system

Abstract

The system according to the embodiment aims to improve the efficiency of preparing tax return documents and reduce costs. [Solution] The system according to the embodiment comprises an information input unit, an analysis unit, a document generation unit, a confirmation / correction unit, and a submission unit. The information input unit inputs information on income, expenses, and deductions. The analysis unit analyzes the information input by the information input unit and selects the format of the tax return. The document generation unit generates the tax return based on the format selected by the analysis unit. The confirmation / correction unit allows the user to confirm and correct the tax return generated by the document generation unit. The submission unit electronically submits the tax return finalized by the confirmation / correction unit to the tax office.

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, preparing tax return documents was time-consuming and expensive to hire a tax accountant.

[0005] The system according to the embodiment aims to improve the efficiency of preparing tax return documents and reduce costs. [Means for solving the problem]

[0006] The system according to the embodiment includes an information input unit, an analysis unit, a document generation unit, a confirmation / correction unit, and a submission unit. The information input unit inputs information on income, expenses, and deductions. The analysis unit analyzes the information input by the information input unit and selects the format of the tax return. The document generation unit generates the tax return based on the format selected by the analysis unit. The confirmation / correction unit allows the user to confirm and correct the tax return generated by the document generation unit. The submission unit electronically submits the tax return finalized by the confirmation / correction unit to the tax office. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of preparing tax return documents and reduce costs. [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 preparation system according to an embodiment of the present invention allows users to input information such as income, expenses, and deductions, analyze it using AI, generate tax return documents, and then review and revise them before electronically submitting them to the tax office. The tax return preparation system allows users to input necessary information, analyze the input information using AI, and automatically generate appropriate tax return documents. The generated documents are then provided to the user for review and revision. For example, the tax return preparation system may provide an interface through which users input information such as income, expenses, and deductions. The tax return preparation system then analyzes the input information using AI and selects the appropriate tax return format. The AI ​​then automatically generates tax return documents based on the analysis results. The tax return preparation system may then provide an interface through which users can review the generated tax return documents and revise them as necessary. The tax return preparation system then has the function of electronically submitting the finalized tax return documents to the tax office. This significantly reduces the effort required to prepare tax return documents and also reduces the cost of hiring a tax accountant. This will make the tax return preparation system easier to use, reducing the burden on users. Furthermore, the use of AI will improve the accuracy of tax return documents.

[0029] The tax return preparation system according to the embodiment includes an information input unit, an analysis unit, a document generation unit, a confirmation / correction unit, and a submission unit. The information input unit inputs information such as income, expenses, and deductions. Income includes, but is not limited to, salary income, business income, and investment income. Expenses include, but are not limited to, business expenses, medical expenses, and education expenses. Deductions include, but are not limited to, basic deductions, spousal deductions, and dependent deductions. The information input unit provides, for example, an interface through which a user inputs information such as income, expenses, and deductions. The analysis unit uses AI to analyze the information input by the information input unit and select an appropriate tax return format. The analysis is performed using, for example, natural language processing or machine learning, but is not limited to these examples. For example, the analysis unit uses natural language processing technology to analyze the input information and select an appropriate tax return format. The analysis unit can also use a machine learning algorithm to analyze the input information and select an appropriate tax return format. The document generation unit generates tax return documents using AI based on the format selected by the analysis unit. Document generation is performed, for example, based on a template, but is not limited to this example. For example, the document generation unit selects a template based on the analysis results and generates tax return documents. The document generation unit can also generate tax return documents using a data-driven generation algorithm. The confirmation and correction unit provides an interface that allows a user to confirm the generated tax return documents and correct them as necessary. The confirmation and correction is performed, for example, through a user interface, but is not limited to this example. For example, the confirmation and correction unit displays the generated tax return documents and allows the user to correct them. The confirmation and correction unit can also save the corrections and finalize the final tax return documents. The submission unit electronically submits the finalized tax return documents to the tax office. The submission is performed, for example, using encryption technology or an authentication system, but is not limited to this example. For example, the submission unit encrypts the tax return documents and submits them electronically. The submission unit can also submit tax return documents using two-factor authentication or biometric authentication.As a result, the tax return preparation system according to the embodiment automates the entire process of inputting information such as income, expenses, and deductions, analyzing it, generating tax return documents, checking and correcting them, and submitting them, thereby significantly reducing the effort required to prepare tax return documents and also reducing the cost of hiring a tax accountant.

[0030] The information input unit can input information on a pay slip, expense receipt, and deduction certificate. The information input unit, for example, inputs information on a pay slip. The pay slip includes information such as a breakdown of salary and payment date. For example, the information input unit provides an interface through which a user can input information on a pay slip. The information input unit can also input information on an expense receipt. The expense receipt includes information such as the issuer of the receipt, the date of issue, and the amount. For example, the information input unit provides an interface through which a user can input information on an expense receipt. The information input unit can also input information on a deduction certificate. The deduction certificate includes information such as the issuer of the certificate, the date of issue, and the amount of deduction. For example, the information input unit provides an interface through which a user can input information on a deduction certificate. In this way, by inputting information such as a pay slip, expense receipt, and deduction certificate, it is possible to comprehensively collect information necessary for preparing tax return documents.

[0031] The analysis unit can analyze the input information using natural language processing or machine learning. The analysis unit analyzes the input information using, for example, natural language processing technology. Natural language processing includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit uses morphological analysis to divide the input text into words and perform analysis. The analysis unit can also use grammatical analysis to analyze the grammatical structure of the input text. The analysis unit can also use semantic analysis to analyze the meaning of the input text. For example, the analysis unit uses semantic analysis to understand the meaning of the input information and select an appropriate tax return format. The analysis unit can also analyze the input information using a machine learning algorithm. Machine learning includes classification algorithms, regression algorithms, etc. For example, the analysis unit uses a classification algorithm to classify the input information into categories and perform analysis. The analysis unit can also use a regression algorithm to analyze the relationships between the input information. In this way, by using natural language processing or machine learning, the input information can be analyzed with high accuracy and an appropriate tax return format can be selected.

[0032] The document generation unit can automatically generate tax return documents based on the analysis results. The document generation unit automatically generates tax return documents based on, for example, the analysis results. Automatic generation includes template-based generation and data-driven generation. For example, the document generation unit selects an appropriate template based on the analysis results and generates tax return documents. The document generation unit can also generate tax return documents using a data-driven generation algorithm. For example, the document generation unit uses a data-driven generation algorithm to generate tax return documents based on input information. In this way, by automatically generating tax return documents based on the analysis results, tax return documents can be prepared quickly and accurately.

[0033] The checking and correcting unit may provide an interface that allows a user to review the generated tax return and correct it as necessary. The checking and correcting unit may provide an interface that allows a user to review the generated tax return and correct it as necessary. The interface may include the design and operation of the user interface. For example, the checking and correcting unit may display the generated tax return and allow the user to correct it. The checking and correcting unit may also save the corrections and finalize the final tax return. This allows a user to review the generated tax return and correct it as necessary, thereby improving the accuracy of the tax return.

[0034] The submission unit can electronically submit the finalized tax return to the tax office using encryption technology and an authentication system. The submission unit electronically submits the finalized tax return to the tax office using, for example, encryption technology and an authentication system. Encryption technologies include AES, RSA, and the like. For example, the submission unit encrypts the tax return using AES and submits it electronically. The submission unit can also encrypt the tax return using RSA and submit it electronically. Authentication systems include two-factor authentication, biometric authentication, and the like. For example, the submission unit submits the tax return using two-factor authentication. The submission unit can also submit the tax return using biometric authentication. In this way, by using encryption technology and an authentication system, the security and reliability of the tax return can be ensured while the tax return can be submitted electronically.

[0035] The information input unit can analyze the user's past input history and select the optimal input method. The information input unit, for example, analyzes the user's past input history and selects the optimal input method. The past input history includes the type of data input and the date and time of input. For example, the information input unit preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The information input unit can also automatically complete information that the user has input in the past. For example, the information input unit analyzes the user's past input patterns and suggests the optimal input order. In this way, by analyzing the user's past input history, the optimal input method can be selected and the efficiency of information input can be improved.

[0036] The information input unit can filter information based on the user's current living situation and areas of interest when inputting information. For example, the information input unit filters information based on the user's current living situation and areas of interest when inputting information. Living situations include family structure, income status, and the like. For example, if the user is a freelancer, the information input unit can prioritize displaying expense items. Furthermore, if the user has a family, the information input unit can also prioritize displaying deduction items related to the family. Areas of interest include hobbies, occupations, and the like. For example, if the user is engaged in a specific industry, the information input unit prioritizes displaying expense items related to that industry. This allows for more appropriate information input by filtering information based on the user's living situation and areas of interest.

[0037] The information input unit can select the optimal input means depending on the user's input method when inputting information. For example, the information input unit selects the optimal input means depending on the user's input method (voice, text, image, etc.) when inputting information. Input methods include voice input, text input, image input, etc. For example, if the user desires voice input, the information input unit inputs information using voice recognition technology. Also, if the user desires text input, the information input unit can prioritize keyboard input. Also, if the user desires image input, the information input unit can extract information using image recognition technology. In this way, by selecting the optimal input means depending on the user's input method, the efficiency of information input can be improved.

[0038] The information input unit can prioritize input of highly relevant information based on the user's geographical location information when inputting information. For example, the information input unit prioritizes input of highly relevant information based on the user's geographical location information when inputting information. Geographical location information includes GPS data, address information, and the like. For example, if the user lives in a specific area, the information input unit can prioritize displaying deduction items related to that area. Furthermore, if the user works in a specific area, the information input unit can prioritize displaying expense items related to that area. Furthermore, if the user does business in a specific area, the information input unit can prioritize displaying tax incentives related to that area. This allows for more appropriate information input by prioritized input of highly relevant information based on the user's geographical location information.

[0039] The information input unit can analyze the user's social media activity and input related information when inputting information. For example, the information input unit analyzes the user's social media activity and inputs related information when inputting information. Social media activity includes the content of posts and the number of likes. For example, the information input unit automatically inputs expense information shared by the user on social media. The information input unit can also analyze the content of the user's social media posts and suggest related deduction items. The information input unit can also suggest related expense items by referring to the activity of the user's friends on social media. In this way, related information can be efficiently input by analyzing the user's social media activity.

[0040] The information input unit can customize the input method by reflecting the user's past feedback when inputting information. For example, the information input unit customizes the input method by reflecting the user's past feedback when inputting information. Past feedback includes the user's ratings, comments, and the like. For example, if the user has preferred voice input in the past, the information input unit can preferentially suggest voice input. Furthermore, if the user has preferred text input in the past, the information input unit can preferentially suggest text input. Furthermore, if the user has preferred image input in the past, the information input unit can preferentially suggest image input. In this way, the input method can be customized by reflecting the user's past feedback, thereby improving the efficiency of information input.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the information during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the information during analysis. The importance of the information includes the impact and urgency of the information. For example, the analysis unit performs a detailed analysis of important information. The analysis unit can also perform a simplified analysis of less important information. The analysis unit can also determine the priority of the analysis according to the importance of the information. In this way, by adjusting the level of detail of the analysis based on the importance of the information, efficient analysis can be achieved.

[0042] The analysis unit can apply different analysis algorithms depending on the category of information during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of information during analysis. Information categories include financial information, personal information, etc. For example, the analysis unit applies an income analysis algorithm to income information. The analysis unit can also apply an expense analysis algorithm to expense information. The analysis unit can also apply a deduction analysis algorithm to deduction information. Analysis algorithms include classification algorithms and regression algorithms. For example, the analysis unit applies a classification algorithm to income information to perform analysis. The analysis unit can also apply a regression algorithm to expense information to perform analysis. In this way, by applying different analysis algorithms depending on the category of information, more accurate analysis can be achieved.

[0043] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit improves the accuracy of the analysis by referring to the user's past analysis results during analysis. Past analysis results include analysis result data and analysis result evaluations. For example, the analysis unit adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also determine the priority of the analysis based on the user's past analysis results. The analysis unit can also adjust the level of detail of the analysis based on the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0044] The analysis unit can determine the priority of analysis based on the time of submission of information during analysis. For example, the analysis unit determines the priority of analysis based on the time of submission of information during analysis. The time of submission of information includes the submission deadline and the timing of submission. For example, the analysis unit prioritizes analysis of information whose submission deadline is approaching. The analysis unit can also postpone analysis of information whose submission deadline is far away. The analysis unit can also adjust the level of detail of the analysis depending on the time of submission. In this way, efficient analysis can be achieved by determining the priority of analysis based on the time of submission of information.

[0045] The analysis unit can adjust the order of analysis based on the relevance of information during analysis. For example, the analysis unit adjusts the order of analysis based on the relevance of information during analysis. The relevance of information includes related topics and related data. For example, the analysis unit prioritizes analysis of highly related information. The analysis unit can also postpone analysis of less related information. The analysis unit can also adjust the level of detail of the analysis depending on the relevance of the information. In this way, efficient analysis can be achieved by adjusting the order of analysis based on the relevance of information.

[0046] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. Expertise levels include beginner, intermediate, advanced, etc. For example, the analysis unit uses a lot of technical terms when the user has expert knowledge. The analysis unit can also avoid technical terms when the user does not have expert knowledge. The analysis unit can also adjust the way the analysis results are expressed according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand.

[0047] The document generation unit can adjust the level of detail of the document based on the importance of the analysis results when generating the document. For example, the document generation unit adjusts the level of detail of the document based on the importance of the analysis results when generating the document. The importance of the analysis results includes impact and urgency. For example, the document generation unit generates a detailed document for important analysis results. The document generation unit can also generate a simplified document for less important analysis results. The document generation unit can also determine the priority of the document according to the importance of the analysis results. In this way, by adjusting the level of detail of the document based on the importance of the analysis results, efficient document generation can be achieved.

[0048] The document generation unit can apply different document generation algorithms depending on the category of information when generating a document. For example, the document generation unit applies different document generation algorithms depending on the category of information when generating a document. Categories of information include financial information, personal information, etc. For example, the document generation unit applies an income document generation algorithm to income information. The document generation unit can also apply an expense document generation algorithm to expense information. The document generation unit can also apply a deduction document generation algorithm to deduction information. Document generation algorithms include template-based generation and data-driven generation. For example, the document generation unit applies a template-based generation algorithm to income information to generate a document. The document generation unit can also apply a data-driven generation algorithm to expense information to generate a document. In this way, by applying different document generation algorithms depending on the category of information, more accurate document generation can be achieved.

[0049] The document generation unit can improve the accuracy of document generation by referring to the user's past document generation results when generating a document. For example, the document generation unit improves the accuracy of document generation by referring to the user's past document generation results when generating a document. The past document generation results include the type of document generated and the date and time of generation. For example, the document generation unit adjusts the document generation algorithm based on the user's past document generation results. The document generation unit can also determine the priority of documents based on the user's past document generation results. The document generation unit can also adjust the level of detail of documents based on the user's past document generation results. In this way, the accuracy of document generation can be improved by referring to the user's past document generation results.

[0050] The document generation unit can determine the priority of document generation based on the time of information submission when generating documents. For example, the document generation unit determines the priority of document generation based on the time of information submission when generating documents. The time of information submission includes the deadline for submission and the timing of submission. For example, the document generation unit prioritizes document generation for information whose submission deadline is approaching. The document generation unit can also postpone document generation for information whose submission deadline is far away. The document generation unit can also adjust the level of detail of the document depending on the time of submission. In this way, efficient document generation can be achieved by determining the priority of document generation based on the time of information submission.

[0051] The document generation unit can adjust the order of document generation based on the relevance of information when generating documents. For example, the document generation unit adjusts the order of document generation based on the relevance of information when generating documents. The relevance of information includes related topics and related data. For example, the document generation unit generates documents with priority for highly related information. The document generation unit can also postpone the generation of documents for less related information. The document generation unit can also adjust the level of detail of the document according to the relevance of information. In this way, by adjusting the order of document generation based on the relevance of information, efficient document generation can be achieved.

[0052] The document generation unit can adjust the use of technical terms in document generation according to the user's level of expertise when generating a document. For example, the document generation unit adjusts the use of technical terms in document generation according to the user's level of expertise when generating a document. Expertise levels include beginner, intermediate, advanced, etc. For example, the document generation unit uses a lot of technical terms when the user has expert knowledge. The document generation unit can also avoid technical terms when the user does not have expert knowledge. The document generation unit can also adjust the way the document is expressed according to the user's level of expertise. In this way, by adjusting the use of technical terms in document generation according to the user's level of expertise, it is possible to generate a document that is easy for the user to understand.

[0053] The checking and correcting unit can adjust the level of detail of the checking and correcting based on the importance of the generated document during checking and correcting. For example, the checking and correcting unit adjusts the level of detail of the checking and correcting based on the importance of the generated document during checking and correcting. The importance of the generated document includes impact and urgency, etc. For example, the checking and correcting unit performs detailed checking and correcting for important documents. The checking and correcting unit can also perform simplified checking and correcting for less important documents. The checking and correcting unit can also determine the priority of checking and correcting based on the importance of the document. In this way, efficient checking and correcting can be achieved by adjusting the level of detail of the checking and correcting based on the importance of the generated document.

[0054] The verification and correction unit can apply different verification and correction algorithms depending on the document category during verification and correction. For example, the verification and correction unit applies different verification and correction algorithms depending on the document category during verification and correction. Document categories include financial documents and personal documents. For example, the verification and correction unit applies an income verification and correction algorithm to income documents. The verification and correction unit can also apply an expense verification and correction algorithm to expense documents. The verification and correction unit can also apply a deduction verification and correction algorithm to deduction documents. Verification and correction algorithms include template-based correction and data-driven correction. For example, the verification and correction unit applies a template-based correction algorithm to income documents to verify and correct them. The verification and correction unit can also apply a data-driven correction algorithm to expense documents to verify and correct them. In this way, by applying different verification and correction algorithms depending on the document category, more accurate verification and correction can be achieved.

[0055] The checking and correcting unit can improve the accuracy of checking and correcting by referring to the user's past checking and correcting results when checking and correcting. For example, the checking and correcting unit can improve the accuracy of checking and correcting by referring to the user's past checking and correcting results when checking and correcting. Past checking and correcting results include the items that were corrected and the date and time of correction. For example, the checking and correcting unit can adjust the checking and correcting algorithm based on the user's past checking and correcting results. The checking and correcting unit can also determine the priority of checking and correcting based on the user's past checking and correcting results. The checking and correcting unit can also adjust the level of detail of checking and correcting based on the user's past checking and correcting results. In this way, the accuracy of checking and correcting can be improved by referring to the user's past checking and correcting results.

[0056] The confirmation and correction department can determine the priority of confirmation and correction based on the time of document submission when confirming and correcting. For example, the confirmation and correction department determines the priority of confirmation and correction based on the time of document submission when confirming and correcting. The time of document submission includes the deadline and timing of submission. For example, the confirmation and correction department prioritizes confirmation and correction for documents with an approaching deadline. The confirmation and correction department can also postpone confirmation and correction for documents with a distant deadline. The confirmation and correction department can also adjust the level of detail of confirmation and correction depending on the time of submission. In this way, efficient confirmation and correction can be achieved by determining the priority of confirmation and correction based on the time of document submission.

[0057] The checking and correcting unit can adjust the order of checking and correcting based on the relevance of documents during checking and correcting. For example, the checking and correcting unit adjusts the order of checking and correcting based on the relevance of documents during checking and correcting. Document relevance includes related topics and related data. For example, the checking and correcting unit can prioritize checking and correcting highly relevant documents. The checking and correcting unit can also postpone checking and correcting less relevant documents. The checking and correcting unit can also adjust the level of detail of checking and correcting based on the relevance of documents. In this way, efficient checking and correcting can be achieved by adjusting the order of checking and correcting based on the relevance of documents.

[0058] The checking and correcting unit can adjust the use of technical terms for checking and correcting depending on the user's level of expertise during checking and correcting. For example, the checking and correcting unit adjusts the use of technical terms for checking and correcting depending on the user's level of expertise during checking and correcting. Expertise levels include beginner, intermediate, and advanced. For example, the checking and correcting unit uses a lot of technical terms when the user has specialized knowledge. The checking and correcting unit can also avoid technical terms when the user does not have specialized knowledge. The checking and correcting unit can also adjust the way the checking and correcting is expressed depending on the user's level of expertise. In this way, by adjusting the use of technical terms for checking and correcting depending on the user's level of expertise, checking and correcting can be provided in a way that is easy for the user to understand.

[0059] The submission unit can adjust the level of detail of submission based on the importance of the document at the time of submission. For example, the submission unit adjusts the level of detail of submission based on the importance of the document at the time of submission. The importance of a document includes impact and urgency, etc. For example, the submission unit performs detailed submission procedures for important documents. The submission unit can also perform simplified submission procedures for less important documents. The submission unit can also determine the priority of submission according to the importance of the document. In this way, efficient submission can be achieved by adjusting the level of detail of submission based on the importance of the document.

[0060] The submission unit can apply different submission algorithms depending on the document category at the time of submission. For example, the submission unit applies different submission algorithms depending on the document category at the time of submission. Document categories include financial documents, personal documents, etc. For example, the submission unit applies an income submission algorithm to income documents. The submission unit can also apply an expense submission algorithm to expense documents. The submission unit can also apply a deduction submission algorithm to deduction documents. Submission algorithms include template-based submission and data-driven submission. For example, the submission unit applies a template-based submission algorithm to income documents and submits them. The submission unit can also apply a data-driven submission algorithm to expense documents and submit them. In this way, by applying different submission algorithms depending on the document category, more accurate submission can be achieved.

[0061] The submission unit can improve the accuracy of submission by referring to the user's past submission results at the time of submission. For example, the submission unit improves the accuracy of submission by referring to the user's past submission results at the time of submission. The past submission results include the type of document submitted and the submission date and time. For example, the submission unit adjusts the submission algorithm based on the user's past submission results. The submission unit can also determine the priority of submission based on the user's past submission results. The submission unit can also adjust the level of detail of submission based on the user's past submission results. In this way, the accuracy of submission can be improved by referring to the user's past submission results.

[0062] The submission unit can determine the priority of submission based on the submission time of the document at the time of submission. For example, the submission unit determines the priority of submission based on the submission time of the document at the time of submission. The submission time of the document includes the submission deadline and the timing of submission. For example, the submission unit prioritizes the submission of documents with an approaching deadline. The submission unit can also postpone the submission of documents with a distant deadline. The submission unit can also adjust the level of detail of submission depending on the submission time. In this way, efficient submission can be achieved by determining the priority of submission based on the submission time of the document.

[0063] The submission unit can adjust the order of submission based on the relevance of documents at the time of submission. For example, the submission unit adjusts the order of submission based on the relevance of documents at the time of submission. The relevance of documents includes related topics, related data, and the like. For example, the submission unit prioritizes the submission of highly related documents. Furthermore, the submission unit can also postpone the submission of less related documents. Furthermore, the submission unit can adjust the level of detail of submission according to the relevance of documents. In this way, efficient submission can be achieved by adjusting the order of submission based on the relevance of documents.

[0064] The submission unit can adjust the use of technical terminology in the submission according to the user's level of expertise at the time of submission. For example, the submission unit adjusts the use of technical terminology in the submission according to the user's level of expertise at the time of submission. Expertise levels include beginner, intermediate, advanced, etc. For example, the submission unit uses a lot of technical terminology if the user has expert knowledge. The submission unit can also avoid technical terminology if the user does not have expert knowledge. The submission unit can also adjust the way the submission is expressed according to the user's level of expertise. In this way, by adjusting the use of technical terminology in the submission according to the user's level of expertise, it is possible to provide a submission procedure that is easy for the user to understand.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The analysis unit can learn input data trends based on the user's past input data and predict future input data. For example, if a user inputs the same expense items every year, the analysis unit can automatically suggest those items. Also, if a user tends to input specific income items at specific times, the analysis unit can automatically display income items at those times. Furthermore, the analysis unit can analyze patterns in data entered by the user in the past and display alerts to prevent input errors. This makes it possible to improve the efficiency and accuracy of input by utilizing the user's past input data.

[0067] The verification and correction module can suggest corrections based on the user's past correction history. For example, if a user has frequently corrected a particular item in the past, it will automatically highlight that item and suggest corrections. It can also learn the corrections the user has made in the past and automatically apply similar corrections. It can also analyze patterns of items corrected by the user in the past and predict the need for corrections. This makes it possible to improve the efficiency and accuracy of corrections by utilizing the user's past correction history.

[0068] The information input unit can automatically suggest region-specific tax incentives and deduction items based on the user's geographic location information. For example, if the user lives in a specific region, deduction items related to that region can be displayed preferentially. Also, if the user does business in a specific region, tax incentives related to that region can be automatically suggested. Furthermore, if the user works in a specific region, expense items related to that region can be displayed preferentially. In this way, more appropriate information input can be achieved by utilizing the user's geographic location information.

[0069] The document generation unit can optimize the document generation process based on the user's past document generation history. For example, it can prioritize and suggest templates that the user has frequently used in the past. It can also analyze patterns of documents the user has generated in the past and automatically generate similar documents. It can also learn the document generation procedures the user has performed in the past and provide an efficient generation process. In this way, the efficiency and accuracy of document generation can be improved by utilizing the user's past document generation history.

[0070] The submission unit can optimize the submission process based on the user's past submission history. For example, it can suggest the timing of submission based on the type of documents the user has submitted in the past and the submission date and time. It can also learn the submission procedures the user has performed in the past and automatically apply similar procedures. Furthermore, it can analyze patterns of documents the user has submitted in the past and predict the need for submission. In this way, the efficiency and accuracy of the submission process can be improved by utilizing the user's past submission history.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The information input unit inputs information such as income, expenses, and deductions. Income includes salary income, business income, investment income, etc., while expenses include business expenses, medical expenses, and education expenses. Deductions include basic deductions, spouse deductions, and dependent deductions. The information input unit provides an interface for the user to input this information. Step 2: The analysis unit analyzes the information entered by the information input unit and selects the appropriate tax return format. The analysis is performed using AI, which can use natural language processing and machine learning algorithms. Step 3: The document generator generates the tax return documents based on the format selected by the analyzer. The document generator uses template-based and data-driven generation algorithms. Step 4: The confirmation and correction section provides an interface for the user to check the generated tax return and make corrections as necessary. The corrections are saved and the final tax return is confirmed. Step 5: The filing department electronically submits the finalized tax return to the tax office. Submission is done using encryption technology and authentication systems.

[0073] (Example 2) A tax return preparation system according to an embodiment of the present invention allows users to input information such as income, expenses, and deductions, analyze it using AI, generate tax return documents, and then review and revise them before electronically submitting them to the tax office. The tax return preparation system allows users to input necessary information, analyze the input information using AI, and automatically generate appropriate tax return documents. The generated documents are then provided to the user for review and revision. For example, the tax return preparation system may provide an interface through which users input information such as income, expenses, and deductions. The tax return preparation system then analyzes the input information using AI and selects the appropriate tax return format. The AI ​​then automatically generates tax return documents based on the analysis results. The tax return preparation system may then provide an interface through which users can review the generated tax return documents and revise them as necessary. The tax return preparation system then has the function of electronically submitting the finalized tax return documents to the tax office. This significantly reduces the effort required to prepare tax return documents and also reduces the cost of hiring a tax accountant. This will make the tax return preparation system easier to use, reducing the burden on users. Furthermore, the use of AI will improve the accuracy of tax return documents.

[0074] The tax return preparation system according to the embodiment includes an information input unit, an analysis unit, a document generation unit, a confirmation / correction unit, and a submission unit. The information input unit inputs information such as income, expenses, and deductions. Income includes, but is not limited to, salary income, business income, and investment income. Expenses include, but are not limited to, business expenses, medical expenses, and education expenses. Deductions include, but are not limited to, basic deductions, spousal deductions, and dependent deductions. The information input unit provides, for example, an interface through which a user inputs information such as income, expenses, and deductions. The analysis unit uses AI to analyze the information input by the information input unit and select an appropriate tax return format. The analysis is performed using, for example, natural language processing or machine learning, but is not limited to these examples. For example, the analysis unit uses natural language processing technology to analyze the input information and select an appropriate tax return format. The analysis unit can also use a machine learning algorithm to analyze the input information and select an appropriate tax return format. The document generation unit generates tax return documents using AI based on the format selected by the analysis unit. Document generation is performed, for example, based on a template, but is not limited to this example. For example, the document generation unit selects a template based on the analysis results and generates tax return documents. The document generation unit can also generate tax return documents using a data-driven generation algorithm. The confirmation and correction unit provides an interface that allows a user to confirm the generated tax return documents and correct them as necessary. The confirmation and correction is performed, for example, through a user interface, but is not limited to this example. For example, the confirmation and correction unit displays the generated tax return documents and allows the user to correct them. The confirmation and correction unit can also save the corrections and finalize the final tax return documents. The submission unit electronically submits the finalized tax return documents to the tax office. The submission is performed, for example, using encryption technology or an authentication system, but is not limited to this example. For example, the submission unit encrypts the tax return documents and submits them electronically. The submission unit can also submit tax return documents using two-factor authentication or biometric authentication.As a result, the tax return preparation system according to the embodiment automates the entire process of inputting information such as income, expenses, and deductions, analyzing it, generating tax return documents, checking and correcting them, and submitting them, thereby significantly reducing the effort required to prepare tax return documents and also reducing the cost of hiring a tax accountant.

[0075] The information input unit can input information on a pay slip, expense receipt, and deduction certificate. The information input unit, for example, inputs information on a pay slip. The pay slip includes information such as a breakdown of salary and payment date. For example, the information input unit provides an interface through which a user can input information on a pay slip. The information input unit can also input information on an expense receipt. The expense receipt includes information such as the issuer of the receipt, the date of issue, and the amount. For example, the information input unit provides an interface through which a user can input information on an expense receipt. The information input unit can also input information on a deduction certificate. The deduction certificate includes information such as the issuer of the certificate, the date of issue, and the amount of deduction. For example, the information input unit provides an interface through which a user can input information on a deduction certificate. In this way, by inputting information such as a pay slip, expense receipt, and deduction certificate, it is possible to comprehensively collect information necessary for preparing tax return documents.

[0076] The analysis unit can analyze the input information using natural language processing or machine learning. The analysis unit analyzes the input information using, for example, natural language processing technology. Natural language processing includes morphological analysis, grammatical analysis, semantic analysis, etc. For example, the analysis unit uses morphological analysis to divide the input text into words and perform analysis. The analysis unit can also use grammatical analysis to analyze the grammatical structure of the input text. The analysis unit can also use semantic analysis to analyze the meaning of the input text. For example, the analysis unit uses semantic analysis to understand the meaning of the input information and select an appropriate tax return format. The analysis unit can also analyze the input information using a machine learning algorithm. Machine learning includes classification algorithms, regression algorithms, etc. For example, the analysis unit uses a classification algorithm to classify the input information into categories and perform analysis. The analysis unit can also use a regression algorithm to analyze the relationships between the input information. In this way, by using natural language processing or machine learning, the input information can be analyzed with high accuracy and an appropriate tax return format can be selected.

[0077] The document generation unit can automatically generate tax return documents based on the analysis results. The document generation unit automatically generates tax return documents based on, for example, the analysis results. Automatic generation includes template-based generation and data-driven generation. For example, the document generation unit selects an appropriate template based on the analysis results and generates tax return documents. The document generation unit can also generate tax return documents using a data-driven generation algorithm. For example, the document generation unit uses a data-driven generation algorithm to generate tax return documents based on input information. In this way, by automatically generating tax return documents based on the analysis results, tax return documents can be prepared quickly and accurately.

[0078] The checking and correcting unit may provide an interface that allows a user to review the generated tax return and correct it as necessary. The checking and correcting unit may provide an interface that allows a user to review the generated tax return and correct it as necessary. The interface may include the design and operation of the user interface. For example, the checking and correcting unit may display the generated tax return and allow the user to correct it. The checking and correcting unit may also save the corrections and finalize the final tax return. This allows a user to review the generated tax return and correct it as necessary, thereby improving the accuracy of the tax return.

[0079] The submission unit can electronically submit the finalized tax return to the tax office using encryption technology and an authentication system. The submission unit electronically submits the finalized tax return to the tax office using, for example, encryption technology and an authentication system. Encryption technologies include AES, RSA, and the like. For example, the submission unit encrypts the tax return using AES and submits it electronically. The submission unit can also encrypt the tax return using RSA and submit it electronically. Authentication systems include two-factor authentication, biometric authentication, and the like. For example, the submission unit submits the tax return using two-factor authentication. The submission unit can also submit the tax return using biometric authentication. In this way, by using encryption technology and an authentication system, the security and reliability of the tax return can be ensured while the tax return can be submitted electronically.

[0080] The information input unit can estimate the user's emotions and adjust the timing of information input based on the estimated user emotions. The information input unit, for example, estimates the user's emotions and adjusts the timing of information input based on the estimated user emotions. Emotion estimation includes facial expression recognition and voice analysis. For example, the information input unit can use facial expression recognition technology to analyze the user's facial expressions and estimate emotions. The information input unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate emotions. Adjustment of the timing of information input includes the frequency and timing of input. For example, if the user is feeling stressed, the information input unit can temporarily suspend input to provide time for relaxation. If the user is concentrating, the information input unit can encourage the user to input information continuously. If the user is tired, the information input unit can suggest dividing the input into parts. This adjusts the timing of information input according to the user's emotions, reducing the user's burden and enabling efficient information input. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0081] The information input unit can analyze the user's past input history and select the optimal input method. The information input unit, for example, analyzes the user's past input history and selects the optimal input method. The past input history includes the type of data input and the date and time of input. For example, the information input unit preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The information input unit can also automatically complete information that the user has input in the past. For example, the information input unit analyzes the user's past input patterns and suggests the optimal input order. In this way, by analyzing the user's past input history, the optimal input method can be selected and the efficiency of information input can be improved.

[0082] The information input unit can filter information based on the user's current living situation and areas of interest when inputting information. For example, the information input unit filters information based on the user's current living situation and areas of interest when inputting information. Living situations include family structure, income status, and the like. For example, if the user is a freelancer, the information input unit can prioritize displaying expense items. Furthermore, if the user has a family, the information input unit can also prioritize displaying deduction items related to the family. Areas of interest include hobbies, occupations, and the like. For example, if the user is engaged in a specific industry, the information input unit prioritizes displaying expense items related to that industry. This allows for more appropriate information input by filtering information based on the user's living situation and areas of interest.

[0083] The information input unit can select the optimal input means depending on the user's input method when inputting information. For example, the information input unit selects the optimal input means depending on the user's input method (voice, text, image, etc.) when inputting information. Input methods include voice input, text input, image input, etc. For example, if the user desires voice input, the information input unit inputs information using voice recognition technology. Also, if the user desires text input, the information input unit can prioritize keyboard input. Also, if the user desires image input, the information input unit can extract information using image recognition technology. In this way, by selecting the optimal input means depending on the user's input method, the efficiency of information input can be improved.

[0084] The information input unit can estimate the user's emotions and determine the priority of information to be input based on the estimated user emotions. The information input unit, for example, estimates the user's emotions and determines the priority of information to be input based on the estimated user emotions. Emotion estimation includes facial expression recognition and voice analysis. For example, the information input unit can use facial expression recognition technology to analyze the user's facial expressions and estimate emotions. The information input unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate emotions. Information priority determination also includes the importance and urgency of the information. For example, if the user is stressed, the information input unit can start inputting simple information first. If the user is relaxed, the information input unit can start inputting complex information first. If the user is in a hurry, the information input unit can start inputting important information first. This allows efficient information input by determining the priority of information to be input based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0085] The information input unit can prioritize input of highly relevant information based on the user's geographical location information when inputting information. For example, the information input unit prioritizes input of highly relevant information based on the user's geographical location information when inputting information. Geographical location information includes GPS data, address information, and the like. For example, if the user lives in a specific area, the information input unit can prioritize displaying deduction items related to that area. Furthermore, if the user works in a specific area, the information input unit can prioritize displaying expense items related to that area. Furthermore, if the user does business in a specific area, the information input unit can prioritize displaying tax incentives related to that area. This allows for more appropriate information input by prioritized input of highly relevant information based on the user's geographical location information.

[0086] The information input unit can analyze the user's social media activity and input related information when inputting information. For example, the information input unit analyzes the user's social media activity and inputs related information when inputting information. Social media activity includes the content of posts and the number of likes. For example, the information input unit automatically inputs expense information shared by the user on social media. The information input unit can also analyze the content of the user's social media posts and suggest related deduction items. The information input unit can also suggest related expense items by referring to the activity of the user's friends on social media. In this way, related information can be efficiently input by analyzing the user's social media activity.

[0087] The information input unit can customize the input method by reflecting the user's past feedback when inputting information. For example, the information input unit customizes the input method by reflecting the user's past feedback when inputting information. Past feedback includes the user's ratings, comments, and the like. For example, if the user has preferred voice input in the past, the information input unit can preferentially suggest voice input. Furthermore, if the user has preferred text input in the past, the information input unit can preferentially suggest text input. Furthermore, if the user has preferred image input in the past, the information input unit can preferentially suggest image input. In this way, the input method can be customized by reflecting the user's past feedback, thereby improving the efficiency of information input.

[0088] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and adjusts the presentation method of the analysis based on the estimated user emotions. Emotion estimation includes facial expression recognition and voice analysis. For example, the analysis unit can use facial expression recognition technology to analyze the user's facial expressions and estimate emotions. The analysis unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate emotions. The presentation method of the analysis can be adjusted using graphs or text. For example, if the user is nervous, the analysis unit can provide simple, highly visible analysis results. If the user is relaxed, the analysis unit can provide detailed analysis results. If the user is in a hurry, the analysis unit can provide analysis results that are concise. By adjusting the presentation method of the analysis according to the user's emotions, it is possible to provide analysis results that are easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0089] The analysis unit can adjust the level of detail of the analysis based on the importance of the information during analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the information during analysis. The importance of the information includes the impact and urgency of the information. For example, the analysis unit performs a detailed analysis of important information. The analysis unit can also perform a simplified analysis of less important information. The analysis unit can also determine the priority of the analysis according to the importance of the information. In this way, by adjusting the level of detail of the analysis based on the importance of the information, efficient analysis can be achieved.

[0090] The analysis unit can apply different analysis algorithms depending on the category of information during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of information during analysis. Information categories include financial information, personal information, etc. For example, the analysis unit applies an income analysis algorithm to income information. The analysis unit can also apply an expense analysis algorithm to expense information. The analysis unit can also apply a deduction analysis algorithm to deduction information. Analysis algorithms include classification algorithms and regression algorithms. For example, the analysis unit applies a classification algorithm to income information to perform analysis. The analysis unit can also apply a regression algorithm to expense information to perform analysis. In this way, by applying different analysis algorithms depending on the category of information, more accurate analysis can be achieved.

[0091] The analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results during analysis. For example, the analysis unit improves the accuracy of the analysis by referring to the user's past analysis results during analysis. Past analysis results include analysis result data and analysis result evaluations. For example, the analysis unit adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also determine the priority of the analysis based on the user's past analysis results. The analysis unit can also adjust the level of detail of the analysis based on the user's past analysis results. In this way, the accuracy of the analysis can be improved by referring to the user's past analysis results.

[0092] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. Emotion estimation includes facial expression recognition and voice analysis. For example, the analysis unit can use facial expression recognition technology to analyze the user's facial expressions and estimate emotions. The analysis unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate emotions. Adjustment of the length of the analysis can include detailed analysis or simplified analysis. For example, the analysis unit can provide a short, concise analysis result if the user is in a hurry. The analysis unit can also provide a detailed analysis result if the user is relaxed. The analysis unit can also provide a visually stimulating analysis result if the user is excited. By adjusting the length of the analysis according to the user's emotions, it is possible to provide the optimal analysis result for the user. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0093] The analysis unit can determine the priority of analysis based on the time of submission of information during analysis. For example, the analysis unit determines the priority of analysis based on the time of submission of information during analysis. The time of submission of information includes the submission deadline and the timing of submission. For example, the analysis unit prioritizes analysis of information whose submission deadline is approaching. The analysis unit can also postpone analysis of information whose submission deadline is far away. The analysis unit can also adjust the level of detail of the analysis depending on the time of submission. In this way, efficient analysis can be achieved by determining the priority of analysis based on the time of submission of information.

[0094] The analysis unit can adjust the order of analysis based on the relevance of information during analysis. For example, the analysis unit adjusts the order of analysis based on the relevance of information during analysis. The relevance of information includes related topics and related data. For example, the analysis unit prioritizes analysis of highly related information. The analysis unit can also postpone analysis of less related information. The analysis unit can also adjust the level of detail of the analysis depending on the relevance of the information. In this way, efficient analysis can be achieved by adjusting the order of analysis based on the relevance of information.

[0095] The analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise during analysis. For example, the analysis unit adjusts the use of technical terms in the analysis according to the user's level of expertise during analysis. Expertise levels include beginner, intermediate, advanced, etc. For example, the analysis unit uses a lot of technical terms when the user has expert knowledge. The analysis unit can also avoid technical terms when the user does not have expert knowledge. The analysis unit can also adjust the way the analysis results are expressed according to the user's level of expertise. In this way, by adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easy for the user to understand.

[0096] The document generation unit can estimate the user's emotion and adjust the document generation method based on the estimated user emotion. For example, the document generation unit estimates the user's emotion and adjusts the document generation method based on the estimated user emotion. Emotion estimation includes facial expression recognition and voice analysis. For example, the document generation unit can use facial expression recognition technology to analyze the user's facial expression and estimate the emotion. The document generation unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate the emotion. Adjustment of the document generation method includes template selection and generation procedures. For example, if the user is nervous, the document generation unit can generate a simple, highly readable document. If the user is relaxed, the document generation unit can generate a document that includes detailed information. If the user is in a hurry, the document generation unit can generate a document that focuses on the main points. By adjusting the document generation method according to the user's emotion, it is possible to generate an optimal document for the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0097] The document generation unit can adjust the level of detail of the document based on the importance of the analysis results when generating the document. For example, the document generation unit adjusts the level of detail of the document based on the importance of the analysis results when generating the document. The importance of the analysis results includes impact and urgency. For example, the document generation unit generates a detailed document for important analysis results. The document generation unit can also generate a simplified document for less important analysis results. The document generation unit can also determine the priority of the document according to the importance of the analysis results. In this way, by adjusting the level of detail of the document based on the importance of the analysis results, efficient document generation can be achieved.

[0098] The document generation unit can apply different document generation algorithms depending on the category of information when generating a document. For example, the document generation unit applies different document generation algorithms depending on the category of information when generating a document. Categories of information include financial information, personal information, etc. For example, the document generation unit applies an income document generation algorithm to income information. The document generation unit can also apply an expense document generation algorithm to expense information. The document generation unit can also apply a deduction document generation algorithm to deduction information. Document generation algorithms include template-based generation and data-driven generation. For example, the document generation unit applies a template-based generation algorithm to income information to generate a document. The document generation unit can also apply a data-driven generation algorithm to expense information to generate a document. In this way, by applying different document generation algorithms depending on the category of information, more accurate document generation can be achieved.

[0099] The document generation unit can improve the accuracy of document generation by referring to the user's past document generation results when generating a document. For example, the document generation unit improves the accuracy of document generation by referring to the user's past document generation results when generating a document. The past document generation results include the type of document generated and the date and time of generation. For example, the document generation unit adjusts the document generation algorithm based on the user's past document generation results. The document generation unit can also determine the priority of documents based on the user's past document generation results. The document generation unit can also adjust the level of detail of documents based on the user's past document generation results. In this way, the accuracy of document generation can be improved by referring to the user's past document generation results.

[0100] The document generation unit can estimate the user's emotion and adjust the length of the document generation based on the estimated user emotion. For example, the document generation unit estimates the user's emotion and adjusts the length of the document generation based on the estimated user emotion. Emotion estimation includes facial expression recognition and voice analysis. For example, the document generation unit uses facial expression recognition technology to analyze the user's facial expression and estimate the emotion. The document generation unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate the emotion. Adjustment of the length of the document generation includes detailed documents and concise documents. For example, the document generation unit can generate a short, to-the-point document when the user is in a hurry. The document generation unit can also generate a longer document with detailed information when the user is relaxed. The document generation unit can also generate a visually stimulating document when the user is excited. By adjusting the length of the document generation based on the user's emotion, the document generation unit can generate an optimal document for the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0101] The document generation unit can determine the priority of document generation based on the time of information submission when generating documents. For example, the document generation unit determines the priority of document generation based on the time of information submission when generating documents. The time of information submission includes the deadline for submission and the timing of submission. For example, the document generation unit prioritizes document generation for information whose submission deadline is approaching. The document generation unit can also postpone document generation for information whose submission deadline is far away. The document generation unit can also adjust the level of detail of the document depending on the time of submission. In this way, efficient document generation can be achieved by determining the priority of document generation based on the time of information submission.

[0102] The document generation unit can adjust the order of document generation based on the relevance of information when generating documents. For example, the document generation unit adjusts the order of document generation based on the relevance of information when generating documents. The relevance of information includes related topics and related data. For example, the document generation unit generates documents with priority for highly related information. The document generation unit can also postpone the generation of documents for less related information. The document generation unit can also adjust the level of detail of the document according to the relevance of information. In this way, by adjusting the order of document generation based on the relevance of information, efficient document generation can be achieved.

[0103] The document generation unit can adjust the use of technical terms in document generation according to the user's level of expertise when generating a document. For example, the document generation unit adjusts the use of technical terms in document generation according to the user's level of expertise when generating a document. Expertise levels include beginner, intermediate, advanced, etc. For example, the document generation unit uses a lot of technical terms when the user has expert knowledge. The document generation unit can also avoid technical terms when the user does not have expert knowledge. The document generation unit can also adjust the way the document is expressed according to the user's level of expertise. In this way, by adjusting the use of technical terms in document generation according to the user's level of expertise, it is possible to generate a document that is easy for the user to understand.

[0104] The confirmation and correction unit can estimate the user's emotions and adjust the confirmation and correction method based on the estimated user emotions. For example, the confirmation and correction unit estimates the user's emotions and adjusts the confirmation and correction method based on the estimated user emotions. Emotion estimation includes facial expression recognition and voice analysis. For example, the confirmation and correction unit can use facial expression recognition technology to analyze the user's facial expressions and estimate emotions. The confirmation and correction unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate emotions. Adjustment of the confirmation and correction method includes interface design and operation method. For example, if the user is nervous, the confirmation and correction unit can provide a simple, highly visible confirmation and correction interface. If the user is relaxed, the confirmation and correction unit can provide a confirmation and correction interface that includes detailed information. If the user is in a hurry, the confirmation and correction unit can provide a confirmation and correction interface that focuses on the main points. This allows the confirmation and correction method to be adjusted according to the user's emotions, thereby providing an optimal confirmation and correction interface for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The checking and correcting unit can adjust the level of detail of the checking and correcting based on the importance of the generated document during checking and correcting. For example, the checking and correcting unit adjusts the level of detail of the checking and correcting based on the importance of the generated document during checking and correcting. The importance of the generated document includes impact and urgency, etc. For example, the checking and correcting unit performs detailed checking and correcting for important documents. The checking and correcting unit can also perform simplified checking and correcting for less important documents. The checking and correcting unit can also determine the priority of checking and correcting based on the importance of the document. In this way, efficient checking and correcting can be achieved by adjusting the level of detail of the checking and correcting based on the importance of the generated document.

[0106] The verification and correction unit can apply different verification and correction algorithms depending on the document category during verification and correction. For example, the verification and correction unit applies different verification and correction algorithms depending on the document category during verification and correction. Document categories include financial documents and personal documents. For example, the verification and correction unit applies an income verification and correction algorithm to income documents. The verification and correction unit can also apply an expense verification and correction algorithm to expense documents. The verification and correction unit can also apply a deduction verification and correction algorithm to deduction documents. Verification and correction algorithms include template-based correction and data-driven correction. For example, the verification and correction unit applies a template-based correction algorithm to income documents to verify and correct them. The verification and correction unit can also apply a data-driven correction algorithm to expense documents to verify and correct them. In this way, by applying different verification and correction algorithms depending on the document category, more accurate verification and correction can be achieved.

[0107] The checking and correcting unit can improve the accuracy of checking and correcting by referring to the user's past checking and correcting results when checking and correcting. For example, the checking and correcting unit can improve the accuracy of checking and correcting by referring to the user's past checking and correcting results when checking and correcting. Past checking and correcting results include the items that were corrected and the date and time of correction. For example, the checking and correcting unit can adjust the checking and correcting algorithm based on the user's past checking and correcting results. The checking and correcting unit can also determine the priority of checking and correcting based on the user's past checking and correcting results. The checking and correcting unit can also adjust the level of detail of checking and correcting based on the user's past checking and correcting results. In this way, the accuracy of checking and correcting can be improved by referring to the user's past checking and correcting results.

[0108] The confirmation and correction unit can estimate the user's emotion and adjust the length of the confirmation and correction based on the estimated user emotion. The confirmation and correction unit, for example, estimates the user's emotion and adjusts the length of the confirmation and correction based on the estimated user emotion. Emotion estimation includes facial expression recognition and voice analysis. For example, the confirmation and correction unit can use facial expression recognition technology to analyze the user's facial expression and estimate the emotion. The confirmation and correction unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate the emotion. Adjustment of the length of the confirmation and correction can include detailed confirmation or brief confirmation. For example, if the user is in a hurry, the confirmation and correction unit can provide a short and to-the-point confirmation and correction. If the user is relaxed, the confirmation and correction unit can provide a detailed confirmation and correction. If the user is excited, the confirmation and correction unit can provide a visually stimulating confirmation and correction. In this way, by adjusting the length of the confirmation and correction according to the user's emotion, the confirmation and correction can be optimal for the user. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0109] The confirmation and correction department can determine the priority of confirmation and correction based on the time of document submission when confirming and correcting. For example, the confirmation and correction department determines the priority of confirmation and correction based on the time of document submission when confirming and correcting. The time of document submission includes the deadline and timing of submission. For example, the confirmation and correction department prioritizes confirmation and correction for documents with an approaching deadline. The confirmation and correction department can also postpone confirmation and correction for documents with a distant deadline. The confirmation and correction department can also adjust the level of detail of confirmation and correction depending on the time of submission. In this way, efficient confirmation and correction can be achieved by determining the priority of confirmation and correction based on the time of document submission.

[0110] The checking and correcting unit can adjust the order of checking and correcting based on the relevance of documents during checking and correcting. For example, the checking and correcting unit adjusts the order of checking and correcting based on the relevance of documents during checking and correcting. Document relevance includes related topics and related data. For example, the checking and correcting unit can prioritize checking and correcting highly relevant documents. The checking and correcting unit can also postpone checking and correcting less relevant documents. The checking and correcting unit can also adjust the level of detail of checking and correcting based on the relevance of documents. In this way, efficient checking and correcting can be achieved by adjusting the order of checking and correcting based on the relevance of documents.

[0111] The checking and correcting unit can adjust the use of technical terms for checking and correcting depending on the user's level of expertise during checking and correcting. For example, the checking and correcting unit adjusts the use of technical terms for checking and correcting depending on the user's level of expertise during checking and correcting. Expertise levels include beginner, intermediate, and advanced. For example, the checking and correcting unit uses a lot of technical terms when the user has specialized knowledge. The checking and correcting unit can also avoid technical terms when the user does not have specialized knowledge. The checking and correcting unit can also adjust the way the checking and correcting is expressed depending on the user's level of expertise. In this way, by adjusting the use of technical terms for checking and correcting depending on the user's level of expertise, checking and correcting can be provided in a way that is easy for the user to understand.

[0112] The submission unit can estimate the user's emotions and adjust the submission method based on the estimated user emotions. For example, the submission unit can estimate the user's emotions and adjust the submission method based on the estimated user emotions. Emotion estimation includes facial expression recognition and voice analysis. For example, the submission unit can use facial expression recognition technology to analyze the user's facial expressions and estimate the emotions. The submission unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate the emotions. The adjustment of the submission method includes interface design and operation method. For example, if the user is nervous, the submission unit can provide a simple, highly visible submission interface. If the user is relaxed, the submission unit can provide a submission interface that includes detailed information. If the user is in a hurry, the submission unit can provide a submission interface that focuses on the main points. By adjusting the submission method according to the user's emotions, it is possible to provide an optimal submission interface for the user. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0113] The submission unit can adjust the level of detail of submission based on the importance of the document at the time of submission. For example, the submission unit adjusts the level of detail of submission based on the importance of the document at the time of submission. The importance of a document includes impact and urgency, etc. For example, the submission unit performs detailed submission procedures for important documents. The submission unit can also perform simplified submission procedures for less important documents. The submission unit can also determine the priority of submission according to the importance of the document. In this way, efficient submission can be achieved by adjusting the level of detail of submission based on the importance of the document.

[0114] The submission unit can apply different submission algorithms depending on the document category at the time of submission. For example, the submission unit applies different submission algorithms depending on the document category at the time of submission. Document categories include financial documents, personal documents, etc. For example, the submission unit applies an income submission algorithm to income documents. The submission unit can also apply an expense submission algorithm to expense documents. The submission unit can also apply a deduction submission algorithm to deduction documents. Submission algorithms include template-based submission and data-driven submission. For example, the submission unit applies a template-based submission algorithm to income documents and submits them. The submission unit can also apply a data-driven submission algorithm to expense documents and submit them. In this way, by applying different submission algorithms depending on the document category, more accurate submission can be achieved.

[0115] The submission unit can improve the accuracy of submission by referring to the user's past submission results at the time of submission. For example, the submission unit improves the accuracy of submission by referring to the user's past submission results at the time of submission. The past submission results include the type of document submitted and the submission date and time. For example, the submission unit adjusts the submission algorithm based on the user's past submission results. The submission unit can also determine the priority of submission based on the user's past submission results. The submission unit can also adjust the level of detail of submission based on the user's past submission results. In this way, the accuracy of submission can be improved by referring to the user's past submission results.

[0116] The submission unit can estimate the user's emotion and adjust the length of the submission based on the estimated user emotion. For example, the submission unit can estimate the user's emotion and adjust the length of the submission based on the estimated user emotion. Emotion estimation can include facial expression recognition and voice analysis. For example, the submission unit can use facial expression recognition technology to analyze the user's facial expression and estimate the emotion. The submission unit can also use voice analysis technology to analyze the tone and speed of the user's voice and estimate the emotion. Adjustment of the length of the submission can include detailed submission or simple submission. For example, if the user is in a hurry, the submission unit can provide a short, concise submission procedure. If the user is relaxed, the submission unit can provide a longer submission procedure with detailed information. If the user is excited, the submission unit can provide a visually stimulating submission procedure. By adjusting the length of the submission according to the user's emotion, the optimal submission procedure can be provided for the user. Emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0117] The submission unit can determine the priority of submission based on the submission time of the document at the time of submission. For example, the submission unit determines the priority of submission based on the submission time of the document at the time of submission. The submission time of the document includes the submission deadline and the timing of submission. For example, the submission unit prioritizes the submission of documents with an approaching deadline. The submission unit can also postpone the submission of documents with a distant deadline. The submission unit can also adjust the level of detail of submission depending on the submission time. In this way, efficient submission can be achieved by determining the priority of submission based on the submission time of the document.

[0118] The submission unit can adjust the order of submission based on the relevance of documents at the time of submission. For example, the submission unit adjusts the order of submission based on the relevance of documents at the time of submission. The relevance of documents includes related topics, related data, and the like. For example, the submission unit prioritizes the submission of highly related documents. Furthermore, the submission unit can also postpone the submission of less related documents. Furthermore, the submission unit can adjust the level of detail of submission according to the relevance of documents. In this way, efficient submission can be achieved by adjusting the order of submission based on the relevance of documents.

[0119] The submission unit can adjust the use of technical terminology in the submission according to the user's level of expertise at the time of submission. For example, the submission unit adjusts the use of technical terminology in the submission according to the user's level of expertise at the time of submission. Expertise levels include beginner, intermediate, advanced, etc. For example, the submission unit uses a lot of technical terminology if the user has expert knowledge. The submission unit can also avoid technical terminology if the user does not have expert knowledge. The submission unit can also adjust the way the submission is expressed according to the user's level of expertise. In this way, by adjusting the use of technical terminology in the submission according to the user's level of expertise, it is possible to provide a submission procedure that is easy for the user to understand. === Hard Collateral 1-1 === Each of the multiple elements, including the information input unit, analysis unit, document generation unit, confirmation / correction unit, and submission unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the information input unit provides an interface for inputting information such as income, expenses, and deductions using the reception device 38 of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using AI and selects an appropriate tax return format. The document generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically generates tax return documents using AI based on the analysis results. The confirmation / correction unit provides an interface for displaying the generated tax return documents using, for example, the output device 40 of the smart device 14 and allowing the user to correct them. The submission unit electronically submits the finalized tax return documents to the tax office using, for example, the communication I / F 26 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the information input unit, analysis unit, document generation unit, confirmation / correction unit, and submission unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the information input unit provides an interface for inputting information such as income, expenses, and deductions using the microphone 238 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using AI and selects an appropriate tax return format. The document generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically generates tax return documents using AI based on the analysis results. The confirmation / correction unit provides an interface for audio notification of the generated tax return documents using, for example, the speaker 240 of the smart glasses 214, allowing the user to make corrections. The submission unit electronically submits the finalized tax return documents to the tax office using, for example, the communication I / F 26 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the information input unit, analysis unit, document generation unit, confirmation / correction unit, and submission unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the information input unit provides an interface for inputting information such as income, expenses, and deductions using the microphone 238 of the headset terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using AI and selects an appropriate tax return format. The document generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically generates tax return documents using AI based on the analysis results. The confirmation / correction unit displays the generated tax return documents using, for example, the display 343 of the headset terminal 314, and provides an interface that allows the user to make corrections. The submission unit electronically submits the finalized tax return documents to the tax office using, for example, the communication I / F 26 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the information input unit, analysis unit, document generation unit, confirmation / correction unit, and submission unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the information input unit provides an interface for inputting information such as income, expenses, and deductions using the microphone 238 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the input information using AI and selects an appropriate tax return format. The document generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and automatically generates tax return documents using AI based on the analysis results. The confirmation / correction unit provides an interface for audio notification of the generated tax return documents using, for example, the speaker 240 of the robot 414, allowing the user to make corrections. The submission unit electronically submits the finalized tax return documents to the tax office using, for example, the communication I / F 26 of the data processing device 12.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The information input unit can estimate the user's emotions and dynamically change the design of the input interface based on the estimated emotions. For example, if the user is feeling stressed, a simple and intuitive interface can be provided. Alternatively, if the user is relaxed, an interface containing detailed information can be provided. Furthermore, if the user is concentrating, more input fields can be displayed at once to encourage efficient input. In this way, by providing an interface that corresponds to the user's emotions, it is possible to improve the efficiency of information input and the user experience.

[0122] The analysis unit can learn input data trends based on the user's past input data and predict future input data. For example, if a user inputs the same expense items every year, the analysis unit can automatically suggest those items. Also, if a user tends to input specific income items at specific times, the analysis unit can automatically display income items at those times. Furthermore, the analysis unit can analyze patterns in data entered by the user in the past and display alerts to prevent input errors. This makes it possible to improve the efficiency and accuracy of input by utilizing the user's past input data.

[0123] The document generation unit can estimate the user's emotions and adjust the document layout based on the estimated emotions. For example, if the user is nervous, a simple, highly visible layout can be provided. If the user is relaxed, a layout including detailed information can be provided. Furthermore, if the user is in a hurry, a concise layout that focuses on the main points can be provided. In this way, by providing a document layout that corresponds to the user's emotions, it is possible to improve the efficiency of document understanding and use.

[0124] The verification and correction module can suggest corrections based on the user's past correction history. For example, if a user has frequently corrected a particular item in the past, it will automatically highlight that item and suggest corrections. It can also learn the corrections the user has made in the past and automatically apply similar corrections. It can also analyze patterns of items corrected by the user in the past and predict the need for corrections. This makes it possible to improve the efficiency and accuracy of corrections by utilizing the user's past correction history.

[0125] The submission unit can estimate the user's emotions and adjust the submission process based on the estimated emotions. For example, if the user is nervous, the submission process can be simplified so that it can be completed with the minimum number of steps. Alternatively, if the user is relaxed, detailed confirmation steps can be added so that the user can double-check all information before submission. Furthermore, if the user is in a hurry, a shortcut can be provided to speed up the submission process. In this way, by providing a submission process that corresponds to the user's emotions, it is possible to improve submission efficiency and the user experience.

[0126] The information input unit can automatically suggest region-specific tax incentives and deduction items based on the user's geographic location information. For example, if the user lives in a specific region, deduction items related to that region can be displayed preferentially. Also, if the user does business in a specific region, tax incentives related to that region can be automatically suggested. Furthermore, if the user works in a specific region, expense items related to that region can be displayed preferentially. In this way, more appropriate information input can be achieved by utilizing the user's geographic location information.

[0127] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is nervous, it can provide simple, highly visible graphs and charts. If the user is relaxed, it can provide a report including detailed analysis results. Furthermore, if the user is in a hurry, it can provide concise analysis results that focus on the main points. In this way, by providing a display method of the analysis results according to the user's emotions, it is possible to improve the understanding and use efficiency of the analysis results.

[0128] The document generation unit can optimize the document generation process based on the user's past document generation history. For example, it can prioritize and suggest templates that the user has frequently used in the past. It can also analyze patterns of documents the user has generated in the past and automatically generate similar documents. It can also learn the document generation procedures the user has performed in the past and provide an efficient generation process. In this way, the efficiency and accuracy of document generation can be improved by utilizing the user's past document generation history.

[0129] The confirmation and correction unit can estimate the user's emotions and determine the priority of corrections based on the estimated emotions. For example, if the user is feeling stressed, important correction items can be displayed first, allowing them to be corrected quickly. If the user is relaxed, detailed correction items can be displayed, allowing the user to carefully check all items. Furthermore, if the user is in a hurry, correction items that focus on the main points can be displayed, allowing them to be corrected efficiently. This makes it possible to improve the efficiency and accuracy of corrections by providing correction priorities according to the user's emotions.

[0130] The submission unit can optimize the submission process based on the user's past submission history. For example, it can suggest the timing of submission based on the type of documents the user has submitted in the past and the submission date and time. It can also learn the submission procedures the user has performed in the past and automatically apply similar procedures. Furthermore, it can analyze patterns of documents the user has submitted in the past and predict the need for submission. In this way, the efficiency and accuracy of the submission process can be improved by utilizing the user's past submission history.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The information input unit inputs information such as income, expenses, and deductions. Income includes salary income, business income, investment income, etc., while expenses include business expenses, medical expenses, and education expenses. Deductions include basic deductions, spouse deductions, and dependent deductions. The information input unit provides an interface for the user to input this information. Step 2: The analysis unit analyzes the information entered by the information input unit and selects the appropriate tax return format. The analysis is performed using AI, which can use natural language processing and machine learning algorithms. Step 3: The document generator generates the tax return documents based on the format selected by the analyzer. The document generator uses template-based and data-driven generation algorithms. Step 4: The confirmation and correction section provides an interface for the user to check the generated tax return and make corrections as necessary. The corrections are saved and the final tax return is confirmed. Step 5: The filing department electronically submits the finalized tax return to the tax office. Submission is done using encryption technology and authentication systems.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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).

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] [Explanation of symbols]

[0205] 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 information input section for inputting information on income, expenses, and deductions; an analysis unit that analyzes the information input by the information input unit and selects a format of the declaration document; a document generation unit that generates a declaration document based on the format selected by the analysis unit; a confirmation and correction unit in which a user confirms and corrects the tax return documents generated by the document generation unit; a submission unit that electronically submits the tax return documents finalized by the confirmation / correction unit to a tax office. A system characterized by:

2. The information input unit Enter information from your pay slip, expense receipts, and deduction certificates 2. The system of claim 1.

3. The analysis unit Analyze input information using natural language processing or machine learning 2. The system of claim 1.

4. The document creation unit Automatically generate tax return documents based on analysis results 2. The system of claim 1.

5. The confirmation and correction unit Provide an interface for users to review the generated tax return and make corrections as necessary 2. The system of claim 1.

6. The submission unit Using encryption technology and authentication systems, finalized tax returns are submitted electronically to the tax office.

2. The system of claim 1.

7. The information input unit Estimates the user's emotions and adjusts the timing of information input based on the estimated user emotions.

2. The system of claim 1.

8. The information input unit Analyze the user's past input history and select the optimal input method 2. The system of claim 1.

Images