system

Abstract

The system according to this embodiment aims to streamline the process of creating and verifying documents. [Solution] The system according to the embodiment comprises a learning unit, a brush-up unit, and an output unit. The learning unit learns information related to document creation. The brush-up unit performs initial brush-up of the document based on the information learned by the learning unit. The output unit outputs the document that has been brushed up by the brush-up unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that a lot of time is required for document creation and confirmation, resulting in a decrease in work efficiency.

[0005] The system according to the embodiment aims to improve the process of document creation and confirmation.

Means for Solving the Problems

[0006] The system according to the embodiment includes a learning unit, a polishing unit, and an output unit. The learning unit learns information related to document creation. The polishing unit performs primary polishing of the document based on the information learned by the learning unit. The output unit outputs the document polished by the polishing unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline the process of creating and verifying documents. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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] [[ID=This 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The document creation support system according to an embodiment of the present invention is a system that provides a mechanism for entrusting the first step of document creation to AI. The document creation support system allows each user to create their own My AIagent and train it in advance, enabling initial document refinement among agents. The document creation support system can handle collaboration among multiple agents, and output is obtained once a consensus is reached. This mechanism can improve the work efficiency of company employees who are constantly busy with document creation and review. For example, the document creation support system allows each user to create their own My AIagent and train it in advance with previously created presentation materials or emails. This allows the AI ​​agent to understand each user's checkpoints regarding content and appearance when creating documents, as well as key points during creation. Next, the document creation support system allows agents to perform initial document refinement among themselves. For example, employee B's My AIagent reviews a document created by employee A's My AIagent and suggests revisions. By repeating this process, a document that has been agreed upon by multiple agents is output. This mechanism, by entrusting the first step of document creation to AI, reduces factors such as oversights on the creator's side and unique perspectives on the review side, thereby improving work efficiency. Furthermore, the document creation support system has the potential to be commercialized and is expected to contribute to the efficiency of back-office operations in companies. This means that the document creation support system can improve operational efficiency by entrusting the first step of document creation to AI.

[0029] The document creation support system according to this embodiment comprises a learning unit, a refinement unit, and an output unit. The learning unit learns information related to document creation. This information includes, but is not limited to, presentation materials, reports, and email documents. The learning unit learns, for example, presentation materials and email documents created in the past. By learning from past documents, the learning unit enables the AI ​​agent to understand the checkpoints for content and appearance when creating documents. The refinement unit performs initial refinement of the document based on the information learned by the learning unit. Initial refinement includes, for example, grammar checks, layout adjustments, and content review, but is not limited to these. The refinement unit performs initial refinement of the document among multiple agents. For example, the refinement unit has employee B's My AIagent review a document created by employee A's My AIagent and suggest revisions. The refinement unit can improve the accuracy of the document through review and revision suggestions among agents. The output unit outputs the document refined by the refinement unit. Outputs include, but are not limited to, PDF format, presentation format, and printed materials. The output unit outputs materials that have been agreed upon by multiple agents. The output unit can also produce outputs that take into account the potential for commercialization. As a result, the document creation support system according to this embodiment can improve work efficiency by entrusting the first step of document creation to AI.

[0030] The learning unit learns information related to document creation. This information includes, but is not limited to, presentation materials, reports, and emails. For example, the learning unit learns from previously created presentation materials and emails. Specifically, the learning unit uses natural language processing technology to extract patterns such as grammar, structure, and expression from past documents. This allows the AI ​​agent to understand the checkpoints for content and appearance when creating documents. Furthermore, the learning unit can learn document creation styles and formats appropriate for different industries and applications. For example, business presentations and academic papers require different content and expression methods, so it learns appropriate document creation methods for each. The learning unit can also incorporate user feedback to continuously update its learning content and respond to the latest trends and needs. This ensures that the learning unit always maintains the knowledge to support high-quality document creation and can respond flexibly to user requests. In addition, the learning unit can collaborate with other systems and databases to collect a wider range of information and improve the accuracy of its learning. For example, it can collect information from publicly available documents on the internet and internal company databases and use it as learning data. This allows the learning department to address a wider range of material creation needs and provide users with useful information.

[0031] The Refinement Unit performs initial refinement of materials based on information learned by the Learning Unit. This initial refinement includes, but is not limited to, grammar checks, layout adjustments, and content review. Specifically, the Refinement Unit uses natural language processing technology to automatically detect and correct grammatical errors and spelling mistakes. Layout adjustments optimize font size, line spacing, and paragraph placement, considering the visual balance and readability of the material. Content review verifies the logical consistency and accuracy of the information, making corrections and additions as needed. The Refinement Unit performs initial refinement of materials across multiple agents. For example, employee A's My AIagent creates a document, which employee B's My AIagent reviews and suggests revisions. This process allows for checks from different perspectives, improving the accuracy of the document. Furthermore, the Refinement Unit can continuously improve the accuracy and efficiency of the refinement process by incorporating user feedback. For example, by recording whether the user accepted the suggested revisions and learning the patterns of accepted revisions, the system can reflect these findings in future refinements. This allows the refinement department to respond flexibly to user needs and improve the quality of the materials. Furthermore, the refinement department can integrate with other systems and tools to achieve more advanced refinements. For instance, it can integrate with professional document proofreading and design tools to perform more accurate grammar checks and layout adjustments. This allows the refinement department to further improve the quality of materials and provide valuable support for creating materials for users.

[0032] The output unit outputs materials that have been refined by the refinement unit. Outputs include, but are not limited to, PDF format, presentation format, and printed materials. Specifically, the output unit outputs materials in the most suitable format according to the user's requirements. For example, in presentation format, the design and animation effects of the slides are optimized to create visually appealing materials. In PDF format, care is taken to ensure that fonts and layouts are not distorted, and in printed materials, the output is optimized considering paper quality and print quality. The output unit outputs materials that have been agreed upon by multiple agents. For example, only materials that have been reviewed by multiple agents and have all revisions reflected are approved as the final output. This process guarantees the quality of the materials. Furthermore, the output unit can also produce outputs that consider the possibility of commercialization. For example, if the materials are to be used as product catalogs or marketing materials, efforts are made to enhance their appeal and attractiveness as commercial products. In this way, the output unit can provide the optimal output according to the purpose and use of the materials and meet the needs of the user. Furthermore, the output unit can collect user feedback and continuously improve the accuracy and efficiency of the output. For example, users can provide evaluations and comments on the outputted materials, and the output process can be reviewed based on that feedback, which can then be reflected in future outputs. This allows the output unit to provide valuable document creation support to users and improve work efficiency.

[0033] The learning unit can learn from previously created presentation materials and emails. For example, the learning unit learns from previously created presentation materials and emails. By learning from past materials, the learning unit enables the AI ​​agent to understand the checkpoints for content and appearance when creating materials. Previously created presentation materials and emails include, but are not limited to, materials from a specific period or materials on a specific theme. This allows the AI ​​agent to understand the checkpoints for content and appearance when creating materials. Some or all of the above processing in the learning unit may be performed using AI, or not. For example, the learning unit can input previously created presentation materials and emails into a generation AI and have the generation AI learn the checkpoints for content and appearance when creating materials.

[0034] The refinement unit can perform initial refinement of a document among multiple agents. For example, the refinement unit can perform initial refinement of a document among multiple agents. The refinement unit can improve the accuracy of the document through confirmation and revision suggestions among agents. Refinement among multiple agents includes, but is not limited to, the division of roles and communication methods among agents. This allows for improvement in the quality of the document by performing initial refinement among multiple agents. Some or all of the above-described processes in the refinement unit may be performed using, for example, AI, or without AI. For example, the refinement unit can have a generation AI perform initial refinement of a document among multiple agents.

[0035] The output unit can output documents that have been agreed upon by multiple agents. For example, the output unit outputs documents that have been agreed upon by multiple agents. By outputting documents that have been agreed upon by multiple agents, the reliability of the documents can be improved. Documents that have been agreed upon by multiple agents include, but are not limited to, the consensus-building process among agents and evaluation criteria. This improves the reliability of the documents by outputting documents that have been agreed upon by multiple agents. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI execute the output of documents that have been agreed upon by multiple agents.

[0036] The Refinement Department allows employee B's My AIagent to review documents created by employee A's My AIagent and suggest revisions. For example, the Refinement Department can have employee B's My AIagent review documents created by employee A's My AIagent and suggest revisions. The Refinement Department can improve the accuracy of documents through review and revision suggestions between agents. Employee A's My AIagent includes, for example, the scope of responsibility for document creation and the algorithms used, but is not limited to such examples. Employee B's My AIagent includes, for example, the scope of responsibility for reviewing documents and suggesting revisions, and the algorithms used, but is not limited to such examples. This allows the accuracy of documents to be improved through review and revision suggestions between agents. Some or all of the above processes in the Refinement Department may be performed using AI, for example, or without AI. For example, the Refinement Department can have a generating AI perform the review and revision suggestion of documents created by employee A's My AIagent.

[0037] The output unit can produce output that takes into account the potential for commercialization. For example, the output unit can produce output that takes into account the potential for commercialization. By considering the potential for commercialization, the output unit can contribute to the efficiency of a company's back-office operations. The potential for commercialization includes, but is not limited to, market research results and competitor analysis. This allows for the efficient production of back-office operations by producing output that takes the potential for commercialization into account. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or without AI. For example, the output unit can have a generation AI produce output that takes the potential for commercialization into account.

[0038] The learning unit can optimize its learning algorithm by referring to past document creation history during the learning process. For example, the learning unit optimizes its learning algorithm by referring to past document creation history during the learning process. By referring to past document creation history, the learning unit improves the accuracy of its learning algorithm. Past document creation history includes, but is not limited to, past project data, creation date and time, and creator. For example, the learning unit analyzes successful and unsuccessful examples of documents created in the past and adjusts its learning algorithm. The learning unit can learn frequently used templates and formats from past document creation history. Based on past document creation history, the learning unit can build learning algorithms specialized for specific industries or fields. This improves the accuracy of the learning algorithm by referring to past document creation history. Some or all of the above processes in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can input past document creation history into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0039] The learning unit can apply different learning methods to each category of material during the learning process. For example, the learning unit can apply different learning methods to each category of material during the learning process. By applying different learning methods to each category of material, the learning unit can perform category-specific learning. Category of materials includes, but is not limited to, technical documents, sales documents, and marketing documents. For example, the learning unit can apply different learning methods to presentation materials and technical documents to perform learning tailored to their respective characteristics. The learning unit can apply different learning methods to email documents and reports to learn appropriate expressions and formats. The learning unit can apply different learning methods to marketing documents and financial documents to perform category-specific learning. This allows for category-specific learning by applying different learning methods to each category of material. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not. For example, the learning unit can have a generating AI perform the application of different learning methods to each category of material.

[0040] The learning unit can weight the learning data based on the submission date of the materials during the learning process. For example, the learning unit can weight the learning data based on the submission date of the materials during the learning process. By weighting the learning data based on the submission date of the materials, the learning unit can perform efficient learning. The submission date of the materials includes, but is not limited to, the submission deadline, submission frequency, and the importance of the submitter. For example, the learning unit can prioritize learning materials with approaching deadlines and respond quickly. For materials with later submission dates, the learning unit can perform detailed learning to aim for high-quality output. The learning unit can adjust the importance of the learning data according to the submission date to perform efficient learning. This enables efficient learning by weighting the learning data based on the submission date of the materials. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can have a generating AI perform the weighting of the learning data based on the submission date of the materials.

[0041] The learning unit can prioritize learning highly relevant materials by considering the user's geographical location during the learning process. For example, the learning unit prioritizes learning highly relevant materials by considering the user's geographical location during the learning process. The learning unit can prioritize learning highly relevant materials by considering the user's geographical location. Geographical location information includes, but is not limited to, the user's location, regional characteristics, and relevant market data. For example, if the user is in a specific region, the learning unit can prioritize learning materials related to that region. If the user is on a business trip, the learning unit can prioritize learning materials related to the destination of the business trip. Based on the user's geographical location, the learning unit can learn materials that include region-specific information. This allows the learning unit to prioritize learning highly relevant materials by considering the user's geographical location. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can have a generating AI perform the learning of highly relevant materials by considering the user's geographical location.

[0042] The refinement unit can adjust the level of detail of revisions based on the importance of the document during the refinement process. For example, the refinement unit can adjust the level of detail of revisions based on the importance of the document during the refinement process. By adjusting the level of detail of revisions based on the importance of the document, the refinement unit can efficiently refine the document. The importance of the document includes, but is not limited to, the purpose of the document, the target audience, and the recipient. For example, in the case of important presentation materials, the refinement unit can make detailed revision suggestions to aim for high-quality output. In the case of everyday email documents, the refinement unit can make concise revision suggestions to respond quickly. The refinement unit can efficiently refine the document by adjusting the level of detail of revisions according to the importance of the document. This allows for efficient refinement by adjusting the level of detail of revisions based on the importance of the document. Some or all of the above-described processes in the refinement unit may be performed using, for example, AI, or not. For example, the refinement unit can have a generating AI perform the adjustment of the level of detail of revisions based on the importance of the document.

[0043] The refinement department can apply different refinement algorithms depending on the category of the document during the refinement process. For example, the refinement department can apply different refinement algorithms depending on the category of the document during the refinement process. By applying refinement algorithms according to the category of the document, the refinement department can make revisions specific to each category. Document categories include, but are not limited to, technical documents, sales documents, and marketing documents. For example, the refinement department can apply different refinement algorithms to presentation materials and technical documents, making revisions according to the characteristics of each. The refinement department can apply different refinement algorithms to email documents and reports, suggesting appropriate expressions and formats. The refinement department can apply different refinement algorithms to marketing documents and financial documents, making revisions specific to each category. This allows for revisions specific to each category by applying refinement algorithms according to the category of the document. Some or all of the above processes in the refinement department may be performed using, for example, AI, or not using AI. For example, the refinement section can have the generating AI apply different refinement algorithms depending on the category of the document.

[0044] The refinement department can determine the priority of revisions based on the submission date of the materials during the refinement process. For example, the refinement department can determine the priority of revisions based on the submission date of the materials during the refinement process. By determining the priority of revisions based on the submission date of the materials, the refinement department can perform efficient refinement. The submission date of the materials includes, but is not limited to, the submission deadline, submission frequency, and the importance of the submitter. For example, the refinement department can prioritize the refinement of materials with approaching deadlines and respond quickly. For materials with later submission dates, the refinement department can perform detailed revisions to aim for high-quality output. The refinement department can adjust the priority of revisions according to the submission date, enabling efficient refinement. As a result, by determining the priority of revisions based on the submission date of the materials, efficient refinement becomes possible. Some or all of the above processes in the refinement department may be performed using, for example, AI, or not using AI. For example, the refinement department can have a generating AI perform the determination of revision priorities based on the submission date of the materials.

[0045] The refinement unit can improve the accuracy of revisions by referring to relevant literature in the document during the refinement process. For example, the refinement unit can improve the accuracy of revisions by referring to relevant literature in the document during the refinement process. The refinement unit improves the accuracy of revisions by referring to relevant literature in the document. Relevant literature includes, but is not limited to, selection criteria, reference methods, and citation methods. For example, the refinement unit can refer to relevant literature in the document and make revision suggestions based on accurate information. The refinement unit can make revision suggestions that complement the content of the document based on data obtained from relevant literature. The refinement unit can analyze relevant literature in the document and propose the optimal revision method. This improves the accuracy of revisions by referring to relevant literature in the document. Some or all of the above processes in the refinement unit may be performed using, for example, AI, or not using AI. For example, the refinement unit can have a generating AI perform the improvement of revision accuracy by referring to relevant literature in the document.

[0046] The output unit can adjust the level of detail of the output based on the importance of the document during output. For example, the output unit adjusts the level of detail of the output based on the importance of the document during output. By adjusting the level of detail of the output according to the importance of the document, the output unit enables efficient output. The importance of the document includes, but is not limited to, the purpose of the document, the target audience, and the recipient. For example, in the case of important presentation materials, the output unit can provide output containing detailed information. In the case of everyday emails, the output unit can provide concise and quick output. The output unit can adjust the level of detail of the output according to the importance of the document, enabling efficient output. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the adjustment of the level of detail of the output based on the importance of the document.

[0047] The output unit can apply different output methods depending on the category of the document during output. For example, the output unit can apply different output methods depending on the category of the document during output. By applying output methods according to the category of the document, the output unit can produce output specialized for each category. Document categories include, but are not limited to, technical documents, sales documents, and marketing documents. For example, the output unit can apply different output methods to presentation materials and technical documents to produce output appropriate to their respective characteristics. The output unit can apply different output methods to emails and reports to provide appropriate expression and formatting. The output unit can apply different output methods to marketing documents and financial documents to produce output specialized for each category. This makes it possible to produce output specialized for each category by applying output methods according to the category of the document. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the application of different output methods depending on the category of the document.

[0048] The output unit can adjust the order of outputs based on the submission dates of the materials during the output process. For example, the output unit can adjust the order of outputs based on the submission dates of the materials during the output process. By adjusting the order of outputs based on the submission dates of the materials, the output unit can achieve efficient output. The submission dates of the materials include, but are not limited to, the submission deadline, submission frequency, and the importance of the submitter. For example, the output unit can prioritize outputting materials with approaching deadlines and respond quickly. For materials with later submission dates, the output unit can provide detailed output, aiming for high-quality output. The output unit can adjust the order of outputs according to the submission dates, enabling efficient output. As a result, by adjusting the order of outputs based on the submission dates of the materials, efficient output becomes possible. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the adjustment of the output order based on the submission dates of the materials.

[0049] The output unit can improve the accuracy of the output by referring to relevant market data for the document during the output process. For example, the output unit can improve the accuracy of the output by referring to relevant market data for the document during the output process. The output unit improves the accuracy of the output by referring to relevant market data for the document. Relevant market data includes, but is not limited to, market data selection criteria, reference methods, and data analysis methods. For example, the output unit can refer to relevant market data for the document and produce output based on accurate information. The output unit can produce output that complements the content of the document based on data obtained from relevant market data. The output unit can analyze relevant market data for the document and propose the optimal output method. This improves the accuracy of the output by referring to relevant market data for the document. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the improvement of output accuracy by referring to relevant market data for the document.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] Document creation support systems can analyze a user's past document creation history and automatically suggest frequently used templates and formats. For example, they can refer to past project data and prioritize suggesting templates for successful documents. Furthermore, they can provide templates tailored to specific industries or fields. This allows users to create documents efficiently and improve their work productivity.

[0052] The document creation support system can prioritize the creation of highly relevant documents by considering the user's geographical location. For example, if the user is in a specific region, it can create documents containing market data and trend information related to that region. If the user is on a business trip, it can create documents containing information related to their destination. It can also provide documents that take into account the unique culture and business practices of the region. This allows users to create more effective documents.

[0053] The document creation support system can apply different output methods depending on the category of the document. For example, it can provide output containing detailed technical information for technical documents, and output in a visually appealing presentation format for sales materials. It can also provide output containing market data and trend information for marketing materials. Furthermore, it can suggest the optimal format and design for each category. This enables effective output tailored to each category.

[0054] The document creation support system can weight training data based on the submission deadline of the documents. For example, it can prioritize training on documents with approaching deadlines to ensure a quick response. For documents with later deadlines, it can conduct detailed training to aim for high-quality output. It can also adjust the weighting of training data according to submission frequency and the importance of the submitter. This enables efficient training and improves the accuracy of document creation.

[0055] The document creation support system can improve the accuracy of revisions by referring to related literature. For example, it can refer to related literature and make revision suggestions based on accurate information. It can also make revision suggestions that complement the content of the document based on data obtained from related literature. Furthermore, it can analyze related literature and suggest the optimal revision method. As a result, by referring to related literature, the accuracy of revisions is improved, and high-quality documents can be created.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The learning unit learns information related to document creation. This information includes presentation materials, reports, and email documents. The learning unit learns from previously created presentation materials and email documents, and the AI ​​agent understands the checkpoints for content and appearance when creating documents. Step 2: The Refinement Unit performs a preliminary refinement of the document based on the information learned by the Learning Unit. This preliminary refinement includes grammar checks, layout adjustments, and content review. The Refinement Unit performs the preliminary refinement of the document with multiple agents. For example, employee A's My AIagent creates a document, employee B's My AIagent reviews it, and suggests revisions. This improves the accuracy of the document. Step 3: The Output Unit outputs the materials that have been refined by the Refinement Unit. Outputs may include PDF format, presentation format, printed materials, etc. The Output Unit can also output materials that have been agreed upon by multiple agents and may consider the possibility of commercialization.

[0058] (Example of form 2) The document creation support system according to an embodiment of the present invention is a system that provides a mechanism for entrusting the first step of document creation to AI. The document creation support system allows each user to create their own My AIagent and train it in advance, enabling initial document refinement among agents. The document creation support system can handle collaboration among multiple agents, and output is obtained once a consensus is reached. This mechanism can improve the work efficiency of company employees who are constantly busy with document creation and review. For example, the document creation support system allows each user to create their own My AIagent and train it in advance with previously created presentation materials or emails. This allows the AI ​​agent to understand each user's checkpoints regarding content and appearance when creating documents, as well as key points during creation. Next, the document creation support system allows agents to perform initial document refinement among themselves. For example, employee B's My AIagent reviews a document created by employee A's My AIagent and suggests revisions. By repeating this process, a document that has been agreed upon by multiple agents is output. This mechanism, by entrusting the first step of document creation to AI, reduces factors such as oversights on the creator's side and unique perspectives on the review side, thereby improving work efficiency. Furthermore, the document creation support system has the potential to be commercialized and is expected to contribute to the efficiency of back-office operations in companies. This means that the document creation support system can improve operational efficiency by entrusting the first step of document creation to AI.

[0059] The document creation support system according to this embodiment comprises a learning unit, a refinement unit, and an output unit. The learning unit learns information related to document creation. This information includes, but is not limited to, presentation materials, reports, and email documents. The learning unit learns, for example, presentation materials and email documents created in the past. By learning from past documents, the learning unit enables the AI ​​agent to understand the checkpoints for content and appearance when creating documents. The refinement unit performs initial refinement of the document based on the information learned by the learning unit. Initial refinement includes, for example, grammar checks, layout adjustments, and content review, but is not limited to these. The refinement unit performs initial refinement of the document among multiple agents. For example, the refinement unit has employee B's My AIagent review a document created by employee A's My AIagent and suggest revisions. The refinement unit can improve the accuracy of the document through review and revision suggestions among agents. The output unit outputs the document refined by the refinement unit. Outputs include, but are not limited to, PDF format, presentation format, and printed materials. The output unit outputs materials that have been agreed upon by multiple agents. The output unit can also produce outputs that take into account the potential for commercialization. As a result, the document creation support system according to this embodiment can improve work efficiency by entrusting the first step of document creation to AI.

[0060] The learning unit learns information related to document creation. This information includes, but is not limited to, presentation materials, reports, and emails. For example, the learning unit learns from previously created presentation materials and emails. Specifically, the learning unit uses natural language processing technology to extract patterns such as grammar, structure, and expression from past documents. This allows the AI ​​agent to understand the checkpoints for content and appearance when creating documents. Furthermore, the learning unit can learn document creation styles and formats appropriate for different industries and applications. For example, business presentations and academic papers require different content and expression methods, so it learns appropriate document creation methods for each. The learning unit can also incorporate user feedback to continuously update its learning content and respond to the latest trends and needs. This ensures that the learning unit always maintains the knowledge to support high-quality document creation and can respond flexibly to user requests. In addition, the learning unit can collaborate with other systems and databases to collect a wider range of information and improve the accuracy of its learning. For example, it can collect information from publicly available documents on the internet and internal company databases and use it as learning data. This allows the learning department to address a wider range of material creation needs and provide users with useful information.

[0061] The Refinement Unit performs initial refinement of materials based on information learned by the Learning Unit. This initial refinement includes, but is not limited to, grammar checks, layout adjustments, and content review. Specifically, the Refinement Unit uses natural language processing technology to automatically detect and correct grammatical errors and spelling mistakes. Layout adjustments optimize font size, line spacing, and paragraph placement, considering the visual balance and readability of the material. Content review verifies the logical consistency and accuracy of the information, making corrections and additions as needed. The Refinement Unit performs initial refinement of materials across multiple agents. For example, employee A's My AIagent creates a document, which employee B's My AIagent reviews and suggests revisions. This process allows for checks from different perspectives, improving the accuracy of the document. Furthermore, the Refinement Unit can continuously improve the accuracy and efficiency of the refinement process by incorporating user feedback. For example, by recording whether the user accepted the suggested revisions and learning the patterns of accepted revisions, the system can reflect these findings in future refinements. This allows the refinement department to respond flexibly to user needs and improve the quality of the materials. Furthermore, the refinement department can integrate with other systems and tools to achieve more advanced refinements. For instance, it can integrate with professional document proofreading and design tools to perform more accurate grammar checks and layout adjustments. This allows the refinement department to further improve the quality of materials and provide valuable support for creating materials for users.

[0062] The output unit outputs materials that have been refined by the refinement unit. Outputs include, but are not limited to, PDF format, presentation format, and printed materials. Specifically, the output unit outputs materials in the most suitable format according to the user's requirements. For example, in presentation format, the design and animation effects of the slides are optimized to create visually appealing materials. In PDF format, care is taken to ensure that fonts and layouts are not distorted, and in printed materials, the output is optimized considering paper quality and print quality. The output unit outputs materials that have been agreed upon by multiple agents. For example, only materials that have been reviewed by multiple agents and have all revisions reflected are approved as the final output. This process guarantees the quality of the materials. Furthermore, the output unit can also produce outputs that consider the possibility of commercialization. For example, if the materials are to be used as product catalogs or marketing materials, efforts are made to enhance their appeal and attractiveness as commercial products. In this way, the output unit can provide the optimal output according to the purpose and use of the materials and meet the needs of the user. Furthermore, the output unit can collect user feedback and continuously improve the accuracy and efficiency of the output. For example, users can provide evaluations and comments on the outputted materials, and the output process can be reviewed based on that feedback, which can then be reflected in future outputs. This allows the output unit to provide valuable document creation support to users and improve work efficiency.

[0063] The learning unit can learn from previously created presentation materials and emails. For example, the learning unit learns from previously created presentation materials and emails. By learning from past materials, the learning unit enables the AI ​​agent to understand the checkpoints for content and appearance when creating materials. Previously created presentation materials and emails include, but are not limited to, materials from a specific period or materials on a specific theme. This allows the AI ​​agent to understand the checkpoints for content and appearance when creating materials. Some or all of the above processing in the learning unit may be performed using AI, or not. For example, the learning unit can input previously created presentation materials and emails into a generation AI and have the generation AI learn the checkpoints for content and appearance when creating materials.

[0064] The refinement unit can perform initial refinement of a document among multiple agents. For example, the refinement unit can perform initial refinement of a document among multiple agents. The refinement unit can improve the accuracy of the document through confirmation and revision suggestions among agents. Refinement among multiple agents includes, but is not limited to, the division of roles and communication methods among agents. This allows for improvement in the quality of the document by performing initial refinement among multiple agents. Some or all of the above-described processes in the refinement unit may be performed using, for example, AI, or without AI. For example, the refinement unit can have a generation AI perform initial refinement of a document among multiple agents.

[0065] The output unit can output documents that have been agreed upon by multiple agents. For example, the output unit outputs documents that have been agreed upon by multiple agents. By outputting documents that have been agreed upon by multiple agents, the reliability of the documents can be improved. Documents that have been agreed upon by multiple agents include, but are not limited to, the consensus-building process among agents and evaluation criteria. This improves the reliability of the documents by outputting documents that have been agreed upon by multiple agents. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI execute the output of documents that have been agreed upon by multiple agents.

[0066] The Refinement Department allows employee B's My AIagent to review documents created by employee A's My AIagent and suggest revisions. For example, the Refinement Department can have employee B's My AIagent review documents created by employee A's My AIagent and suggest revisions. The Refinement Department can improve the accuracy of documents through review and revision suggestions between agents. Employee A's My AIagent includes, for example, the scope of responsibility for document creation and the algorithms used, but is not limited to such examples. Employee B's My AIagent includes, for example, the scope of responsibility for reviewing documents and suggesting revisions, and the algorithms used, but is not limited to such examples. This allows the accuracy of documents to be improved through review and revision suggestions between agents. Some or all of the above processes in the Refinement Department may be performed using AI, for example, or without AI. For example, the Refinement Department can have a generating AI perform the review and revision suggestion of documents created by employee A's My AIagent.

[0067] The output unit can produce output that takes into account the potential for commercialization. For example, the output unit can produce output that takes into account the potential for commercialization. By considering the potential for commercialization, the output unit can contribute to the efficiency of a company's back-office operations. The potential for commercialization includes, but is not limited to, market research results and competitor analysis. This allows for the efficient production of back-office operations by producing output that takes the potential for commercialization into account. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or without AI. For example, the output unit can have a generation AI produce output that takes the potential for commercialization into account.

[0068] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, the learning unit can estimate the user's emotions and select training data based on the estimated emotions. By selecting training data according to the user's emotions, the learning unit can achieve more effective learning. User emotions include, but are not limited to, facial recognition, voice analysis, and survey results. For example, if the user is stressed, the learning unit will prioritize learning materials that promote relaxation. If the user is focused, the learning unit can prioritize learning detailed technical documents. If the user is tired, the learning unit can prioritize learning concise and easy-to-understand materials. This allows for more effective learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can estimate the user's emotions and then have the generating AI select training data based on the estimated user emotions.

[0069] The learning unit can optimize its learning algorithm by referring to past document creation history during the learning process. For example, the learning unit optimizes its learning algorithm by referring to past document creation history during the learning process. By referring to past document creation history, the learning unit improves the accuracy of its learning algorithm. Past document creation history includes, but is not limited to, past project data, creation date and time, and creator. For example, the learning unit analyzes successful and unsuccessful examples of documents created in the past and adjusts its learning algorithm. The learning unit can learn frequently used templates and formats from past document creation history. Based on past document creation history, the learning unit can build learning algorithms specialized for specific industries or fields. This improves the accuracy of the learning algorithm by referring to past document creation history. Some or all of the above processes in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can input past document creation history into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0070] The learning unit can apply different learning methods to each category of material during the learning process. For example, the learning unit can apply different learning methods to each category of material during the learning process. By applying different learning methods to each category of material, the learning unit can perform category-specific learning. Category of materials includes, but is not limited to, technical documents, sales documents, and marketing documents. For example, the learning unit can apply different learning methods to presentation materials and technical documents to perform learning tailored to their respective characteristics. The learning unit can apply different learning methods to email documents and reports to learn appropriate expressions and formats. The learning unit can apply different learning methods to marketing documents and financial documents to perform category-specific learning. This allows for category-specific learning by applying different learning methods to each category of material. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not. For example, the learning unit can have a generating AI perform the application of different learning methods to each category of material.

[0071] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit estimates the user's emotions and adjusts the learning frequency based on the estimated emotions. By adjusting the learning frequency according to the user's emotions, the learning unit enables effective learning. User emotions include, but are not limited to, facial recognition, voice analysis, and survey results. For example, if the user is stressed, the learning unit reduces the learning frequency and increases the time for relaxation. If the user is focused, the learning unit increases the learning frequency, allowing for more efficient learning. If the user is tired, the learning unit can adjust the learning frequency and include appropriate breaks. This enables effective learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using AI, or without AI. For example, the learning unit can estimate the user's emotions and cause the generating AI to adjust the frequency of learning based on the estimated user emotions.

[0072] The learning unit can weight the learning data based on the submission date of the materials during the learning process. For example, the learning unit can weight the learning data based on the submission date of the materials during the learning process. By weighting the learning data based on the submission date of the materials, the learning unit can perform efficient learning. The submission date of the materials includes, but is not limited to, the submission deadline, submission frequency, and the importance of the submitter. For example, the learning unit can prioritize learning materials with approaching deadlines and respond quickly. For materials with later submission dates, the learning unit can perform detailed learning to aim for high-quality output. The learning unit can adjust the importance of the learning data according to the submission date to perform efficient learning. This enables efficient learning by weighting the learning data based on the submission date of the materials. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can have a generating AI perform the weighting of the learning data based on the submission date of the materials.

[0073] The learning unit can prioritize learning highly relevant materials by considering the user's geographical location during the learning process. For example, the learning unit prioritizes learning highly relevant materials by considering the user's geographical location during the learning process. The learning unit can prioritize learning highly relevant materials by considering the user's geographical location. Geographical location information includes, but is not limited to, the user's location, regional characteristics, and relevant market data. For example, if the user is in a specific region, the learning unit can prioritize learning materials related to that region. If the user is on a business trip, the learning unit can prioritize learning materials related to the destination of the business trip. Based on the user's geographical location, the learning unit can learn materials that include region-specific information. This allows the learning unit to prioritize learning highly relevant materials by considering the user's geographical location. Some or all of the above processing in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can have a generating AI perform the learning of highly relevant materials by considering the user's geographical location.

[0074] The refinement unit can estimate the user's emotions and adjust the refinement method based on the estimated emotions. For example, the refinement unit can estimate the user's emotions and adjust the refinement method based on the estimated emotions. By adjusting the refinement method according to the user's emotions, the refinement unit enables effective refinement. User emotions include, but are not limited to, facial recognition, voice analysis, and survey results. For example, if the user is stressed, the refinement unit can offer simple correction suggestions to reduce the burden. If the user is focused, the refinement unit can offer detailed correction suggestions to enable high-quality refinement. If the user is tired, the refinement unit can offer concise and easy-to-understand correction suggestions. This allows for effective refinement by adjusting the refinement method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the refinement unit may be performed using AI, for example, or without AI. For example, the refinement unit can estimate the user's emotions and have the generating AI adjust the refinement method based on the estimated user emotions.

[0075] The refinement unit can adjust the level of detail of revisions based on the importance of the document during the refinement process. For example, the refinement unit can adjust the level of detail of revisions based on the importance of the document during the refinement process. By adjusting the level of detail of revisions based on the importance of the document, the refinement unit can efficiently refine the document. The importance of the document includes, but is not limited to, the purpose of the document, the target audience, and the recipient. For example, in the case of important presentation materials, the refinement unit can make detailed revision suggestions to aim for high-quality output. In the case of everyday email documents, the refinement unit can make concise revision suggestions to respond quickly. The refinement unit can efficiently refine the document by adjusting the level of detail of revisions according to the importance of the document. This allows for efficient refinement by adjusting the level of detail of revisions based on the importance of the document. Some or all of the above-described processes in the refinement unit may be performed using, for example, AI, or not. For example, the refinement unit can have a generating AI perform the adjustment of the level of detail of revisions based on the importance of the document.

[0076] The refinement department can apply different refinement algorithms depending on the category of the document during the refinement process. For example, the refinement department can apply different refinement algorithms depending on the category of the document during the refinement process. By applying refinement algorithms according to the category of the document, the refinement department can make revisions specific to each category. Document categories include, but are not limited to, technical documents, sales documents, and marketing documents. For example, the refinement department can apply different refinement algorithms to presentation materials and technical documents, making revisions according to the characteristics of each. The refinement department can apply different refinement algorithms to email documents and reports, suggesting appropriate expressions and formats. The refinement department can apply different refinement algorithms to marketing documents and financial documents, making revisions specific to each category. This allows for revisions specific to each category by applying refinement algorithms according to the category of the document. Some or all of the above processes in the refinement department may be performed using, for example, AI, or not using AI. For example, the refinement section can have the generating AI apply different refinement algorithms depending on the category of the document.

[0077] The refinement unit can estimate the user's emotions and determine the priority of refinement based on those emotions. For example, the refinement unit can estimate the user's emotions and determine the priority of refinement based on those emotions. By determining the priority of refinement according to the user's emotions, the refinement unit enables effective refinement. User emotions include, but are not limited to, facial recognition, voice analysis, and survey results. For example, if the user is stressed, the refinement unit can prioritize refining less important materials to reduce the burden. If the user is focused, the refinement unit can prioritize refining highly important materials to aim for high-quality output. If the user is tired, the refinement unit can prioritize refining concise and easy-to-understand materials. This enables effective refinement by determining the priority of refinement according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the refinement unit may be performed using AI, or not using AI. For example, the refinement unit may estimate the user's emotions and cause the generative AI to determine the priority of the refinement based on the estimated user emotions.

[0078] The refinement department can determine the priority of revisions based on the submission date of the materials during the refinement process. For example, the refinement department can determine the priority of revisions based on the submission date of the materials during the refinement process. By determining the priority of revisions based on the submission date of the materials, the refinement department can perform efficient refinement. The submission date of the materials includes, but is not limited to, the submission deadline, submission frequency, and the importance of the submitter. For example, the refinement department can prioritize the refinement of materials with approaching deadlines and respond quickly. For materials with later submission dates, the refinement department can perform detailed revisions to aim for high-quality output. The refinement department can adjust the priority of revisions according to the submission date, enabling efficient refinement. As a result, by determining the priority of revisions based on the submission date of the materials, efficient refinement becomes possible. Some or all of the above processes in the refinement department may be performed using, for example, AI, or not using AI. For example, the refinement department can have a generating AI perform the determination of revision priorities based on the submission date of the materials.

[0079] The refinement unit can improve the accuracy of revisions by referring to relevant literature in the document during the refinement process. For example, the refinement unit can improve the accuracy of revisions by referring to relevant literature in the document during the refinement process. The refinement unit improves the accuracy of revisions by referring to relevant literature in the document. Relevant literature includes, but is not limited to, selection criteria, reference methods, and citation methods. For example, the refinement unit can refer to relevant literature in the document and make revision suggestions based on accurate information. The refinement unit can make revision suggestions that complement the content of the document based on data obtained from relevant literature. The refinement unit can analyze relevant literature in the document and propose the optimal revision method. This improves the accuracy of revisions by referring to relevant literature in the document. Some or all of the above processes in the refinement unit may be performed using, for example, AI, or not using AI. For example, the refinement unit can have a generating AI perform the improvement of revision accuracy by referring to relevant literature in the document.

[0080] The output unit can estimate the user's emotions and adjust the output method based on the estimated emotions. For example, the output unit estimates the user's emotions and adjusts the output method based on the estimated emotions. By adjusting the output method according to the user's emotions, the output unit can provide effective output. User emotions include, but are not limited to, facial recognition, voice analysis, and survey results. For example, if the user is stressed, the output unit can provide a simple and highly visual output. If the user is focused, the output unit can provide an output containing detailed information. If the user is tired, the output unit can provide a concise and easy-to-understand output. This allows for effective output by adjusting the output method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processing in the output unit may be performed using AI, or not using AI. For example, the output unit can estimate the user's emotions and have the generating AI adjust the output method based on the estimated user emotions.

[0081] The output unit can adjust the level of detail of the output based on the importance of the document during output. For example, the output unit adjusts the level of detail of the output based on the importance of the document during output. By adjusting the level of detail of the output according to the importance of the document, the output unit enables efficient output. The importance of the document includes, but is not limited to, the purpose of the document, the target audience, and the recipient. For example, in the case of important presentation materials, the output unit can provide output containing detailed information. In the case of everyday emails, the output unit can provide concise and quick output. The output unit can adjust the level of detail of the output according to the importance of the document, enabling efficient output. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the adjustment of the level of detail of the output based on the importance of the document.

[0082] The output unit can apply different output methods depending on the category of the document during output. For example, the output unit can apply different output methods depending on the category of the document during output. By applying output methods according to the category of the document, the output unit can produce output specialized for each category. Document categories include, but are not limited to, technical documents, sales documents, and marketing documents. For example, the output unit can apply different output methods to presentation materials and technical documents to produce output appropriate to their respective characteristics. The output unit can apply different output methods to emails and reports to provide appropriate expression and formatting. The output unit can apply different output methods to marketing documents and financial documents to produce output specialized for each category. This makes it possible to produce output specialized for each category by applying output methods according to the category of the document. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the application of different output methods depending on the category of the document.

[0083] The output unit can estimate the user's emotions and determine the priority of outputs based on the estimated emotions. For example, the output unit can estimate the user's emotions and determine the priority of outputs based on the estimated emotions. By determining the priority of outputs according to the user's emotions, the output unit can produce effective outputs. User emotions include, but are not limited to, facial recognition, voice analysis, and survey results. For example, if the user is stressed, the output unit can prioritize less important outputs to reduce the burden. If the user is focused, the output unit can prioritize highly important outputs to aim for high-quality outputs. If the user is tired, the output unit can prioritize concise and easy-to-understand outputs. This allows for effective outputs by determining the priority of outputs according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the processing described above in the output unit may be performed using AI, for example, or without AI. For example, the output unit may estimate the user's emotions and cause the generating AI to determine the priority of the output based on the estimated user emotions.

[0084] The output unit can adjust the order of outputs based on the submission dates of the materials during the output process. For example, the output unit can adjust the order of outputs based on the submission dates of the materials during the output process. By adjusting the order of outputs based on the submission dates of the materials, the output unit can achieve efficient output. The submission dates of the materials include, but are not limited to, the submission deadline, submission frequency, and the importance of the submitter. For example, the output unit can prioritize outputting materials with approaching deadlines and respond quickly. For materials with later submission dates, the output unit can provide detailed output, aiming for high-quality output. The output unit can adjust the order of outputs according to the submission dates, enabling efficient output. As a result, by adjusting the order of outputs based on the submission dates of the materials, efficient output becomes possible. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the adjustment of the output order based on the submission dates of the materials.

[0085] The output unit can improve the accuracy of the output by referring to relevant market data for the document during the output process. For example, the output unit can improve the accuracy of the output by referring to relevant market data for the document during the output process. The output unit improves the accuracy of the output by referring to relevant market data for the document. Relevant market data includes, but is not limited to, market data selection criteria, reference methods, and data analysis methods. For example, the output unit can refer to relevant market data for the document and produce output based on accurate information. The output unit can produce output that complements the content of the document based on data obtained from relevant market data. The output unit can analyze relevant market data for the document and propose the optimal output method. This improves the accuracy of the output by referring to relevant market data for the document. Some or all of the above processing in the output unit may be performed using, for example, AI, or not using AI. For example, the output unit can have a generating AI perform the improvement of output accuracy by referring to relevant market data for the document.

[0086] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0087] The document creation support system can estimate the user's emotions and adjust the content of the document based on those emotions. For example, if the user is stressed, the system will prioritize creating a concise and easy-to-understand document. If the user is focused, it can create a document containing detailed information. Furthermore, if the user is tired, it can create a document with a visually appealing and relaxing design. This enables document creation tailored to the user's emotions, further improving work efficiency.

[0088] Document creation support systems can analyze a user's past document creation history and automatically suggest frequently used templates and formats. For example, they can refer to past project data and prioritize suggesting templates for successful documents. Furthermore, they can provide templates tailored to specific industries or fields. This allows users to create documents efficiently and improve their work productivity.

[0089] The document creation support system can prioritize the creation of highly relevant documents by considering the user's geographical location. For example, if the user is in a specific region, it can create documents containing market data and trend information related to that region. If the user is on a business trip, it can create documents containing information related to their destination. It can also provide documents that take into account the unique culture and business practices of the region. This allows users to create more effective documents.

[0090] The document creation support system can estimate the user's emotions and adjust the document layout based on those emotions. For example, if the user is stressed, it can provide a simple and highly visible layout. If the user is focused, it can provide a complex layout containing detailed information. If the user is tired, it can provide a layout using relaxing colors and designs. This allows the system to provide the optimal layout according to the user's emotions.

[0091] The document creation support system can apply different output methods depending on the category of the document. For example, it can provide output containing detailed technical information for technical documents, and output in a visually appealing presentation format for sales materials. It can also provide output containing market data and trend information for marketing materials. Furthermore, it can suggest the optimal format and design for each category. This enables effective output tailored to each category.

[0092] The document creation support system can estimate the user's emotions and suggest revisions to the document based on those emotions. For example, if the user is stressed, it will suggest simple and easy-to-follow revisions. If the user is focused, it will suggest detailed revisions, enabling the creation of high-quality documents. If the user is tired, it will suggest concise and easy-to-understand revisions. In this way, it can provide optimal revision suggestions tailored to the user's emotions.

[0093] The document creation support system can weight training data based on the submission deadline of the documents. For example, it can prioritize training on documents with approaching deadlines to ensure a quick response. For documents with later deadlines, it can conduct detailed training to aim for high-quality output. It can also adjust the weighting of training data according to submission frequency and the importance of the submitter. This enables efficient training and improves the accuracy of document creation.

[0094] The document creation support system can estimate the user's emotions and prioritize documents based on those emotions. For example, if the user is stressed, it can prioritize creating less important documents to reduce their burden. If the user is focused, it can prioritize creating highly important documents to aim for high-quality output. Furthermore, if the user is tired, it can prioritize creating concise and easy-to-understand documents. This enables the creation of optimal documents tailored to the user's emotions.

[0095] The document creation support system can improve the accuracy of revisions by referring to related literature. For example, it can refer to related literature and make revision suggestions based on accurate information. It can also make revision suggestions that complement the content of the document based on data obtained from related literature. Furthermore, it can analyze related literature and suggest the optimal revision method. As a result, by referring to related literature, the accuracy of revisions is improved, and high-quality documents can be created.

[0096] The document creation support system can estimate the user's emotions and adjust the output method based on those emotions. For example, if the user is stressed, it can provide a simple and highly visual output. If the user is focused, it can provide an output containing detailed information. And if the user is tired, it can provide a concise and easy-to-understand output. In this way, it can provide the optimal output method according to the user's emotions.

[0097] The following briefly describes the processing flow for example form 2.

[0098] Step 1: The learning unit learns information related to document creation. This information includes presentation materials, reports, and email documents. The learning unit learns from previously created presentation materials and email documents, and the AI ​​agent understands the checkpoints for content and appearance when creating documents. Step 2: The Refinement Unit performs a preliminary refinement of the document based on the information learned by the Learning Unit. This preliminary refinement includes grammar checks, layout adjustments, and content review. The Refinement Unit performs the preliminary refinement of the document with multiple agents. For example, employee A's My AIagent creates a document, employee B's My AIagent reviews it, and suggests revisions. This improves the accuracy of the document. Step 3: The Output Unit outputs the materials that have been refined by the Refinement Unit. Outputs may include PDF format, presentation format, printed materials, etc. The Output Unit can also output materials that have been agreed upon by multiple agents and may consider the possibility of commercialization.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0101] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0102] Each of the multiple elements described above, including the learning unit, the refinement unit, and the output unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart device 14 and learns from previously created presentation materials and email texts. The refinement unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs initial refinement of the materials based on the learned information. The output unit is implemented by the control unit 46A of the smart device 14 and outputs the refined materials in PDF format or presentation format. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0103] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0104] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0109] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0110] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0111] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0112] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0113] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0117] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements described above, including the learning unit, the refinement unit, and the output unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart glasses 214 and learns presentation materials and email texts created in the past. The refinement unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs initial refinement of the materials based on the learned information. The output unit is implemented by the control unit 46A of the smart glasses 214 and outputs the refined materials in PDF format or presentation format. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0119] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0120] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0122] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0123] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0125] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0126] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0127] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0128] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0129] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0133] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the learning unit, the refinement unit, and the output unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the headset terminal 314 and learns presentation materials and email texts created in the past. The refinement unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs initial refinement of the materials based on the learned information. The output unit is implemented by the control unit 46A of the headset terminal 314 and outputs the refined materials in PDF format or presentation format. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0135] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0136] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0143] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0144] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0145] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0146] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0148] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0150] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] Each of the multiple elements described above, including the learning unit, the refinement unit, and the output unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the robot 414 and learns from previously created presentation materials and email documents. The refinement unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs initial refinement of the materials based on the learned information. The output unit is implemented by the control unit 46A of the robot 414 and outputs the refined materials in PDF format or presentation format. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0152] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0154] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0155] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0156] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0160] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0161] 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.

[0162] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0163] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0164] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0165] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0167] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0168] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0169] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0170] (Note 1) A learning section where you can learn about information related to document creation, A brush-up unit performs initial refinement of the materials based on the information learned by the aforementioned learning unit, The system comprises an output unit that outputs the materials that have been refined by the aforementioned refinement unit. A system characterized by the following features. (Note 2) The aforementioned learning unit, Learn from presentation materials and emails created in the past. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned brush-up section is, Perform initial refinement of materials among multiple agents. The system described in Appendix 1, characterized by the features described herein. (Note 4) The output unit is, Output documents that have been agreed upon by multiple agents. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned brush-up section is, Employee B's My AIagent reviews a document created by Employee A's My AIagent and proposes revisions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The output unit is, We will produce output that takes into account the potential for commercialization. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past document creation history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, When learning, apply different learning methods to each category of material. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, During training, the training data is weighted based on the submission timing of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, During learning, the system prioritizes learning relevant materials by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned brush-up section is, We estimate the user's emotions and adjust the refinement method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned brush-up section is, During the refinement process, adjust the level of detail of the revisions based on the importance of the material. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned brush-up section is, During the refinement process, different refinement algorithms are applied depending on the category of the document. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned brush-up section is, We estimate the user's emotions and determine the priority of improvements based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned brush-up section is, During the refinement process, prioritize revisions based on the submission deadlines for the documents. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned brush-up section is, During the refinement process, we improve the accuracy of the revisions by referring to related literature in the materials. The system described in Appendix 1, characterized by the features described herein. (Note 19) The output unit is, It estimates the user's emotions and adjusts the output method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The output unit is, When outputting, adjust the level of detail in the output based on the importance of the document. The system described in Appendix 1, characterized by the features described herein. (Note 21) The output unit is, When outputting, different output methods are applied depending on the category of the document. The system described in Appendix 1, characterized by the features described herein. (Note 22) The output unit is, It estimates the user's emotions and determines the priority of outputs based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The output unit is, When outputting, adjust the order of output based on the submission date of the materials. The system described in Appendix 1, characterized by the features described herein. (Note 24) The output unit is, When outputting, we improve the accuracy of the output by referring to relevant market data in the document. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning section where you can learn about information related to document creation, A brush-up unit performs initial refinement of the materials based on the information learned by the aforementioned learning unit, The system comprises an output unit that outputs the materials that have been refined by the aforementioned refinement unit. A system characterized by the following features.

2. The aforementioned learning unit, Learn from presentation materials and emails created in the past. The system according to feature 1.

3. The aforementioned brush-up section is, Perform initial refinement of materials among multiple agents. The system according to feature 1.

4. The output unit is, Output documents that have been agreed upon by multiple agents. The system according to feature 1.

5. The aforementioned brush-up section is, Employee B's My AIagent reviews a document created by Employee A's My AIagent and proposes revisions. The system according to feature 1.

6. The output unit is, We will produce output that takes into account the potential for commercialization. The system according to feature 1.

7. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

8. The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past document creation history. The system according to feature 1.

Images