a result, the accuracy of the output is improved by referring to the applicant's past image output results. Some or all of the above-described processing in the image output unit may be performed, for example, using AI, or may be performed without AI. For example, the image output unit can input the applicant's past image output results into AI, which can analyze the information and improve the accuracy of the output.

[0139] The image output unit can estimate the applicant's emotions and adjust the length of the image output based on the estimated emotions. The image output unit, for example, uses an emotion estimation algorithm to estimate the applicant's emotions. The emotion estimation algorithm analyzes the applicant's facial expressions, voice, and text data to estimate the applicant's emotions. For example, the image output unit can provide a short, to-the-point image if the applicant is stressed. Alternatively, the image output unit can provide a longer image containing detailed information if the applicant is relaxed. Furthermore, the image output unit can provide a quick, concise image if the applicant is in a hurry. This allows for more appropriate information provision by adjusting the length of the image output according to the applicant's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be 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 image output unit may be performed using, for example, AI, or without AI. For example, the image output unit can input the applicant's emotional data into AI, which can then analyze the emotions and adjust the length of the image output.

[0140] The image output unit can determine the output priority based on the submission date of the grant program when outputting the image. The image output unit, for example, uses an algorithm for evaluating the submission date of the grant program. The algorithm determines the output priority based on the submission date of the grant program. For example, the image output unit can prioritize providing information on grant programs with upcoming submission deadlines as images. The image output unit can also postpone providing information on grant programs with distant submission deadlines as images. Furthermore, the image output unit can adjust the image output priority based on the submission date of the grant program. In this way, by determining the output priority based on the submission date of the grant program, information can be provided at the optimal time. Some or all of the above-mentioned processing in the image output unit may be performed, for example, using AI, or may be performed without using AI. For example, the image output unit can input the submission date of the grant program into AI, which analyzes the information and determines the output priority.

[0141] The image output unit can adjust the output order based on the relevance of the subsidy programs when outputting images. The image output unit, for example, uses an algorithm for evaluating the relevance of the subsidy programs. The algorithm adjusts the output order based on the relevance of the subsidy programs. For example, the image output unit can first provide information on the subsidy programs most relevant to the applicant's situation in the form of images. The image output unit can also provide information on subsidy programs less relevant to the applicant's situation in the form of images later. Furthermore, the image output unit can adjust the image output order based on the relevance of the subsidy programs. In this way, by adjusting the output order based on the relevance of the subsidy programs, the most relevant information can be provided preferentially. Some or all of the above-described processing in the image output unit may be performed using, for example, AI, or may be performed without using AI. For example, the image output unit can input the relevance of the subsidy programs into AI, which can analyze the information and adjust the output order.

[0142] When outputting an image, the image output unit can adjust the use of technical terms in the image output according to the applicant's level of expertise. The image output unit, for example, uses an algorithm to evaluate the applicant's level of expertise. The algorithm adjusts the use of technical terms in the image output based on the applicant's level of expertise. For example, if the applicant has technical expertise, the image output unit can provide an image that uses a lot of technical terms. Alternatively, if the applicant does not have technical expertise, the image output unit can provide an image in easy-to-understand language. Furthermore, the image output unit can adjust the use of technical terms in the image output according to the applicant's level of expertise. This allows for the provision of information that is easier to understand by adjusting the use of technical terms according to the applicant's level of expertise. Some or all of the above-described processing in the image output unit can be performed, for example, using AI, or can be performed without AI. For example, the image output unit can input the applicant's level of expertise into AI, which can analyze the information and adjust the use of technical terms in the image output. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, proposal unit, generation unit, voice input unit, voice output unit, image input unit, and image output unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and provides an interface for the applicant to input information about their place of residence, financial situation, and medical expenses. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to propose an optimal subsidy system based on the applicant's situation. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates templates for application forms and required attachments. The voice input unit converts the applicant's voice into text data, for example, using the microphone 38B of the smart device 14. The voice output unit provides answers generated by the generation AI via a voice, for example, using the speaker 40B of the smart device 14. The image input unit analyzes image data entered by the applicant using the camera 42 of the smart device 14 and extracts necessary information. The image output unit provides information in a visual format such as a graph or chart based on information generated by the specific processing unit 290 of the data processing device 12, for example. === Hard Collateral 1-2 === Each of the above-described elements, including the reception unit, proposal unit, generation unit, voice input unit, voice output unit, image input unit, and image output unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for the applicant to input their place of residence, financial situation, and medical expenses. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to propose an optimal subsidy system based on the applicant's situation. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates templates for application forms and required attached documents. The voice input unit converts the applicant's voice into text data, for example, using the microphone 238 of the smart glasses 214. The voice output unit provides the answer generated by the generation AI by voice, for example, using the speaker 240 of the smart glasses 214. The image input unit analyzes image data input by the applicant using, for example, the camera 42 of the smart glasses 214, and extracts necessary information. The image output unit provides information in a visual format, such as a graph or chart, based on information generated by, for example, the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the above-described elements, including the reception unit, proposal unit, generation unit, voice input unit, voice output unit, image input unit, and image output unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface for the applicant to input their place of residence, financial situation, and medical expenses. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to propose an optimal subsidy system based on the applicant's situation. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates templates for application forms and required attached documents. The voice input unit converts the applicant's voice into text data, for example, using the microphone 238 of the headset terminal 314. The voice output unit provides the answer generated by the generation AI via a voice, for example, using the speaker 240 of the headset terminal 314. The image input unit analyzes image data input by the applicant using, for example, the camera 42 of the headset terminal 314, and extracts necessary information. The image output unit provides information in a visual format, such as a graph or chart, based on information generated by, for example, the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the above-described elements, including the reception unit, proposal unit, generation unit, voice input unit, voice output unit, image input unit, and image output unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and provides an interface for the applicant to input information about their place of residence, financial situation, and medical expenses. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and uses a generation AI to propose an optimal subsidy system based on the applicant's situation. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and automatically generates templates for application forms and required attached documents. The voice input unit converts the applicant's voice into text data, for example, using the microphone 238 of the robot 414. The voice output unit provides answers generated by the generation AI via a voice, for example, using the speaker 240 of the robot 414. The image input unit analyzes image data entered by the applicant using the camera 42 of the robot 414 and extracts necessary information. The image output unit provides information in a visual format such as a graph or chart based on information generated by the specific processing unit 290 of the data processing device 12, for example.

[0143] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0144] The suggestion unit can also estimate the emotion of the applicant and adjust the way the proposal is expressed based on the estimated emotion. For example, if the applicant is feeling stressed, a simple and easy-to-understand expression can be used. If the applicant is relaxed, an expression including detailed information can be used. Furthermore, if the applicant is in a hurry, a concise expression that focuses on the main points can be used. In this way, by adjusting the way the proposal is expressed depending on the emotion of the applicant, more appropriate proposals can be made.

[0145] The reception unit can also analyze the applicant's past application history and select the optimal input method. For example, it can prioritize and suggest input methods (voice, text, etc.) that the applicant has used in the past. It can also predict and suggest input methods to be used at specific times based on the applicant's past application history. It can also automatically display information that the applicant has frequently entered in the past as candidates. In this way, it is possible to provide the applicant with the optimal input method by analyzing their past application history.

[0146] The proposal unit can also adjust the level of detail of the proposal based on the importance of the grant program. For example, detailed information can be provided for grant programs with high importance. Concise information can also be provided for grant programs with low importance. Furthermore, the level of detail of the proposal can be adjusted according to the importance of the grant program to provide optimal information. In this way, optimal information can be provided by adjusting the level of detail of the proposal based on the importance of the grant program.

[0147] The generation unit can also estimate the emotion of the applicant and adjust the expression of the generated document based on the estimated emotion. For example, if the applicant is feeling stressed, a simple and easy-to-understand expression can be used. If the applicant is relaxed, an expression including detailed information can be used. Furthermore, if the applicant is in a hurry, a concise expression that focuses on the main points can be used. In this way, by adjusting the expression of the document according to the emotion of the applicant, more appropriate documents can be generated.

[0148] The voice input unit can also estimate the emotions of the applicant and adjust the timing of the voice input based on the estimated emotions. For example, if the applicant is feeling stressed, the timing of the voice input can be delayed to provide a relaxing environment. If the applicant is relaxed, the timing of the voice input can be accelerated to allow the applicant to input efficiently. Furthermore, if the applicant is in a hurry, the timing of the voice input can be optimized to allow the applicant to complete the input quickly. In this way, the burden on the applicant can be reduced by adjusting the timing of the voice input according to the applicant's emotions.

[0149] The image input unit can also estimate the emotions of the applicant and adjust the timing of image input based on the estimated emotions. For example, if the applicant is feeling stressed, the timing of image input can be delayed to provide a relaxing environment. Also, if the applicant is relaxed, the timing of image input can be accelerated to allow input to proceed efficiently. Furthermore, if the applicant is in a hurry, the timing of image input can be optimized to allow input to be completed quickly. In this way, the burden on the applicant can be reduced by adjusting the timing of image input according to the applicant's emotions.

[0150] The proposal unit can also apply different proposal algorithms depending on the category of the subsidy program. For example, a medical-related algorithm can be applied to a proposal regarding a medical expense subsidy program. A lifestyle-related algorithm can be applied to a proposal regarding a living assistance subsidy program. Furthermore, an education-related algorithm can be applied to a proposal regarding an education expense subsidy program. This allows for more appropriate proposals to be made by applying different proposal algorithms depending on the category of the subsidy program.

[0151] When generating documents, the generation unit can also determine the priority of documents based on the submission date for the grant program. For example, documents for grant programs with upcoming submission deadlines can be generated with priority. Documents for grant programs with more distant submission deadlines can also be generated at a later date. Furthermore, the priority of documents can also be adjusted based on the submission date for the grant program. In this way, by determining the priority of documents based on the submission date for the grant program, documents can be generated at the optimal time.

[0152] The voice output unit can also estimate the emotion of the applicant and adjust the voice output expression method based on the estimated emotion. For example, if the applicant is feeling stressed, information can be provided in a calm voice. If the applicant is relaxed, information can be provided in a cheerful voice. Furthermore, if the applicant is in a hurry, quick and concise voice output can be provided. In this way, by adjusting the voice output expression method according to the emotion of the applicant, more appropriate information can be provided.

[0153] The image output unit can also estimate the emotion of the applicant and adjust the way the image output is presented based on the estimated emotion. For example, if the applicant is feeling stressed, an image with calm colors can be provided. If the applicant is relaxed, an image with bright colors can be provided. Furthermore, if the applicant is in a hurry, a quick and concise image can be provided. In this way, by adjusting the way the image output is presented according to the emotion of the applicant, more appropriate information can be provided.

[0154] The processing flow of the second embodiment will be briefly explained below.

[0155] Step 1: The reception unit inputs the applicant's information, including the applicant's place of residence, financial situation, and medical expenses. The reception unit provides an interface for the applicant to input this information and also supports voice and image input. For example, voice input can be converted into text data using voice recognition technology. Step 2: The proposal unit proposes the most suitable subsidy system for the applicant based on the information entered by the reception unit. Using generative AI, the proposal unit analyzes the applicant's place of residence, financial situation, and medical expenses burden, and executes an algorithm to propose the most suitable subsidy system. For example, for elderly people living in a specific area, the proposal proposes medical expense subsidy systems available in that area. Step 3: The generation unit generates templates for the application form and required attached documents based on the grant system proposed by the proposal unit. The generation unit uses generation AI to automatically generate templates for the application form and required attached documents. The generation AI runs an algorithm to generate the format of the required documents based on the applicant's situation, and generates them in PDF or Word format.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0174] 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.

[0175] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0176] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0177] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0190] 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.

[0191] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0192] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0193] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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).

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0207] 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.

[0208] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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).

[0213] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0214] 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."

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] [Explanation of symbols]

[0228] 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 reception unit for inputting the applicant's status; a proposal unit that proposes a subsidy system based on the information input by the reception unit; a generation unit that automatically generates necessary documents based on the subsidy system proposed by the proposal unit; Equipped with A system characterized by:

2. The reception unit Enter information about the applicant's place of residence, financial situation, and medical expenses 2. The system of claim 1.

3. The proposal unit Based on the information input by the reception unit, a subsidy system suitable for the applicant is proposed.

2. The system of claim 1.

4. The generation unit Generates application forms and required attachment formats based on the grant programs proposed by the proposal department.

2. The system of claim 1.

5. A voice input unit is provided that allows applicants to input questions by voice.

2. The system of claim 1.

6. It has a voice output unit that enables the generation AI to provide answers by voice.

2. The system of claim 1.

7. Equipped with an image input unit that allows applicants to input information via images 2. The system of claim 1.

8. Equipped with an image output unit that enables the generation AI to provide information in the form of images 2. The system of claim 1.

9. The reception unit Analyze the applicant's emotions and adjust the timing of information input based on the analyzed emotions of the applicant.

2. The system of claim 1.

Images