System

Abstract

An object of a system according to an embodiment is to enable a freelance or a sole proprietor to easily make a final tax return.SOLUTION: A system includes an upload unit, an analysis unit, a creation unit, and an application unit. The upload unit uploads data. The analysis unit analyzes the data uploaded by the upload unit. The creation unit creates a final tax return document based on the data analyzed by the analysis unit. The application unit applies for the final tax return document created by the creation 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, freelancers and sole proprietors had to spend a lot of time preparing the necessary documents and checking the information they entered when filing their tax returns.

[0005] The system according to the embodiment aims to enable freelancers and sole proprietors to easily file tax returns. [Means for solving the problem]

[0006] The system according to the embodiment includes an upload unit, an analysis unit, a creation unit, and an application unit. The upload unit uploads data. The analysis unit analyzes the data uploaded by the upload unit. The creation unit creates tax return documents based on the data analyzed by the analysis unit. The application unit applies for the tax return documents created by the creation unit. [Effects of the Invention]

[0007] The system according to the embodiment can enable freelancers and sole proprietors to easily file tax returns. [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 tax return support system according to an embodiment of the present invention allows freelancers and sole proprietors to easily file their tax returns. This system automatically prepares and submits tax return documents by allowing users to select the fiscal year for which they wish to file and upload data they believe to be necessary. For example, a user selects the fiscal year for which they wish to file their tax return and uploads data such as income certificates and expense receipts. The system analyzes the uploaded data and automatically prepares the necessary tax return documents. The system then automatically submits the prepared documents. This significantly reduces the effort required for users to file their tax returns. This tax return support system significantly reduces the effort required for freelancers and sole proprietors to file their tax returns. For example, by simply uploading income certificates and expense receipts, tax return documents are automatically prepared and submitted, significantly reducing the effort required for users to file their tax returns. Furthermore, by using AI, the system automatically checks for errors in input data, allowing users to file their tax returns with peace of mind.

[0029] The tax return support system according to the embodiment includes an upload unit, an analysis unit, a creation unit, and an application unit. The upload unit allows a user to upload data necessary for filing a tax return. For example, data such as an income certificate and expense receipts can be uploaded. For example, the upload unit allows a user to scan an income certificate and upload it as digital data. The upload unit also allows a user to take a photo of an expense receipt with a smartphone and upload it as image data. The upload unit also allows a user to directly upload a digital income certificate. The analysis unit analyzes the data uploaded by the upload unit. For example, the analysis unit analyzes the data using AI to extract necessary information. For example, the analysis unit extracts the income amount from the income certificate and the expense amount from the expense receipt. The analysis unit also includes a formatting unit that unifies the format of the uploaded data. For example, the analysis unit converts data of different formats into a unified format. The analysis unit also includes an encryption unit that encrypts the uploaded data. For example, the analysis unit encrypts the uploaded data using AES encryption. The preparation unit prepares tax return documents based on the data analyzed by the analysis unit. The preparation unit automatically prepares tax return documents using, for example, AI. For example, the preparation unit prepares tax return documents based on income amounts and expense amounts. The preparation unit also includes a detection unit that detects errors in input content. For example, the preparation unit detects whether the input content contains any formal or logical errors. The application unit submits the tax return documents prepared by the preparation unit. For example, the application unit automatically transmits the prepared tax return documents to a tax office. For example, the application unit transmits the tax return documents through an electronic application system. The application unit also includes a feedback unit that provides feedback to the user. For example, the application unit notifies the user of the application results and provides an error message or a success message. This allows the tax return support system according to the embodiment to easily file tax returns.

[0030] The upload unit can upload data of income certificates or expense receipts. Examples of income certificates include, but are not limited to, pay slips, bank statements, contracts, etc. Examples of expense receipts include, but are not limited to, transportation receipts, accommodation receipts, and purchase details. For example, the upload unit allows a user to scan an income certificate and save it as image data. The upload unit then uploads the image data to the system. Alternatively, the upload unit can allow a user to take a photo of an expense receipt using a smartphone camera and save it as image data. For example, the upload unit automatically corrects the image data and uploads it to the system. Alternatively, the upload unit can allow a user to directly upload a digital income certificate to the system. For example, the upload unit uploads digital data in PDF format or text format to the system. This allows a user to easily upload necessary documents. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without AI. For example, the upload unit can input image data of an income certificate into a generation AI and have the generation AI convert the image data into text data.

[0031] The analysis unit may include a formatting unit that standardizes the format of the uploaded data. Examples of formats include, but are not limited to, CSV, PDF, and XML. The analysis unit may convert data of different formats into a unified format. For example, the analysis unit may convert data in CSV format into PDF format. The analysis unit may also convert data in PDF format into XML format. The analysis unit may also include an algorithm for converting data of different formats into a unified format. For example, the analysis unit may automatically detect the data format and convert it into an appropriate format. This standardizes the data format, thereby improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the uploaded data into a generation AI and have the generation AI standardize the data format.

[0032] The analysis unit may include an encryption unit that encrypts the uploaded data. Examples of encryption methods include, but are not limited to, AES encryption, RSA encryption, and hash functions. For example, the analysis unit encrypts the uploaded data using AES encryption. For example, the analysis unit encrypts the data to ensure security. The analysis unit can also encrypt the data using RSA encryption. For example, the analysis unit encrypts the data using public key cryptography. The analysis unit can also encrypt the data using a hash function. For example, the analysis unit uses a hash function to verify the integrity of the data. This improves data security. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the uploaded data to a generation AI and have the generation AI encrypt the data.

[0033] The creation unit may include a detection unit that detects errors in the input content. Examples of errors in the input content include, but are not limited to, formal errors, logical errors, and numerical errors. The creation unit, for example, detects whether the input content has any formal errors. For example, the creation unit checks whether the input content conforms to a predetermined format. The creation unit can also detect whether the input content has any logical errors. For example, the creation unit checks whether the input content is logically consistent. The creation unit can also detect whether the input content has any numerical errors. For example, the creation unit checks whether the numerical values ​​in the input content are correct. This enables accurate document creation by automatically detecting errors in the input content. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input the input content to a generation AI and have the generation AI detect errors.

[0034] The application unit may include a feedback unit that provides feedback to the user. Feedback may include, but is not limited to, an error message, a success message, and an improvement suggestion. For example, the application unit may notify the user of the application result. For example, the application unit may display a success message if the application is successful. The application unit may also display an error message if the application fails. For example, the application unit may notify the user of the cause of the application failure. The application unit may also provide the user with an improvement suggestion. For example, the application unit may suggest improvements to the application content to the user. This allows the user to check the application result and receive feedback. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit may input the application result into a generation AI and cause the generation AI to generate feedback.

[0035] The upload unit can analyze the user's past upload history and select the optimal upload method. Examples of upload methods include, but are not limited to, drag-and-drop, manual upload, automatic upload, and batch upload. The upload unit, for example, prioritizes and suggests an upload method that the user has frequently used in the past. For example, if the user has frequently used drag-and-drop in the past, the upload unit can suggest that method. Furthermore, if the user has previously uploaded during a specific time period, the upload unit can also prompt the user to upload during that time period. For example, if the user has previously uploaded at night, the upload unit can prompt the user to upload at night. Furthermore, if the user has previously failed to upload, the upload unit can analyze the cause of the failure and suggest an improved method. For example, if the user has previously failed to manually upload, the upload unit can suggest an automatic upload. This allows the optimal upload method to be suggested based on the user's past history. Some or all of the above-described processing in the upload unit may be performed using, or without, AI. For example, the upload unit can input the user's past upload history into a generation AI and have the generation AI select the optimal upload method.

[0036] The uploading unit may filter data based on the user's current project or areas of interest when uploading the data. Examples of filtering include, but are not limited to, keyword filtering, category filtering, and time filtering. For example, the uploading unit may filter data so that only data related to the user's current project is uploaded. For example, the uploading unit may filter data based on keywords related to the user's current project. The uploading unit may also suggest that data related to the user's areas of interest be preferentially uploaded. For example, the uploading unit may filter data based on categories related to the user's areas of interest. The uploading unit may also filter data so that data similar to data previously uploaded by the user is preferentially uploaded. For example, the uploading unit may filter similar data based on the characteristics of data previously uploaded by the user. This allows data to be filtered based on the user's interests and uploaded efficiently. Some or all of the above-described processing in the uploading unit may be performed using, or without, AI. For example, the uploading unit may input data related to the user's current project or areas of interest to a generation AI and have the generation AI perform the filtering.

[0037] The upload unit can select an appropriate upload means depending on the user's input method. Input methods include, but are not limited to, voice input, text input, and image input. For example, when a user uses voice input, the upload unit automatically converts the voice data into text and uploads it. For example, the upload unit can convert the voice data into text data using voice recognition technology. Furthermore, when a user uploads image data, the upload unit can extract and upload necessary information using image recognition technology. For example, the upload unit extracts text data from the image data and uploads it to the system. Furthermore, when a user uses text input, the upload unit can upload the text data as is. For example, the upload unit uploads the text data entered by the user to the system. This allows data to be uploaded using the optimal means depending on the user's input method. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without using AI. For example, the upload unit can input the user's input data into a generation AI and have the generation AI select the optimal upload means.

[0038] When uploading data, the uploading unit can prioritize uploading highly relevant data by taking into account the user's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP address, and location information services. For example, if the user is in a specific area, the uploading unit prioritizes uploading data related to that area. For example, if the user is in a specific city, the uploading unit prioritizes uploading data related to that city. Furthermore, if the user is traveling, the uploading unit can prioritize uploading data related to the user's travel destination. For example, the uploading unit prioritizes uploading image data taken by the user at the travel destination. Furthermore, if the user is at home, the uploading unit can prioritize uploading data related to the user's home. For example, the uploading unit prioritizes uploading text data created by the user at home. This allows highly relevant data to be prioritized based on the user's geographical location information. Some or all of the above-described processing in the uploading unit may be performed using, or without, AI. For example, the uploading unit may input the user's geographical location information to a generation AI and cause the generation AI to select highly relevant data.

[0039] When uploading data, the uploading unit can analyze the user's social media activity and upload related data. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of followers. For example, the uploading unit prioritizes uploading data shared by the user on social media. For example, the uploading unit prioritizes uploading image data shared by the user on social media. The uploading unit can also analyze the content of the user's social media posts and upload related data. For example, the uploading unit prioritizes uploading text data related to the content of the user's posts. The uploading unit can also upload related data based on the activity of the user's friends on social media. For example, the uploading unit prioritizes uploading data related to data shared by the user's friends. This makes it possible to upload related data based on the user's social media activity. Some or all of the above-described processing by the uploading unit may be performed using, or without, AI. For example, the uploading unit may input the user's social media activity data into a generation AI and cause the generation AI to select related data.

[0040] When uploading data, the upload unit can customize the upload method by reflecting the user's past feedback. Feedback includes, but is not limited to, user ratings, comments, and improvement suggestions. The upload unit, for example, suggests an optimal upload method based on feedback provided by the user in the past. For example, the upload unit suggests an upload method that the user has previously given a high rating. The upload unit can also avoid upload methods that the user has previously dissatisfied with and suggest an improved method. For example, the upload unit can avoid manual uploads that the user has previously dissatisfied with and suggest automatic uploads. The upload unit can also analyze the user's past feedback and simplify the upload procedure. For example, the upload unit can optimize the upload procedure based on the user's feedback. This allows the optimal upload method to be suggested based on the user's past feedback. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without using AI. For example, the upload unit can input the user's past feedback data into a generation AI and have the generation AI customize the upload method.

[0041] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. Examples of the importance of data include, but are not limited to, business impact, legal requirements, and user interest. The analysis unit, for example, performs a detailed analysis on data with high importance to provide highly accurate results. For example, the analysis unit performs a detailed analysis on data with high business impact. The analysis unit can also perform a simplified analysis on data with low importance to quickly provide results. For example, the analysis unit performs a simplified analysis on data with low user interest. The analysis unit can also appropriately allocate analysis resources according to the importance of the data. For example, the analysis unit allocates more resources to data with high importance and performs a detailed analysis. This allows the level of detail of the analysis to be adjusted according to the importance of the data, enabling efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the importance of the data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0042] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. Data categories include, but are not limited to, text data, numerical data, and image data. For example, the analysis unit applies an income data analysis algorithm to an income certificate. For example, the analysis unit analyzes the text data of the income certificate. The analysis unit can also apply an expense data analysis algorithm to an expense receipt. For example, the analysis unit analyzes the numerical data of the expense receipt. The analysis unit can also select an appropriate analysis algorithm to analyze other documents. For example, the analysis unit applies an image analysis algorithm to image data. This allows the optimal analysis algorithm to be applied depending on the data category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data category to the generation AI and cause the generation AI to apply the optimal analysis algorithm.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, past trends, error rates, and success rates. For example, the analysis unit performs highly accurate analysis of similar data based on the user's past analysis results. For example, the analysis unit performs analysis based on past trends. The analysis unit can also learn analysis patterns from the user's past analysis results and improve accuracy. For example, the analysis unit optimizes the analysis algorithm based on past error rates. The analysis unit can also optimize the analysis algorithm by referring to the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on past success rates. This allows the accuracy of the analysis to be improved by referring to the user's past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0044] During analysis, the analysis unit can determine analysis priorities based on the time of data submission. Examples of data submission times include, but are not limited to, submission deadlines, submission frequency, and submission timing. For example, the analysis unit prioritizes analysis of data with an upcoming submission deadline. For example, the analysis unit first analyzes data with an upcoming submission deadline. The analysis unit can also postpone analysis of data with a more distant submission deadline. For example, the analysis unit postpones analysis of data with a more distant submission deadline. The analysis unit can also appropriately allocate analysis resources based on the submission time. For example, the analysis unit allocates more resources to data with an upcoming submission deadline and performs analysis quickly. This allows analysis priorities to be determined based on the time of data submission, enabling efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the time of data submission to the generation AI and have the generation AI determine the analysis priorities.

[0045] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. Examples of data relevance include, but are not limited to, co-occurrence, correlation, and causal relationships. For example, the analysis unit prioritizes analysis of highly related data. For example, the analysis unit first analyzes data with high co-occurrence. The analysis unit can also postpone analysis of less related data. For example, the analysis unit postpones analysis of data with low correlation. The analysis unit can also optimize the order of analysis according to the relevance of the data. For example, the analysis unit prioritizes analysis of data with strong causal relationships. This allows the order of analysis to be adjusted based on the relevance of the data, enabling efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the relevance of the data to the generation AI and cause the generation AI to adjust the order of analysis.

[0046] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. Examples of technical expertise include, but are not limited to, qualifications, years of experience, and past achievements. For example, if the user has technical expertise, the analysis unit provides the analysis results using detailed technical terminology. For example, the analysis unit can explain the analysis results using technical terminology. Furthermore, if the user does not have technical expertise, the analysis unit can provide the analysis results in simple language. For example, the analysis unit can explain the analysis results while avoiding technical terminology. Furthermore, the analysis unit can adjust the explanation of the analysis results according to the user's level of expertise. For example, the analysis unit can use detailed explanations or simple explanations depending on the user's level of expertise. This allows the analysis results to be provided according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's level of expertise into the generation AI and have the generation AI explain the analysis results.

[0047] When creating a document, the creation unit can adjust the level of detail of the document based on the importance of the data. Examples of the level of detail of the document include, but are not limited to, comprehensiveness of information, detailed explanations, and concise summaries. For example, the creation unit creates a detailed document for data of high importance. For example, the creation unit creates a document that emphasizes comprehensiveness of information. The creation unit can also create a simplified document for data of low importance. For example, the creation unit creates a document that emphasizes concise summaries. The creation unit can also appropriately adjust the content of the document depending on the importance of the data. For example, the creation unit selectively uses detailed explanations and concise summaries. This allows the level of detail of the document to be adjusted depending on the importance of the data, enabling efficient document creation. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without AI. For example, the creation unit may input the importance of the data to a generation AI and cause the generation AI to adjust the level of detail of the document.

[0048] When creating a document, the creation unit can apply different creation algorithms depending on the category of data. Examples of creation algorithms include, but are not limited to, rule-based, machine learning-based, and template-based algorithms. For example, the creation unit applies an income data creation algorithm to an income certificate. For example, the creation unit creates a document based on the income certificate data. The creation unit can also apply an expense data creation algorithm to an expense receipt. For example, the creation unit creates a document based on the expense receipt data. The creation unit can also select an appropriate creation algorithm to create other documents. For example, the creation unit applies a template-based creation algorithm. This allows the optimal creation algorithm to be applied depending on the category of data. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the data category to the generation AI and cause the generation AI to apply the optimal creation algorithm.

[0049] When creating a document, the creation unit can improve the accuracy of the document creation by referring to the user's past creation results. Past creation results include, but are not limited to, success rates, error rates, and user feedback. For example, the creation unit creates documents with high accuracy for similar data based on the user's past creation results. For example, the creation unit creates documents based on past success rates. The creation unit can also learn creation patterns from the user's past creation results and improve accuracy. For example, the creation unit optimizes the creation algorithm based on past error rates. The creation unit can also optimize the creation algorithm by referring to the user's past creation results. For example, the creation unit adjusts the creation algorithm based on user feedback. This allows the accuracy of the document creation to be improved by referring to the user's past creation results. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without AI. For example, the creation unit can input the user's past creation results into a generation AI and cause the generation AI to improve the creation accuracy.

[0050] When creating a document, the creation unit can determine the priority of documents based on the time of data submission. Examples of data submission times include, but are not limited to, submission deadlines, submission frequency, and submission timing. For example, the creation unit prioritizes data with an upcoming submission deadline in the document. For example, the creation unit first reflects data with an upcoming submission deadline in the document. The creation unit can also create documents after data with a distant submission deadline. For example, the creation unit postpones data with a distant submission deadline. The creation unit can also appropriately allocate document creation resources based on the submission time. For example, the creation unit allocates more resources to data with an upcoming submission deadline and creates documents quickly. This allows document prioritization based on the time of data submission and efficient document creation. Some or all of the above-described processes in the creation unit may be performed using, or without, AI. For example, the creation unit can input the time of data submission into the generation AI and have the generation AI determine the document priorities.

[0051] The creation unit can adjust the order of documents based on the relevance of data when creating documents. Examples of data relevance include, but are not limited to, co-occurrence, correlation, and causal relationships. For example, the creation unit prioritizes reflecting highly relevant data in the document. For example, the creation unit first reflects data with high co-occurrence in the document. The creation unit can also create documents after data with low relevance. For example, the creation unit postpones data with low correlation. The creation unit can also optimize the order of documents according to the relevance of data. For example, the creation unit prioritizes reflecting data with strong causal relationships in the document. This allows the order of documents to be adjusted based on the relevance of data, enabling documents to be created efficiently. Some or all of the above-described processing in the creation unit may be performed using, or without, AI. For example, the creation unit may input the relevance of data to a generation AI and have the generation AI adjust the order of documents.

[0052] When creating a document, the creation unit can adjust the use of technical terminology in the document depending on the user's level of expertise. Examples of the level of expertise include, but are not limited to, qualifications, years of experience, and past achievements. For example, if the user has technical expertise, the creation unit creates the document using detailed technical terminology. For example, the creation unit creates the document using technical terminology. Furthermore, if the user does not have technical expertise, the creation unit can create the document using simple language. For example, the creation unit creates the document while avoiding technical terminology. Furthermore, the creation unit can adjust the content of the document depending on the user's level of expertise. For example, the creation unit can use detailed explanations or simple explanations depending on the user's level of expertise. This allows the content of the document to be adjusted depending on the user's level of expertise, creating a document that is easy to understand. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without AI. For example, the creation unit can input the user's level of expertise into a generation AI and have the generation AI adjust the content of the document.

[0053] The application unit can adjust the level of detail of the application based on the importance of the data when submitting the application. Examples of the level of detail of the application include, but are not limited to, comprehensiveness of information, detailed explanations, and concise summaries. For example, the application unit may submit a detailed application for highly important data to provide highly accurate results. For example, the application unit may submit an application that emphasizes comprehensiveness of information. The application unit may also submit a simplified application for less important data to provide quick results. For example, the application unit may submit an application that emphasizes concise summaries. The application unit may also appropriately allocate application resources according to the importance of the data. For example, the application unit may allocate more resources to highly important data and submit a detailed application. This allows the level of detail of the application to be adjusted according to the importance of the data, enabling efficient submission. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit may input the importance of the data into a generation AI and have the generation AI adjust the level of detail of the application.

[0054] The application unit can apply different application algorithms depending on the data category when submitting an application. Examples of application algorithms include, but are not limited to, rule-based, machine learning-based, and template-based algorithms. For example, the application unit applies an income data application algorithm to an income certificate. For example, the application unit submits an application based on the income certificate data. The application unit can also apply an expense data application algorithm to expense receipts. For example, the application unit submits an application based on the expense receipt data. The application unit can also select an appropriate application algorithm for other documents and submit an application. For example, the application unit applies a template-based application algorithm. This allows the optimal application algorithm to be applied depending on the data category. Some or all of the above-described processing in the application unit may be performed using, for example, AI, or may be performed without using AI. For example, the application unit can input the data category into a generation AI and have the generation AI apply the optimal application algorithm.

[0055] When submitting a request, the request unit can improve the accuracy of the request by referring to the user's past request results. Past request results include, but are not limited to, success rates, error rates, and user feedback. For example, the request unit makes a request with high accuracy for similar data based on the user's past request results. For example, the request unit submits a request based on past success rates. The request unit can also learn request patterns from the user's past request results and improve accuracy. For example, the request unit optimizes the request algorithm based on past error rates. The request unit can also optimize the request algorithm by referring to the user's past request results. For example, the request unit adjusts the request algorithm based on user feedback. This allows the accuracy of the request to be improved by referring to the user's past request results. Some or all of the above-described processing in the request unit may be performed using, for example, AI, or may be performed without AI. For example, the request unit can input the user's past request results into a generation AI and have the generation AI improve the accuracy of the request.

[0056] At the time of application, the application unit can determine the priority of applications based on the timing of data submission. Examples of data submission timing include, but are not limited to, submission deadlines, submission frequency, and submission timing. For example, the application unit prioritizes applications for data with an upcoming submission deadline. For example, the application unit first submits data with an upcoming submission deadline. The application unit can also postpone applications for data with a more distant submission deadline. For example, the application unit postpones applications for data with a more distant submission deadline. The application unit can also appropriately allocate application resources according to the submission timing. For example, the application unit allocates more resources to data with an upcoming submission deadline and submits the application quickly. This allows application priorities to be determined based on the timing of data submission, enabling efficient applications. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit can input the data submission timing into the generation AI and have the generation AI determine the priority of applications.

[0057] The application unit can adjust the order of applications based on the relevance of the data when submitting the application. Examples of data relevance include, but are not limited to, co-occurrence, correlation, and causal relationships. For example, the application unit prioritizes submitting highly relevant data. For example, the application unit may first submit data with high co-occurrence. The application unit can also postpone submitting data with low relevance. For example, the application unit may postpone submitting data with low correlation. The application unit can also optimize the order of applications based on the relevance of the data. For example, the application unit prioritizes submitting data with strong causal relationships. This allows the order of applications to be adjusted based on the relevance of the data, enabling efficient applications. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit may input the relevance of the data into a generation AI and have the generation AI adjust the order of applications.

[0058] When submitting an application, the application unit can adjust the use of technical terminology in the application depending on the user's level of expertise. Examples of technical terminology include, but are not limited to, qualifications, years of experience, and past achievements. For example, if the user has technical expertise, the application unit can submit the application using detailed technical terminology. For example, the application unit can submit the application using technical terminology. Furthermore, if the user does not have technical expertise, the application unit can submit the application using simple language. For example, the application unit can submit the application while avoiding technical terminology. Furthermore, the application unit can adjust the content of the application depending on the user's level of expertise. For example, the application unit can use detailed or concise explanations depending on the user's level of expertise. This allows the content of the application to be adjusted depending on the user's level of expertise, making the application easier to understand. Some or all of the above-described processing in the application unit may be performed using, for example, AI, or may be performed without AI. For example, the application unit can input the user's level of expertise into a generation AI and have the generation AI adjust the content of the application.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The upload unit can analyze the user's past upload history and select the optimal upload method. For example, it can preferentially suggest upload methods that the user has frequently used in the past. If the user has previously uploaded during a specific time period, it can encourage the user to upload during that time period. Also, if the user has previously failed to upload, it can analyze the cause and suggest an improved method. This makes it possible to suggest the optimal upload method based on the user's past history.

[0061] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, it can perform a detailed analysis on data of high importance and provide highly accurate results. It can also perform a simplified analysis on data of low importance and provide results quickly. It can also appropriately allocate analysis resources depending on the importance of the data. This allows the level of detail of the analysis to be adjusted depending on the importance of the data, enabling efficient analysis.

[0062] When uploading data, the upload unit can prioritize uploading highly relevant data in consideration of the user's geographical location information. For example, if the user is in a specific area, data related to that area can be prioritized for upload. If the user is traveling, data related to the travel destination can be prioritized for upload. Also, if the user is at home, data related to the home can be prioritized for upload. In this way, highly relevant data can be prioritized for upload based on the user's geographical location information.

[0063] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, it can perform highly accurate analysis of similar data based on the user's past analysis results. It can also learn analysis patterns from the user's past analysis results and improve accuracy. It can also optimize the analysis algorithm by referring to the user's past analysis results. This makes it possible to improve the accuracy of the analysis by referring to the user's past analysis results.

[0064] When creating documents, the creation department can determine the priority of documents based on the time of data submission. For example, data with an upcoming submission deadline can be reflected in the document first. Document creation for data with a distant submission deadline can also be postponed. Document creation resources can also be appropriately allocated depending on the submission time. This allows documents to be prioritized based on the time of data submission, allowing documents to be created efficiently.

[0065] The application unit can apply different application algorithms depending on the data category at the time of application. For example, an income data application algorithm can be applied to an income certificate. An expense data application algorithm can be applied to an expense receipt. Furthermore, an appropriate application algorithm can be selected for other documents and an application can be made. This allows the optimal application algorithm to be applied depending on the data category.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: In the upload section, users upload the data required for their tax return. For example, they can upload data such as income certificates and expense receipts. Users can scan income certificates and upload them as digital data, take photos of expense receipts with their smartphones and upload them as image data, or directly upload digital income certificates. Step 2: The analysis unit analyzes the data uploaded by the upload unit. For example, it uses AI to analyze the data and extracts income amounts from income certificates and expense amounts from expense receipts. The analysis unit also includes a formatting unit that standardizes the format of the uploaded data and converts data of different formats into a unified format. The analysis unit also includes an encryption unit that encrypts the uploaded data and encrypts the data using AES encryption. Step 3: The creation unit creates tax return documents based on the data analyzed by the analysis unit. For example, it uses AI to automatically create tax return documents based on income and expense amounts. The creation unit also includes a detection unit that detects input errors, checking for formal or logical errors. Step 4: The application unit submits the tax return documents prepared by the preparation unit. For example, the application unit automatically sends the prepared tax return documents to the tax office and transmits them through the electronic application system. The application unit also includes a feedback unit that provides feedback to the user, notifying the user of the application result and providing an error message or a success message.

[0068] (Example 2) A tax return support system according to an embodiment of the present invention allows freelancers and sole proprietors to easily file their tax returns. This system automatically prepares and submits tax return documents by allowing users to select the fiscal year for which they wish to file and upload data they believe to be necessary. For example, a user selects the fiscal year for which they wish to file their tax return and uploads data such as income certificates and expense receipts. The system analyzes the uploaded data and automatically prepares the necessary tax return documents. The system then automatically submits the prepared documents. This significantly reduces the effort required for users to file their tax returns. This tax return support system significantly reduces the effort required for freelancers and sole proprietors to file their tax returns. For example, by simply uploading income certificates and expense receipts, tax return documents are automatically prepared and submitted, significantly reducing the effort required for users to file their tax returns. Furthermore, by using AI, the system automatically checks for errors in input data, allowing users to file their tax returns with peace of mind.

[0069] The tax return support system according to the embodiment includes an upload unit, an analysis unit, a creation unit, and an application unit. The upload unit allows a user to upload data necessary for filing a tax return. For example, data such as an income certificate and expense receipts can be uploaded. For example, the upload unit allows a user to scan an income certificate and upload it as digital data. The upload unit also allows a user to take a photo of an expense receipt with a smartphone and upload it as image data. The upload unit also allows a user to directly upload a digital income certificate. The analysis unit analyzes the data uploaded by the upload unit. For example, the analysis unit analyzes the data using AI to extract necessary information. For example, the analysis unit extracts the income amount from the income certificate and the expense amount from the expense receipt. The analysis unit also includes a formatting unit that unifies the format of the uploaded data. For example, the analysis unit converts data of different formats into a unified format. The analysis unit also includes an encryption unit that encrypts the uploaded data. For example, the analysis unit encrypts the uploaded data using AES encryption. The preparation unit prepares tax return documents based on the data analyzed by the analysis unit. The preparation unit automatically prepares tax return documents using, for example, AI. For example, the preparation unit prepares tax return documents based on income amounts and expense amounts. The preparation unit also includes a detection unit that detects errors in input content. For example, the preparation unit detects whether the input content contains any formal or logical errors. The application unit submits the tax return documents prepared by the preparation unit. For example, the application unit automatically transmits the prepared tax return documents to a tax office. For example, the application unit transmits the tax return documents through an electronic application system. The application unit also includes a feedback unit that provides feedback to the user. For example, the application unit notifies the user of the application results and provides an error message or a success message. This allows the tax return support system according to the embodiment to easily file tax returns.

[0070] The upload unit can upload data of income certificates or expense receipts. Examples of income certificates include, but are not limited to, pay slips, bank statements, contracts, etc. Examples of expense receipts include, but are not limited to, transportation receipts, accommodation receipts, and purchase details. For example, the upload unit allows a user to scan an income certificate and save it as image data. The upload unit then uploads the image data to the system. Alternatively, the upload unit can allow a user to take a photo of an expense receipt using a smartphone camera and save it as image data. For example, the upload unit automatically corrects the image data and uploads it to the system. Alternatively, the upload unit can allow a user to directly upload a digital income certificate to the system. For example, the upload unit uploads digital data in PDF format or text format to the system. This allows a user to easily upload necessary documents. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without AI. For example, the upload unit can input image data of an income certificate into a generation AI and have the generation AI convert the image data into text data.

[0071] The analysis unit may include a formatting unit that standardizes the format of the uploaded data. Examples of formats include, but are not limited to, CSV, PDF, and XML. The analysis unit may convert data of different formats into a unified format. For example, the analysis unit may convert data in CSV format into PDF format. The analysis unit may also convert data in PDF format into XML format. The analysis unit may also include an algorithm for converting data of different formats into a unified format. For example, the analysis unit may automatically detect the data format and convert it into an appropriate format. This standardizes the data format, thereby improving the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the uploaded data into a generation AI and have the generation AI standardize the data format.

[0072] The analysis unit may include an encryption unit that encrypts the uploaded data. Examples of encryption methods include, but are not limited to, AES encryption, RSA encryption, and hash functions. For example, the analysis unit encrypts the uploaded data using AES encryption. For example, the analysis unit encrypts the data to ensure security. The analysis unit can also encrypt the data using RSA encryption. For example, the analysis unit encrypts the data using public key cryptography. The analysis unit can also encrypt the data using a hash function. For example, the analysis unit uses a hash function to verify the integrity of the data. This improves data security. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the uploaded data to a generation AI and have the generation AI encrypt the data.

[0073] The creation unit may include a detection unit that detects errors in the input content. Examples of errors in the input content include, but are not limited to, formal errors, logical errors, and numerical errors. The creation unit, for example, detects whether the input content has any formal errors. For example, the creation unit checks whether the input content conforms to a predetermined format. The creation unit can also detect whether the input content has any logical errors. For example, the creation unit checks whether the input content is logically consistent. The creation unit can also detect whether the input content has any numerical errors. For example, the creation unit checks whether the numerical values ​​in the input content are correct. This enables accurate document creation by automatically detecting errors in the input content. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input the input content to a generation AI and have the generation AI detect errors.

[0074] The application unit may include a feedback unit that provides feedback to the user. Feedback may include, but is not limited to, an error message, a success message, and an improvement suggestion. For example, the application unit may notify the user of the application result. For example, the application unit may display a success message if the application is successful. The application unit may also display an error message if the application fails. For example, the application unit may notify the user of the cause of the application failure. The application unit may also provide the user with an improvement suggestion. For example, the application unit may suggest improvements to the application content to the user. This allows the user to check the application result and receive feedback. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit may input the application result into a generation AI and cause the generation AI to generate feedback.

[0075] The upload unit can estimate a user's emotions and adjust the timing of data upload based on the estimated user emotions. Examples of user emotions include, but are not limited to, stress, relaxation, and hurry. For example, the upload unit delays the timing of uploading data when the user is feeling stressed. For example, the upload unit prompts the user to upload data during a time when the user is relaxed. The upload unit can also prompt the user to upload data immediately when the user is relaxed. For example, the upload unit supports smooth operation. The upload unit can also prompt the user to upload data quickly when the user is in a hurry. For example, the upload unit immediately processes necessary data. This allows data to be uploaded at the optimal timing depending on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or without AI. For example, the upload unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0076] The upload unit can analyze the user's past upload history and select the optimal upload method. Examples of upload methods include, but are not limited to, drag-and-drop, manual upload, automatic upload, and batch upload. The upload unit, for example, prioritizes and suggests an upload method that the user has frequently used in the past. For example, if the user has frequently used drag-and-drop in the past, the upload unit can suggest that method. Furthermore, if the user has previously uploaded during a specific time period, the upload unit can also prompt the user to upload during that time period. For example, if the user has previously uploaded at night, the upload unit can prompt the user to upload at night. Furthermore, if the user has previously failed to upload, the upload unit can analyze the cause of the failure and suggest an improved method. For example, if the user has previously failed to manually upload, the upload unit can suggest an automatic upload. This allows the optimal upload method to be suggested based on the user's past history. Some or all of the above-described processing in the upload unit may be performed using, or without, AI. For example, the upload unit can input the user's past upload history into a generation AI and have the generation AI select the optimal upload method.

[0077] The uploading unit may filter data based on the user's current project or areas of interest when uploading the data. Examples of filtering include, but are not limited to, keyword filtering, category filtering, and time filtering. For example, the uploading unit may filter data so that only data related to the user's current project is uploaded. For example, the uploading unit may filter data based on keywords related to the user's current project. The uploading unit may also suggest that data related to the user's areas of interest be preferentially uploaded. For example, the uploading unit may filter data based on categories related to the user's areas of interest. The uploading unit may also filter data so that data similar to data previously uploaded by the user is preferentially uploaded. For example, the uploading unit may filter similar data based on the characteristics of data previously uploaded by the user. This allows data to be filtered based on the user's interests and uploaded efficiently. Some or all of the above-described processing in the uploading unit may be performed using, or without, AI. For example, the uploading unit may input data related to the user's current project or areas of interest to a generation AI and have the generation AI perform the filtering.

[0078] The upload unit can select an appropriate upload means depending on the user's input method. Input methods include, but are not limited to, voice input, text input, and image input. For example, when a user uses voice input, the upload unit automatically converts the voice data into text and uploads it. For example, the upload unit can convert the voice data into text data using voice recognition technology. Furthermore, when a user uploads image data, the upload unit can extract and upload necessary information using image recognition technology. For example, the upload unit extracts text data from the image data and uploads it to the system. Furthermore, when a user uses text input, the upload unit can upload the text data as is. For example, the upload unit uploads the text data entered by the user to the system. This allows data to be uploaded using the optimal means depending on the user's input method. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without using AI. For example, the upload unit can input the user's input data into a generation AI and have the generation AI select the optimal upload means.

[0079] The upload unit can estimate the user's emotions and determine the priority of data to be uploaded based on the estimated user emotions. Data priorities include, but are not limited to, importance, urgency, and relevance. For example, when the user is feeling stressed, the upload unit postpones uploading less important data and prioritizes uploading more important data. For example, when the user is feeling stressed, the upload unit uploads more important data first. The upload unit can also upload all data equally when the user is relaxed. For example, when the user is relaxed, the upload unit uploads all data with the same priority. The upload unit can also upload the most important data first when the user is in a hurry. For example, when the user is in a hurry, the upload unit uploads the most important data first. This allows data to be prioritized according to the user's emotions and uploaded efficiently. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without using AI. For example, the upload unit may input user emotion data to the generation AI and have the generation AI estimate the emotion.

[0080] When uploading data, the uploading unit can prioritize uploading highly relevant data by taking into account the user's geographical location information. Geographical location information includes, but is not limited to, GPS data, IP address, and location information services. For example, if the user is in a specific area, the uploading unit prioritizes uploading data related to that area. For example, if the user is in a specific city, the uploading unit prioritizes uploading data related to that city. Furthermore, if the user is traveling, the uploading unit can prioritize uploading data related to the user's travel destination. For example, the uploading unit prioritizes uploading image data taken by the user at the travel destination. Furthermore, if the user is at home, the uploading unit can prioritize uploading data related to the user's home. For example, the uploading unit prioritizes uploading text data created by the user at home. This allows highly relevant data to be prioritized based on the user's geographical location information. Some or all of the above-described processing in the uploading unit may be performed using, or without, AI. For example, the uploading unit may input the user's geographical location information to a generation AI and cause the generation AI to select highly relevant data.

[0081] When uploading data, the uploading unit can analyze the user's social media activity and upload related data. Social media activity includes, but is not limited to, the content of posts, the number of likes, and the number of followers. For example, the uploading unit prioritizes uploading data shared by the user on social media. For example, the uploading unit prioritizes uploading image data shared by the user on social media. The uploading unit can also analyze the content of the user's social media posts and upload related data. For example, the uploading unit prioritizes uploading text data related to the content of the user's posts. The uploading unit can also upload related data based on the activity of the user's friends on social media. For example, the uploading unit prioritizes uploading data related to data shared by the user's friends. This makes it possible to upload related data based on the user's social media activity. Some or all of the above-described processing by the uploading unit may be performed using, or without, AI. For example, the uploading unit may input the user's social media activity data into a generation AI and cause the generation AI to select related data.

[0082] When uploading data, the upload unit can customize the upload method by reflecting the user's past feedback. Feedback includes, but is not limited to, user ratings, comments, and improvement suggestions. The upload unit, for example, suggests an optimal upload method based on feedback provided by the user in the past. For example, the upload unit suggests an upload method that the user has previously given a high rating. The upload unit can also avoid upload methods that the user has previously dissatisfied with and suggest an improved method. For example, the upload unit can avoid manual uploads that the user has previously dissatisfied with and suggest automatic uploads. The upload unit can also analyze the user's past feedback and simplify the upload procedure. For example, the upload unit can optimize the upload procedure based on the user's feedback. This allows the optimal upload method to be suggested based on the user's past feedback. Some or all of the above-described processing in the upload unit may be performed using, for example, AI, or may be performed without using AI. For example, the upload unit can input the user's past feedback data into a generation AI and have the generation AI customize the upload method.

[0083] The analysis unit can estimate the user's emotions and adjust the data analysis method based on the estimated user emotions. Data analysis methods include, but are not limited to, statistical analysis, machine learning, and data mining. For example, when the user is stressed, the analysis unit selects a simple analysis method to quickly provide results. For example, when the user is stressed, the analysis unit performs a simplified statistical analysis. Furthermore, when the user is relaxed, the analysis unit can select a detailed analysis method to provide highly accurate results. For example, when the user is relaxed, the analysis unit performs a detailed analysis using a machine learning algorithm. Furthermore, when the user is in a hurry, the analysis unit can prioritize analysis of the most important data. For example, when the user is in a hurry, the analysis unit analyzes data with high importance first. This allows the optimal analysis method to be selected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using 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 analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data to the generation AI and have the generation AI estimate the emotion.

[0084] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. Examples of the importance of data include, but are not limited to, business impact, legal requirements, and user interest. The analysis unit, for example, performs a detailed analysis on data with high importance to provide highly accurate results. For example, the analysis unit performs a detailed analysis on data with high business impact. The analysis unit can also perform a simplified analysis on data with low importance to quickly provide results. For example, the analysis unit performs a simplified analysis on data with low user interest. The analysis unit can also appropriately allocate analysis resources according to the importance of the data. For example, the analysis unit allocates more resources to data with high importance and performs a detailed analysis. This allows the level of detail of the analysis to be adjusted according to the importance of the data, enabling efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the importance of the data to the generation AI and have the generation AI adjust the level of detail of the analysis.

[0085] During analysis, the analysis unit can apply different analysis algorithms depending on the data category. Data categories include, but are not limited to, text data, numerical data, and image data. For example, the analysis unit applies an income data analysis algorithm to an income certificate. For example, the analysis unit analyzes the text data of the income certificate. The analysis unit can also apply an expense data analysis algorithm to an expense receipt. For example, the analysis unit analyzes the numerical data of the expense receipt. The analysis unit can also select an appropriate analysis algorithm to analyze other documents. For example, the analysis unit applies an image analysis algorithm to image data. This allows the optimal analysis algorithm to be applied depending on the data category. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data category to the generation AI and cause the generation AI to apply the optimal analysis algorithm.

[0086] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, past trends, error rates, and success rates. For example, the analysis unit performs highly accurate analysis of similar data based on the user's past analysis results. For example, the analysis unit performs analysis based on past trends. The analysis unit can also learn analysis patterns from the user's past analysis results and improve accuracy. For example, the analysis unit optimizes the analysis algorithm based on past error rates. The analysis unit can also optimize the analysis algorithm by referring to the user's past analysis results. For example, the analysis unit adjusts the analysis algorithm based on past success rates. This allows the accuracy of the analysis to be improved by referring to the user's past analysis results. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis results into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0087] The analysis unit can estimate the user's emotions and determine analysis priorities based on the estimated user emotions. Analysis priorities include, but are not limited to, the importance, urgency, and relevance of data. For example, when the user is stressed, the analysis unit prioritizes analysis of data with high importance. For example, when the user is stressed, the analysis unit analyzes data with high importance first. Furthermore, when the user is relaxed, the analysis unit can analyze all data equally. For example, when the user is relaxed, the analysis unit analyzes all data with the same priority. Furthermore, when the user is in a hurry, the analysis unit can analyze the most important data first. For example, when the user is in a hurry, the analysis unit analyzes the most important data first. This allows analysis priorities to be determined according to the user's emotions, enabling efficient analysis. Emotion estimation is achieved using an emotion estimation function, such as 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 analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input user emotion data to the generation AI and have the generation AI estimate the emotion.

[0088] During analysis, the analysis unit can determine analysis priorities based on the time of data submission. Examples of data submission times include, but are not limited to, submission deadlines, submission frequency, and submission timing. For example, the analysis unit prioritizes analysis of data with an upcoming submission deadline. For example, the analysis unit first analyzes data with an upcoming submission deadline. The analysis unit can also postpone analysis of data with a more distant submission deadline. For example, the analysis unit postpones analysis of data with a more distant submission deadline. The analysis unit can also appropriately allocate analysis resources based on the submission time. For example, the analysis unit allocates more resources to data with an upcoming submission deadline and performs analysis quickly. This allows analysis priorities to be determined based on the time of data submission, enabling efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the time of data submission to the generation AI and have the generation AI determine the analysis priorities.

[0089] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the data. Examples of data relevance include, but are not limited to, co-occurrence, correlation, and causal relationships. For example, the analysis unit prioritizes analysis of highly related data. For example, the analysis unit first analyzes data with high co-occurrence. The analysis unit can also postpone analysis of less related data. For example, the analysis unit postpones analysis of data with low correlation. The analysis unit can also optimize the order of analysis according to the relevance of the data. For example, the analysis unit prioritizes analysis of data with strong causal relationships. This allows the order of analysis to be adjusted based on the relevance of the data, enabling efficient analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the relevance of the data to the generation AI and cause the generation AI to adjust the order of analysis.

[0090] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. Examples of technical expertise include, but are not limited to, qualifications, years of experience, and past achievements. For example, if the user has technical expertise, the analysis unit provides the analysis results using detailed technical terminology. For example, the analysis unit can explain the analysis results using technical terminology. Furthermore, if the user does not have technical expertise, the analysis unit can provide the analysis results in simple language. For example, the analysis unit can explain the analysis results while avoiding technical terminology. Furthermore, the analysis unit can adjust the explanation of the analysis results according to the user's level of expertise. For example, the analysis unit can use detailed explanations or simple explanations depending on the user's level of expertise. This allows the analysis results to be provided according to the user's level of expertise. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's level of expertise into the generation AI and have the generation AI explain the analysis results.

[0091] The creation unit can estimate the user's emotions and adjust the document creation method based on the estimated user's emotions. Examples of document creation methods include, but are not limited to, template-based, custom format, and guideline-based creation. For example, when the user is stressed, the creation unit selects a simple document creation method to quickly create a document. For example, the creation unit selects a template-based document creation method. Furthermore, when the user is relaxed, the creation unit can select a detailed document creation method to create a highly accurate document. For example, the creation unit selects a custom format document creation method. Furthermore, when the user is in a hurry, the creation unit can prioritize the most important information in the document. For example, the creation unit selects a guideline-based creation method. This allows the optimal document creation method to be selected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or without AI. For example, the creation unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0092] When creating a document, the creation unit can adjust the level of detail of the document based on the importance of the data. Examples of the level of detail of the document include, but are not limited to, comprehensiveness of information, detailed explanations, and concise summaries. For example, the creation unit creates a detailed document for data of high importance. For example, the creation unit creates a document that emphasizes comprehensiveness of information. The creation unit can also create a simplified document for data of low importance. For example, the creation unit creates a document that emphasizes concise summaries. The creation unit can also appropriately adjust the content of the document depending on the importance of the data. For example, the creation unit selectively uses detailed explanations and concise summaries. This allows the level of detail of the document to be adjusted depending on the importance of the data, enabling efficient document creation. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without AI. For example, the creation unit may input the importance of the data to a generation AI and cause the generation AI to adjust the level of detail of the document.

[0093] When creating a document, the creation unit can apply different creation algorithms depending on the category of data. Examples of creation algorithms include, but are not limited to, rule-based, machine learning-based, and template-based algorithms. For example, the creation unit applies an income data creation algorithm to an income certificate. For example, the creation unit creates a document based on the income certificate data. The creation unit can also apply an expense data creation algorithm to an expense receipt. For example, the creation unit creates a document based on the expense receipt data. The creation unit can also select an appropriate creation algorithm to create other documents. For example, the creation unit applies a template-based creation algorithm. This allows the optimal creation algorithm to be applied depending on the category of data. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the data category to the generation AI and cause the generation AI to apply the optimal creation algorithm.

[0094] When creating a document, the creation unit can improve the accuracy of the document creation by referring to the user's past creation results. Past creation results include, but are not limited to, success rates, error rates, and user feedback. For example, the creation unit creates documents with high accuracy for similar data based on the user's past creation results. For example, the creation unit creates documents based on past success rates. The creation unit can also learn creation patterns from the user's past creation results and improve accuracy. For example, the creation unit optimizes the creation algorithm based on past error rates. The creation unit can also optimize the creation algorithm by referring to the user's past creation results. For example, the creation unit adjusts the creation algorithm based on user feedback. This allows the accuracy of the document creation to be improved by referring to the user's past creation results. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without AI. For example, the creation unit can input the user's past creation results into a generation AI and cause the generation AI to improve the creation accuracy.

[0095] The creation unit can estimate the user's emotions and adjust the length of the document based on the estimated user's emotions. Examples of document length include, but are not limited to, the number of pages, the number of characters, and the number of sections. For example, when the user is stressed, the creation unit creates a document that is short and to the point. For example, the creation unit reduces the number of pages and creates a document that focuses on the main points. Furthermore, when the user is relaxed, the creation unit can create a longer document that includes detailed explanations. For example, the creation unit increases the number of sections and creates a document that includes detailed explanations. Furthermore, when the user is in a hurry, the creation unit can prioritize the most important information in the document. For example, the creation unit reduces the number of characters and prioritizes important information in the document. This allows the length of the document to be adjusted according to the user's emotions, enabling efficient document creation. 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 creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit may input user emotion data to the generation AI and have the generation AI estimate the emotion.

[0096] When creating a document, the creation unit can determine the priority of documents based on the time of data submission. Examples of data submission times include, but are not limited to, submission deadlines, submission frequency, and submission timing. For example, the creation unit prioritizes data with an upcoming submission deadline in the document. For example, the creation unit first reflects data with an upcoming submission deadline in the document. The creation unit can also create documents after data with a distant submission deadline. For example, the creation unit postpones data with a distant submission deadline. The creation unit can also appropriately allocate document creation resources based on the submission time. For example, the creation unit allocates more resources to data with an upcoming submission deadline and creates documents quickly. This allows document prioritization based on the time of data submission and efficient document creation. Some or all of the above-described processes in the creation unit may be performed using, or without, AI. For example, the creation unit can input the time of data submission into the generation AI and have the generation AI determine the document priorities.

[0097] The creation unit can adjust the order of documents based on the relevance of data when creating documents. Examples of data relevance include, but are not limited to, co-occurrence, correlation, and causal relationships. For example, the creation unit prioritizes reflecting highly relevant data in the document. For example, the creation unit first reflects data with high co-occurrence in the document. The creation unit can also create documents after data with low relevance. For example, the creation unit postpones data with low correlation. The creation unit can also optimize the order of documents according to the relevance of data. For example, the creation unit prioritizes reflecting data with strong causal relationships in the document. This allows the order of documents to be adjusted based on the relevance of data, enabling documents to be created efficiently. Some or all of the above-described processing in the creation unit may be performed using, or without, AI. For example, the creation unit may input the relevance of data to a generation AI and have the generation AI adjust the order of documents.

[0098] When creating a document, the creation unit can adjust the use of technical terminology in the document depending on the user's level of expertise. Examples of the level of expertise include, but are not limited to, qualifications, years of experience, and past achievements. For example, if the user has technical expertise, the creation unit creates the document using detailed technical terminology. For example, the creation unit creates the document using technical terminology. Furthermore, if the user does not have technical expertise, the creation unit can create the document using simple language. For example, the creation unit creates the document while avoiding technical terminology. Furthermore, the creation unit can adjust the content of the document depending on the user's level of expertise. For example, the creation unit can use detailed explanations or simple explanations depending on the user's level of expertise. This allows the content of the document to be adjusted depending on the user's level of expertise, creating a document that is easy to understand. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without AI. For example, the creation unit can input the user's level of expertise into a generation AI and have the generation AI adjust the content of the document.

[0099] The application unit can estimate the user's emotions and adjust the application method based on the estimated user emotions. Application methods include, but are not limited to, online applications, mail applications, and in-person applications. For example, if the user is feeling stressed, the application unit selects a simple application method to quickly submit the application. For example, the application unit selects online applications. Furthermore, if the user is relaxed, the application unit can select a detailed application method to submit an accurate application. For example, the application unit selects in-person applications. Furthermore, if the user is in a hurry, the application unit can prioritize the most important information in the application. For example, the application unit selects mail applications. This allows the optimal application method to be selected according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. Generation AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the application unit may be performed using AI, or may be performed without AI. For example, the application unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0100] The application unit can adjust the level of detail of the application based on the importance of the data when submitting the application. Examples of the level of detail of the application include, but are not limited to, comprehensiveness of information, detailed explanations, and concise summaries. For example, the application unit may submit a detailed application for highly important data to provide highly accurate results. For example, the application unit may submit an application that emphasizes comprehensiveness of information. The application unit may also submit a simplified application for less important data to provide quick results. For example, the application unit may submit an application that emphasizes concise summaries. The application unit may also appropriately allocate application resources according to the importance of the data. For example, the application unit may allocate more resources to highly important data and submit a detailed application. This allows the level of detail of the application to be adjusted according to the importance of the data, enabling efficient submission. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit may input the importance of the data into a generation AI and have the generation AI adjust the level of detail of the application.

[0101] The application unit can apply different application algorithms depending on the data category when submitting an application. Examples of application algorithms include, but are not limited to, rule-based, machine learning-based, and template-based algorithms. For example, the application unit applies an income data application algorithm to an income certificate. For example, the application unit submits an application based on the income certificate data. The application unit can also apply an expense data application algorithm to expense receipts. For example, the application unit submits an application based on the expense receipt data. The application unit can also select an appropriate application algorithm for other documents and submit an application. For example, the application unit applies a template-based application algorithm. This allows the optimal application algorithm to be applied depending on the data category. Some or all of the above-described processing in the application unit may be performed using, for example, AI, or may be performed without using AI. For example, the application unit can input the data category into a generation AI and have the generation AI apply the optimal application algorithm.

[0102] When submitting a request, the request unit can improve the accuracy of the request by referring to the user's past request results. Past request results include, but are not limited to, success rates, error rates, and user feedback. For example, the request unit makes a request with high accuracy for similar data based on the user's past request results. For example, the request unit submits a request based on past success rates. The request unit can also learn request patterns from the user's past request results and improve accuracy. For example, the request unit optimizes the request algorithm based on past error rates. The request unit can also optimize the request algorithm by referring to the user's past request results. For example, the request unit adjusts the request algorithm based on user feedback. This allows the accuracy of the request to be improved by referring to the user's past request results. Some or all of the above-described processing in the request unit may be performed using, for example, AI, or may be performed without AI. For example, the request unit can input the user's past request results into a generation AI and have the generation AI improve the accuracy of the request.

[0103] The request unit can estimate the user's emotions and determine the priority of requests based on the estimated user emotions. The priority of requests includes, but is not limited to, the importance, urgency, and relevance of data. For example, when the user is stressed, the request unit prioritizes requests with higher importance. For example, when the user is stressed, the request unit prioritizes requests with higher importance first. Furthermore, when the user is relaxed, the request unit can process all requests equally. For example, when the user is relaxed, the request unit prioritizes all requests with the same priority. Furthermore, when the user is in a hurry, the request unit can process the most important request first. For example, when the user is in a hurry, the request unit prioritizes the most important request. This allows requests to be prioritized according to the user's emotions and submitted efficiently. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the request unit may be performed using, for example, AI, or may be performed without using AI. For example, the request unit may input user emotion data into the generation AI and have the generation AI estimate the emotion.

[0104] At the time of application, the application unit can determine the priority of applications based on the timing of data submission. Examples of data submission timing include, but are not limited to, submission deadlines, submission frequency, and submission timing. For example, the application unit prioritizes applications for data with an upcoming submission deadline. For example, the application unit first submits data with an upcoming submission deadline. The application unit can also postpone applications for data with a more distant submission deadline. For example, the application unit postpones applications for data with a more distant submission deadline. The application unit can also appropriately allocate application resources according to the submission timing. For example, the application unit allocates more resources to data with an upcoming submission deadline and submits the application quickly. This allows application priorities to be determined based on the timing of data submission, enabling efficient applications. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit can input the data submission timing into the generation AI and have the generation AI determine the priority of applications.

[0105] The application unit can adjust the order of applications based on the relevance of the data when submitting the application. Examples of data relevance include, but are not limited to, co-occurrence, correlation, and causal relationships. For example, the application unit prioritizes submitting highly relevant data. For example, the application unit may first submit data with high co-occurrence. The application unit can also postpone submitting data with low relevance. For example, the application unit may postpone submitting data with low correlation. The application unit can also optimize the order of applications based on the relevance of the data. For example, the application unit prioritizes submitting data with strong causal relationships. This allows the order of applications to be adjusted based on the relevance of the data, enabling efficient applications. Some or all of the above-described processing in the application unit may be performed using, or without, AI. For example, the application unit may input the relevance of the data into a generation AI and have the generation AI adjust the order of applications.

[0106] When submitting an application, the application unit can adjust the use of technical terminology in the application depending on the user's level of expertise. Examples of technical terminology include, but are not limited to, qualifications, years of experience, and past achievements. For example, if the user has technical expertise, the application unit can submit the application using detailed technical terminology. For example, the application unit can submit the application using technical terminology. Furthermore, if the user does not have technical expertise, the application unit can submit the application using simple language. For example, the application unit can submit the application while avoiding technical terminology. Furthermore, the application unit can adjust the content of the application depending on the user's level of expertise. For example, the application unit can use detailed or concise explanations depending on the user's level of expertise. This allows the content of the application to be adjusted depending on the user's level of expertise, making the application easier to understand. Some or all of the above-described processing in the application unit may be performed using, for example, AI, or may be performed without AI. For example, the application unit can input the user's level of expertise into a generation AI and have the generation AI adjust the content of the application. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, creation unit, and application unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the upload unit allows a user to upload income certificates and expense receipts using the reception device 38 of the smart device 14. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded data and extracts necessary information. For example, the creation unit is realized by the specific processing unit 290 of the data processing device 12 and creates tax return documents based on the analyzed data. For example, the application unit is realized by the specific processing unit 290 of the data processing device 12 and automatically transmits the created tax return documents to a tax office. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, creation unit, and application unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the upload unit allows a user to upload income certificates or expense receipts using the microphone 238 of the smart glasses 214. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded data and extracts necessary information. For example, the creation unit is realized by the specific processing unit 290 of the data processing device 12 and creates tax return documents based on the analyzed data. For example, the application unit is realized by the specific processing unit 290 of the data processing device 12 and automatically transmits the created tax return documents to a tax office. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, creation unit, and application unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the upload unit allows a user to upload income certificates and expense receipts using the microphone 238 of the headset-type terminal 314. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded data and extracts necessary information. For example, the creation unit is realized by the specific processing unit 290 of the data processing device 12 and creates tax return documents based on the analyzed data. For example, the application unit is realized by the specific processing unit 290 of the data processing device 12 and automatically transmits the created tax return documents to a tax office. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, creation unit, and application unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the upload unit allows a user to upload income certificates and expense receipts using the microphone 238 of the robot 414. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded data and extracts necessary information. For example, the creation unit is realized by the specific processing unit 290 of the data processing device 12 and creates tax return documents based on the analyzed data. For example, the application unit is realized by the specific processing unit 290 of the data processing device 12 and automatically transmits the created tax return documents to a tax office.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] The analysis unit can estimate the user's emotions and adjust the data analysis method based on the estimated user emotions. For example, if the user is feeling stressed, a simple analysis method can be selected to provide quick results. If the user is relaxed, a detailed analysis method can be selected to provide highly accurate results. Also, if the user is in a hurry, the most important data can be prioritized for analysis. This allows the optimal analysis method to be selected according to the user's emotions.

[0109] The upload unit can analyze the user's past upload history and select the optimal upload method. For example, it can preferentially suggest upload methods that the user has frequently used in the past. If the user has previously uploaded during a specific time period, it can encourage the user to upload during that time period. Also, if the user has previously failed to upload, it can analyze the cause and suggest an improved method. This makes it possible to suggest the optimal upload method based on the user's past history.

[0110] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, it can perform a detailed analysis on data of high importance and provide highly accurate results. It can also perform a simplified analysis on data of low importance and provide results quickly. It can also appropriately allocate analysis resources depending on the importance of the data. This allows the level of detail of the analysis to be adjusted depending on the importance of the data, enabling efficient analysis.

[0111] The creation unit can estimate the user's emotions and adjust the document creation method based on the estimated user's emotions. For example, if the user is feeling stressed, a simple document creation method can be selected to quickly create a document. If the user is relaxed, a detailed document creation method can be selected to create a highly accurate document. Also, if the user is in a hurry, the most important information can be reflected in the document with priority. This makes it possible to select the optimal document creation method according to the user's emotions.

[0112] The application unit can estimate the user's emotions and adjust the application method based on the estimated user emotions. For example, if the user is feeling stressed, a simple application method can be selected to quickly submit an application. If the user is relaxed, a detailed application method can be selected to submit an application with high accuracy. Also, if the user is in a hurry, the most important information can be reflected in the application with priority. This makes it possible to select the optimal application method according to the user's emotions.

[0113] When uploading data, the upload unit can prioritize uploading highly relevant data in consideration of the user's geographical location information. For example, if the user is in a specific area, data related to that area can be prioritized for upload. If the user is traveling, data related to the travel destination can be prioritized for upload. Also, if the user is at home, data related to the home can be prioritized for upload. In this way, highly relevant data can be prioritized for upload based on the user's geographical location information.

[0114] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, it can perform highly accurate analysis of similar data based on the user's past analysis results. It can also learn analysis patterns from the user's past analysis results and improve accuracy. It can also optimize the analysis algorithm by referring to the user's past analysis results. This makes it possible to improve the accuracy of the analysis by referring to the user's past analysis results.

[0115] When creating documents, the creation department can determine the priority of documents based on the time of data submission. For example, data with an upcoming submission deadline can be reflected in the document first. Document creation for data with a distant submission deadline can also be postponed. Document creation resources can also be appropriately allocated depending on the submission time. This allows documents to be prioritized based on the time of data submission, allowing documents to be created efficiently.

[0116] The application unit can apply different application algorithms depending on the data category at the time of application. For example, an income data application algorithm can be applied to an income certificate. An expense data application algorithm can be applied to an expense receipt. Furthermore, an appropriate application algorithm can be selected for other documents and an application can be made. This allows the optimal application algorithm to be applied depending on the data category.

[0117] The request unit can estimate the user's emotions and determine the priority of requests based on the estimated user's emotions. For example, if the user is feeling stressed, requests with high importance can be given priority. If the user is relaxed, all requests can be processed equally. Also, if the user is in a hurry, the most important request can be processed first. In this way, the priority of requests can be determined according to the user's emotions, and requests can be made efficiently.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: In the upload section, users upload the data required for their tax return. For example, they can upload data such as income certificates and expense receipts. Users can scan income certificates and upload them as digital data, take photos of expense receipts with their smartphones and upload them as image data, or directly upload digital income certificates. Step 2: The analysis unit analyzes the data uploaded by the upload unit. For example, it uses AI to analyze the data and extracts income amounts from income certificates and expense amounts from expense receipts. The analysis unit also includes a formatting unit that standardizes the format of the uploaded data and converts data of different formats into a unified format. The analysis unit also includes an encryption unit that encrypts the uploaded data and encrypts the data using AES encryption. Step 3: The creation unit creates tax return documents based on the data analyzed by the analysis unit. For example, it uses AI to automatically create tax return documents based on income and expense amounts. The creation unit also includes a detection unit that detects input errors, checking for formal or logical errors. Step 4: The application unit submits the tax return documents prepared by the preparation unit. For example, the application unit automatically sends the prepared tax return documents to the tax office and transmits them through the electronic application system. The application unit also includes a feedback unit that provides feedback to the user, notifying the user of the application result and providing an error message or a success message.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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."

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] [Explanation of symbols]

[0192] 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. an upload unit for uploading data; an analysis unit that analyzes the data uploaded by the upload unit; a preparation unit that prepares tax return documents based on the data analyzed by the analysis unit; an application unit that applies for the final tax return documents prepared by the preparation unit; A system characterized by:

2. The upload unit Upload your proof of income or expense receipts 2. The system of claim 1.

3. The analysis unit It has a formatting section that unifies the format of uploaded data.

2. The system of claim 1.

4. The analysis unit Equipped with an encryption unit that encrypts uploaded data 2. The system of claim 1.

5. The creation unit Equipped with a detection unit that detects input errors 2. The system of claim 1.

6. The application department A feedback unit is provided to provide feedback to the user.

2. The system of claim 1.

7. The upload unit Inferring user emotions and adjusting the timing of data uploads based on the estimated user emotions 2. The system of claim 1.

8. The upload unit Analyze the user's upload history and select the appropriate upload method 2. The system of claim 1.

Images