system

Abstract

An object of the system according to the embodiment is to provide a learning environment for a material generation AI that operates on a local PC.SOLUTION: A system according to an embodiment includes a provision unit, an operation unit, and a subscription unit. The providing unit provides a learning environment of the material generation AI. The operation unit operates the material generation model learned by the provision unit on the local PC. The subscription unit provides a learning environment of the material generation AI in a subscription form.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the learning environment for document generation AI relied on cloud computing, posing a risk of confidential information being leaked.

[0005] The system according to the embodiment aims to provide a learning environment for a material generation AI that runs on a local PC. [Means for solving the problem]

[0006] The system according to the embodiment includes a providing unit, an operating unit, and a subscription unit. The providing unit provides a learning environment for the material generation AI. The operating unit runs the material generation model trained by the providing unit on a local PC. The subscription unit provides the learning environment for the material generation AI in a subscription format. [Effects of the Invention]

[0007] The system according to the embodiment can provide a learning environment for a material generation AI that runs on a local PC. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A document generation system according to an embodiment of the present invention provides a learning environment for a document generation AI and operates on a local PC. By providing a learning environment for the document generation AI and operating on a local PC, the document generation system reduces the risk of confidential information leaks and enables efficient document creation. For example, the document generation system uses documents previously created by a company as input data, and the generation AI learns the format and content of those documents. The document generation system then runs the trained document generation model on the local PC. For example, when a user inputs the document's theme and necessary information, the generation AI automatically generates the optimal document. Furthermore, the document generation system provides a learning environment for the document generation AI on a subscription basis and provides support for a document generation model optimized for each company. For example, if a company introduces a new document format, consulting services are provided to help the company learn that format. This allows the document generation system to improve the efficiency of document creation and reduce the risk of confidential information leaks. The system can be used for a variety of purposes, such as creating product manuals in the manufacturing industry and medical reports in the medical industry.

[0029] A document generation system according to an embodiment includes a providing unit, an operating unit, and a subscription unit. The providing unit uses documents previously created by a company as input data, and the generation AI learns the format and content of the documents. For example, the providing unit uses reports, presentation materials, technical documents, etc. previously created by the company as input data. The providing unit can also provide datasets, hardware, software tools, etc. for the generation AI to learn the format and content of the documents. The operating unit automatically generates optimal documents when a user inputs the document's theme and necessary information. For example, the operating unit allows a user to input information such as a project outline, technical specifications, and market analysis, and the generation AI generates documents based on that information. The operating unit also allows the generation AI to use a document generation model optimized for each company, thereby generating documents tailored to the company's needs. The subscription unit provides a learning environment for the document generation AI in a subscription format and provides support for the document generation model optimized for each company. For example, if a company introduces a new document format, the subscription unit provides consulting services to help the company learn the format. This allows the document generation system according to an embodiment to improve the efficiency of document creation and reduce the risk of confidential information leaks.

[0030] The providing unit can use materials previously created by a company as input data, allowing the generation AI to learn the format and content of those materials. Materials previously created by a company include, but are not limited to, reports, presentation materials, and technical documents. For example, the providing unit can use reports previously created by a company as input data, allowing the generation AI to learn their format and content. The providing unit can also use presentation materials previously created by a company as input data, allowing the generation AI to learn their format and content. Furthermore, the providing unit can use technical documents previously created by a company as input data, allowing the generation AI to learn their format and content. This allows a document generation model optimized for each company to be built by learning from the company's past materials. Some or all of the above-described processing in the providing unit can be performed, for example, using AI, or can be performed without AI. For example, the providing unit can input materials previously created by a company into the generation AI, causing the generation AI to learn the format and content of the materials.

[0031] The operating unit allows the generation AI to automatically generate materials when a user inputs the theme and necessary information of the materials. Examples of the theme and necessary information of the materials include, but are not limited to, a project outline, technical specifications, and market analysis. For example, when a user inputs a project outline, the generation AI generates materials based on the project outline. The operating unit can also allow the generation AI to generate materials based on technical specifications when a user inputs them. Furthermore, the operating unit can also allow the generation AI to generate materials based on market analysis when a user inputs it. This allows optimal materials to be automatically generated based on the information input by the user. Some or all of the above-described processing in the operating unit may be performed using AI, for example, or may be performed without using AI. For example, the operating unit can input information input by a user into the generation AI and cause the generation AI to generate materials.

[0032] When a company introduces a new document format, the subscription department can provide a service for training the format. Examples of new document formats include, but are not limited to, template types, layouts, and design elements. For example, when a company introduces a new template, the subscription department can provide a consulting service for training the template. Furthermore, when a company introduces a new layout, the subscription department can provide a consulting service for training the layout. Furthermore, when a company introduces new design elements, the subscription department can provide a consulting service for training the design elements. This enables the generation AI to respond quickly when a new document format is introduced. Some or all of the above-described processing in the subscription department may be performed using AI, or may be performed without AI. For example, the subscription department can input a new document format into the generation AI and cause the generation AI to train the format.

[0033] The providing unit can analyze the company's past document creation history and select the optimal learning method. For example, the providing unit can analyze the format of documents created by the company in the past, and the generation AI can learn based on that format. The providing unit can also identify frequently used templates from the company's past document creation history and have the generation AI prioritize learning from those templates. Furthermore, the providing unit can analyze the company's past document creation history and select the most efficient learning method for the generation AI. In this way, an efficient learning method can be selected by analyzing the company's past document creation history. Optimal learning methods include, but are not limited to, supervised learning, unsupervised learning, and reinforcement learning. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the company's past document creation history into the generation AI and have the generation AI select the optimal learning method.

[0034] When learning the materials, the providing unit can filter them based on the company's current projects and areas of interest. For example, the providing unit prioritizes learning materials related to the company's current projects. The providing unit can also filter and learn materials related to the generation AI based on the company's areas of interest. Furthermore, the providing unit can also select and learn optimal materials based on the company's current projects and areas of interest. This allows the generation AI to prioritize learning related materials based on the company's current projects and areas of interest. Examples of the company's current projects and areas of interest include, but are not limited to, research and development projects and marketing campaigns. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input data on the company's current projects and areas of interest into the generation AI and have the generation AI perform filtering.

[0035] When studying the materials, the providing unit can select the optimal learning means according to the company's input method. For example, if the company uses voice input, the providing unit can cause the generation AI to learn the voice data. Furthermore, if the company uses text input, the providing unit can also cause the generation AI to learn the text data. Furthermore, if the company uses image input, the providing unit can also cause the generation AI to learn the image data. This enables efficient learning by selecting the optimal learning means according to the company's input method. Examples of company input methods include, but are not limited to, voice input, text input, and image input. Some or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the company's input data into the generation AI and cause the generation AI to select the optimal learning means.

[0036] When learning materials, the providing unit can prioritize learning highly relevant materials by taking into account the geographical location information of the company. For example, the providing unit can prioritize learning materials related to the company's location. The providing unit can also cause the generation AI to learn region-specific materials based on the geographical location information of the company. Furthermore, the providing unit can cause the generation AI to select and learn optimal materials by taking into account the geographical location information of the company. This allows highly relevant materials to be prioritized by taking into account the geographical location information of the company. Examples of geographical location information of the company include, but are not limited to, countries, regions, cities, etc. Some or all of the above-mentioned processing in the providing unit can be performed using AI, or can be performed without using AI. For example, the providing unit can input the geographical location information of the company into the generation AI and cause the generation AI to select highly relevant materials.

[0037] When learning the materials, the providing unit can analyze the company's social media activities and learn related materials. For example, the providing unit analyzes the company's social media posts, and the generation AI learns related materials. The providing unit can also select the most appropriate materials from the company's social media activities and have the generation AI learn from them. Furthermore, the providing unit can also have the generation AI prioritize learning related materials based on the company's social media activities. This allows the generation AI to prioritize learning related materials by analyzing the company's social media activities. Examples of the company's social media activities include, but are not limited to, post content, follower reactions, and engagement rates. Some or all of the above-mentioned processing in the providing unit can be performed using AI, or can be performed without using AI. For example, the providing unit can input data on the company's social media activities into the generation AI and have the generation AI learn related materials.

[0038] The provision unit can customize the learning method by reflecting the company's past feedback when studying the materials. For example, the provision unit causes the generation AI to adjust the learning method based on the company's past feedback. The provision unit can also cause the generation AI to select the optimal learning method by reflecting the company's past feedback. Furthermore, the provision unit can cause the generation AI to customize the learning method by taking the company's past feedback into consideration. This allows the optimal learning method to be selected by reflecting the company's past feedback. Examples of the company's past feedback include, but are not limited to, user reviews, survey results, and customer support records. Some or all of the above-described processing in the provision unit may be performed using AI, or may be performed without using AI. For example, the provision unit can input the company's past feedback into the generation AI and cause the generation AI to customize the learning method.

[0039] The operating unit can adjust the level of detail of the generated material based on the importance of the material when generating the material. For example, in the case of important material, the operating unit causes the generation AI to generate material with detailed content. In addition, in the case of less important material, the operating unit can cause the generation AI to generate material with concise content. Furthermore, the operating unit can cause the generation AI to select an optimal level of detail depending on the importance of the material and generate the material. This enables efficient material generation by adjusting the level of detail of the generated material depending on the importance of the material. Examples of the importance of the material include, but are not limited to, project priorities, management instructions, and customer requests. Some or all of the above-mentioned processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input material importance data into the generation AI and cause the generation AI to adjust the level of detail of the generated material.

[0040] When generating materials, the operating unit can apply different generation algorithms depending on the category of the materials. For example, in the case of technical materials, the operating unit causes the generation AI to apply an algorithm specialized for technical content. Furthermore, in the case of marketing materials, the operating unit can cause the generation AI to apply an algorithm specialized for marketing. Furthermore, the operating unit can cause the generation AI to select an optimal generation algorithm depending on the category of the materials and generate the materials. This enables efficient material generation by applying an optimal generation algorithm depending on the category of the materials. Examples of material categories include, but are not limited to, technical documents, marketing materials, financial reports, etc. Some or all of the above-mentioned processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input material category data into the generation AI and cause the generation AI to apply a generation algorithm.

[0041] When generating materials, the operating unit can improve the accuracy of generation by referring to the user's past generation results. For example, the operating unit analyzes the user's past generation results, and the generation AI generates optimal materials. The operating unit can also improve the accuracy of generation by referring to the user's past generation results. Furthermore, the operating unit can select the optimal generation method for the generation AI based on the user's past generation results. This improves the accuracy of generation by referring to the user's past generation results. The user's past generation results include, for example, past project materials, review results, feedback, etc., but are not limited to these examples. Some or all of the above-mentioned processing in the operating unit may be performed using AI, for example, or may be performed without using AI. For example, the operating unit can input the user's past generation result data into the generation AI and cause the generation AI to improve the accuracy of generation.

[0042] The operating unit can determine the generation priority based on the submission date of the materials when generating the materials. For example, the operating unit prioritizes the generation of materials with an upcoming deadline. The operating unit can also postpone materials with a more distant submission date. Furthermore, the operating unit can cause the generation AI to select the optimal priority based on the submission date of the materials and generate the materials. This enables efficient material generation by determining the generation priority based on the submission date of the materials. The submission date of the materials includes, but is not limited to, project deadlines, customer requests, internal schedules, etc. Some or all of the above-mentioned processing in the operating unit can be performed using, for example, AI, or can be performed without using AI. For example, the operating unit can input data on the submission date of the materials to the generation AI and cause the generation AI to determine the generation priority.

[0043] The operating unit can adjust the order of generation based on the relevance of the materials when generating the materials. For example, the operating unit can prioritize generating highly relevant materials. The operating unit can also postpone generating less relevant materials. Furthermore, the operating unit can cause the generation AI to select an optimal order based on the relevance of the materials and generate the materials. This enables efficient material generation by adjusting the order of generation based on the relevance of the materials. Examples of the relevance of the materials include, but are not limited to, a common theme, overlapping content, and commonality of purpose. Some or all of the above-described processing in the operating unit can be performed using, or without, AI. For example, the operating unit can input relevance data of the materials into the generation AI and cause the generation AI to adjust the order of generation.

[0044] The operating unit can adjust the use of technical terminology in generating materials according to the user's level of expertise. For example, if the user has technical expertise, the operating unit can cause the generation AI to generate materials that use a lot of technical terminology. Alternatively, if the user does not have technical expertise, the operating unit can cause the generation AI to generate materials that avoid technical terminology. Furthermore, the operating unit can cause the generation AI to select the most appropriate technical terminology to be used according to the user's level of expertise and generate materials. This enables appropriate materials to be generated by adjusting the use of technical terminology according to the user's level of expertise. Examples of the user's level of expertise include, but are not limited to, work experience, educational background, and past project experience. Some or all of the above-described processing by the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0045] When providing a subscription, the subscription unit can analyze the company's past usage history and select the optimal service. For example, the subscription unit can have a generation AI propose the optimal subscription service based on the company's past usage history. The subscription unit can also analyze the company's past usage history and have the generation AI select the optimal service content. Furthermore, the subscription unit can have the generation AI provide the optimal subscription content by referring to the company's past usage history. This allows the optimal service to be provided by analyzing the company's past usage history. The company's past usage history includes, for example, past service usage status, contract history, feedback, etc., but is not limited to these examples. Some or all of the above-described processing in the subscription unit may be performed using, or without, AI. For example, the subscription unit can input the company's past usage history data into the generation AI and have the generation AI select the optimal service.

[0046] The subscription department can customize the service content based on the company's current needs when providing a subscription. For example, the subscription department can have the generation AI provide the optimal subscription content based on the company's current needs. The subscription department can also have the generation AI customize the service content according to the company's current needs. Furthermore, the subscription department can also have the generation AI select the optimal service content taking the company's current needs into consideration. This enables appropriate service provision by customizing the service content based on the company's current needs. The company's current needs include, but are not limited to, current project requirements, management policies, and customer requests. Some or all of the above-described processing in the subscription department can be performed using, or without, AI. For example, the subscription department can input the company's current needs data into the generation AI and have the generation AI customize the service content.

[0047] The subscription unit can improve the service content by reflecting the company's feedback when providing a subscription. For example, the subscription unit allows the generation AI to improve the service content based on the company's feedback. The subscription unit can also allow the generation AI to select the optimal service content by reflecting the company's feedback. Furthermore, the subscription unit can also allow the generation AI to customize the service content by taking the company's feedback into consideration. This allows the service content to be improved by reflecting the company's feedback. Examples of company feedback include, but are not limited to, user reviews, survey results, and customer support records. Some or all of the above-described processing in the subscription unit may be performed using, or without, AI. For example, the subscription unit can input company feedback data into the generation AI and have the generation AI improve the service content.

[0048] When providing a subscription, the subscription unit can select the optimal service by taking into account the company's geographic location information. For example, the subscription unit can prioritize services related to the company's location. The subscription unit can also cause the generation AI to provide region-specific services based on the company's geographic location information. Furthermore, the subscription unit can cause the generation AI to select the optimal service by taking into account the company's geographic location information. This allows the optimal service to be provided by taking into account the company's geographic location information. Examples of the company's geographic location information include, but are not limited to, countries, regions, and cities. Some or all of the above-described processing in the subscription unit may be performed using AI, or may be performed without using AI. For example, the subscription unit can input the company's geographic location information data into the generation AI and cause the generation AI to select the optimal service.

[0049] When providing a subscription, the subscription unit can analyze the company's social media activity and suggest service content. For example, the subscription unit analyzes the company's social media posts, and the generation AI suggests related services. The subscription unit can also select the most appropriate service content based on the company's social media activity. Furthermore, the subscription unit can prioritize related services based on the company's social media activity. This allows related services to be provided by analyzing the company's social media activity. Examples of the company's social media activity include, but are not limited to, post content, follower reactions, and engagement rates. Some or all of the above-mentioned processing in the subscription unit may be performed using AI, or may be performed without AI. For example, the subscription unit can input the company's social media activity data into the generation AI and have the generation AI suggest service content.

[0050] When providing a subscription, the subscription unit can customize the service content by reflecting the company's past feedback. For example, the subscription unit allows the generation AI to adjust the service content based on the company's past feedback. The subscription unit can also allow the generation AI to select optimal service content by reflecting the company's past feedback. Furthermore, the subscription unit can also allow the generation AI to customize the service content by taking the company's past feedback into consideration. This allows optimal services to be provided by reflecting the company's past feedback. Examples of the company's past feedback include, but are not limited to, user reviews, survey results, and customer support records. Some or all of the above-described processing in the subscription unit may be performed using, or without, AI. For example, the subscription unit can input the company's past feedback data into the generation AI and have the generation AI customize the service content.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The providing unit can analyze the company's past document creation history and select the optimal learning method. For example, the format of documents created by the company in the past can be analyzed, and the generation AI can learn based on that format. The providing unit can also identify frequently used templates from the company's past document creation history and have the generation AI prioritize learning from those templates. The providing unit can also analyze the company's past document creation history and select the most efficient learning method for the generation AI. In this way, an efficient learning method can be selected by analyzing the company's past document creation history. Optimal learning methods include, but are not limited to, supervised learning, unsupervised learning, and reinforcement learning. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the company's past document creation history into the generation AI and have the generation AI select the optimal learning method.

[0053] When generating documents, the operating unit can adjust the level of detail of the generated documents based on the importance of the documents. For example, in the case of important documents, the generation AI can generate documents with detailed content. In addition, in the case of documents with low importance, the operating unit can also generate documents with concise content. Furthermore, the operating unit can generate documents by having the generation AI select an optimal level of detail depending on the importance of the documents. This enables efficient document generation by adjusting the level of detail of the generated documents based on the importance of the documents. Examples of the importance of documents include, but are not limited to, project priorities, management instructions, and customer requests. Some or all of the above-described processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input data on the importance of the documents into the generation AI and cause the generation AI to adjust the level of detail of the generated documents.

[0054] When learning materials, the providing unit can filter them based on the company's current projects and areas of interest. For example, materials related to the company's current projects can be prioritized for learning. The providing unit can also filter and learn materials related to the generation AI based on the company's areas of interest. Furthermore, the providing unit can also select and learn optimal materials based on the company's current projects and areas of interest. This allows related materials to be learned preferentially based on the company's current projects and areas of interest. Examples of the company's current projects and areas of interest include, but are not limited to, research and development projects and marketing campaigns. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input data on the company's current projects and areas of interest into the generation AI and have the generation AI perform filtering.

[0055] When generating materials, the operating unit can apply different generation algorithms depending on the category of the materials. For example, in the case of technical materials, the generation AI can apply an algorithm specialized for technical content. In addition, in the case of marketing materials, the operating unit can also cause the generation AI to apply an algorithm specialized for marketing. Furthermore, the operating unit can cause the generation AI to select an optimal generation algorithm depending on the category of the materials and generate the materials. This enables efficient material generation by applying an optimal generation algorithm depending on the category of the materials. Examples of material categories include, but are not limited to, technical documents, marketing materials, financial reports, etc. Some or all of the above-mentioned processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input material category data into the generation AI and cause the generation AI to apply a generation algorithm.

[0056] When studying the materials, the providing unit can select the optimal learning means depending on the company's input method. For example, if the company uses voice input, the generation AI can learn the voice data. Furthermore, if the company uses text input, the providing unit can also have the generation AI learn the text data. Furthermore, if the company uses image input, the providing unit can also have the generation AI learn the image data. This enables efficient learning by selecting the optimal learning means depending on the company's input method. Examples of company input methods include, but are not limited to, voice input, text input, and image input. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input the company's input data into the generation AI and have the generation AI select the optimal learning means.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The provision department uses documents previously created by the company as input data, and the generation AI learns the format and content of those documents. For example, the provision department uses reports, presentation materials, technical documents, etc. previously created by the company as input data. The provision department can also provide datasets, hardware, software tools, etc. for the generation AI to learn the format and content of those documents. Step 2: In the operating unit, the user inputs the document theme and necessary information, and the generation AI automatically generates the optimal document. For example, when the user inputs information such as a project outline, technical specifications, and market analysis, the generation AI generates the document based on that information. In addition, the operating unit uses a document generation model optimized for each company, so the generation AI can generate documents that meet the company's needs. Step 3: The Subscription Department provides a learning environment for the document generation AI on a subscription basis and provides support for document generation models optimized for each company. For example, if a company introduces a new document format, the Subscription Department provides consulting services to train that format.

[0059] (Example 2) A document generation system according to an embodiment of the present invention provides a learning environment for a document generation AI and operates on a local PC. By providing a learning environment for the document generation AI and operating on a local PC, the document generation system reduces the risk of confidential information leaks and enables efficient document creation. For example, the document generation system uses documents previously created by a company as input data, and the generation AI learns the format and content of those documents. The document generation system then runs the trained document generation model on the local PC. For example, when a user inputs the document's theme and necessary information, the generation AI automatically generates the optimal document. Furthermore, the document generation system provides a learning environment for the document generation AI on a subscription basis and provides support for a document generation model optimized for each company. For example, if a company introduces a new document format, consulting services are provided to help the company learn that format. This allows the document generation system to improve the efficiency of document creation and reduce the risk of confidential information leaks. The system can be used for a variety of purposes, such as creating product manuals in the manufacturing industry and medical reports in the medical industry.

[0060] A document generation system according to an embodiment includes a providing unit, an operating unit, and a subscription unit. The providing unit uses documents previously created by a company as input data, and the generation AI learns the format and content of the documents. For example, the providing unit uses reports, presentation materials, technical documents, etc. previously created by the company as input data. The providing unit can also provide datasets, hardware, software tools, etc. for the generation AI to learn the format and content of the documents. The operating unit automatically generates optimal documents when a user inputs the document's theme and necessary information. For example, the operating unit allows a user to input information such as a project outline, technical specifications, and market analysis, and the generation AI generates documents based on that information. The operating unit also allows the generation AI to use a document generation model optimized for each company, thereby generating documents tailored to the company's needs. The subscription unit provides a learning environment for the document generation AI in a subscription format and provides support for the document generation model optimized for each company. For example, if a company introduces a new document format, the subscription unit provides consulting services to help the company learn the format. This allows the document generation system according to an embodiment to improve the efficiency of document creation and reduce the risk of confidential information leaks.

[0061] The providing unit can use materials previously created by a company as input data, allowing the generation AI to learn the format and content of those materials. Materials previously created by a company include, but are not limited to, reports, presentation materials, and technical documents. For example, the providing unit can use reports previously created by a company as input data, allowing the generation AI to learn their format and content. The providing unit can also use presentation materials previously created by a company as input data, allowing the generation AI to learn their format and content. Furthermore, the providing unit can use technical documents previously created by a company as input data, allowing the generation AI to learn their format and content. This allows a document generation model optimized for each company to be built by learning from the company's past materials. Some or all of the above-described processing in the providing unit can be performed, for example, using AI, or can be performed without AI. For example, the providing unit can input materials previously created by a company into the generation AI, causing the generation AI to learn the format and content of the materials.

[0062] The operating unit allows the generation AI to automatically generate materials when a user inputs the theme and necessary information of the materials. Examples of the theme and necessary information of the materials include, but are not limited to, a project outline, technical specifications, and market analysis. For example, when a user inputs a project outline, the generation AI generates materials based on the project outline. The operating unit can also allow the generation AI to generate materials based on technical specifications when a user inputs them. Furthermore, the operating unit can also allow the generation AI to generate materials based on market analysis when a user inputs it. This allows optimal materials to be automatically generated based on the information input by the user. Some or all of the above-described processing in the operating unit may be performed using AI, for example, or may be performed without using AI. For example, the operating unit can input information input by a user into the generation AI and cause the generation AI to generate materials.

[0063] When a company introduces a new document format, the subscription department can provide a service for training the format. Examples of new document formats include, but are not limited to, template types, layouts, and design elements. For example, when a company introduces a new template, the subscription department can provide a consulting service for training the template. Furthermore, when a company introduces a new layout, the subscription department can provide a consulting service for training the layout. Furthermore, when a company introduces new design elements, the subscription department can provide a consulting service for training the design elements. This enables the generation AI to respond quickly when a new document format is introduced. Some or all of the above-described processing in the subscription department may be performed using AI, or may be performed without AI. For example, the subscription department can input a new document format into the generation AI and cause the generation AI to train the format.

[0064] The providing unit can estimate the user's emotions and adjust the timing of studying the materials based on the estimated user emotions. For example, if the user is feeling stressed, the providing unit can cause the generation AI to temporarily suspend studying the materials and resume when the user is able to relax. Furthermore, if the user is concentrating, the providing unit can cause the generation AI to continuously study the materials and efficiently build a model. Furthermore, if the user is tired, the providing unit can cause the generation AI to reduce the frequency of study, thereby reducing the user's burden. This enables efficient study by adjusting the study timing according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without AI. For example, the providing unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0065] The providing unit can analyze the company's past document creation history and select the optimal learning method. For example, the providing unit can analyze the format of documents created by the company in the past, and the generation AI can learn based on that format. The providing unit can also identify frequently used templates from the company's past document creation history and have the generation AI prioritize learning from those templates. Furthermore, the providing unit can analyze the company's past document creation history and select the most efficient learning method for the generation AI. In this way, an efficient learning method can be selected by analyzing the company's past document creation history. Optimal learning methods include, but are not limited to, supervised learning, unsupervised learning, and reinforcement learning. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the company's past document creation history into the generation AI and have the generation AI select the optimal learning method.

[0066] When learning the materials, the providing unit can filter them based on the company's current projects and areas of interest. For example, the providing unit prioritizes learning materials related to the company's current projects. The providing unit can also filter and learn materials related to the generation AI based on the company's areas of interest. Furthermore, the providing unit can also select and learn optimal materials based on the company's current projects and areas of interest. This allows the generation AI to prioritize learning related materials based on the company's current projects and areas of interest. Examples of the company's current projects and areas of interest include, but are not limited to, research and development projects and marketing campaigns. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input data on the company's current projects and areas of interest into the generation AI and have the generation AI perform filtering.

[0067] When studying the materials, the providing unit can select the optimal learning means according to the company's input method. For example, if the company uses voice input, the providing unit can cause the generation AI to learn the voice data. Furthermore, if the company uses text input, the providing unit can also cause the generation AI to learn the text data. Furthermore, if the company uses image input, the providing unit can also cause the generation AI to learn the image data. This enables efficient learning by selecting the optimal learning means according to the company's input method. Examples of company input methods include, but are not limited to, voice input, text input, and image input. Some or all of the above-mentioned processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input the company's input data into the generation AI and cause the generation AI to select the optimal learning means.

[0068] The providing unit can estimate the user's emotions and determine the priority of learning materials based on the estimated user emotions. For example, if the user is feeling stressed, the providing unit can cause the generation AI to start learning from simple materials. Furthermore, if the user is concentrating, the providing unit can also cause the generation AI to prioritize learning from complex materials. Furthermore, if the user is tired, the providing unit can also prioritize materials that the generation AI can learn in a short time. This enables efficient learning by determining the priority of learning materials according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, an AI. For example, the providing unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0069] When learning materials, the providing unit can prioritize learning highly relevant materials by taking into account the geographical location information of the company. For example, the providing unit can prioritize learning materials related to the company's location. The providing unit can also cause the generation AI to learn region-specific materials based on the geographical location information of the company. Furthermore, the providing unit can cause the generation AI to select and learn optimal materials by taking into account the geographical location information of the company. This allows highly relevant materials to be prioritized by taking into account the geographical location information of the company. Examples of geographical location information of the company include, but are not limited to, countries, regions, cities, etc. Some or all of the above-mentioned processing in the providing unit can be performed using AI, or can be performed without using AI. For example, the providing unit can input the geographical location information of the company into the generation AI and cause the generation AI to select highly relevant materials.

[0070] When learning the materials, the providing unit can analyze the company's social media activities and learn related materials. For example, the providing unit analyzes the company's social media posts, and the generation AI learns related materials. The providing unit can also select the most appropriate materials from the company's social media activities and have the generation AI learn from them. Furthermore, the providing unit can also have the generation AI prioritize learning related materials based on the company's social media activities. This allows the generation AI to prioritize learning related materials by analyzing the company's social media activities. Examples of the company's social media activities include, but are not limited to, post content, follower reactions, and engagement rates. Some or all of the above-mentioned processing in the providing unit can be performed using AI, or can be performed without using AI. For example, the providing unit can input data on the company's social media activities into the generation AI and have the generation AI learn related materials.

[0071] The provision unit can customize the learning method by reflecting the company's past feedback when studying the materials. For example, the provision unit causes the generation AI to adjust the learning method based on the company's past feedback. The provision unit can also cause the generation AI to select the optimal learning method by reflecting the company's past feedback. Furthermore, the provision unit can cause the generation AI to customize the learning method by taking the company's past feedback into consideration. This allows the optimal learning method to be selected by reflecting the company's past feedback. Examples of the company's past feedback include, but are not limited to, user reviews, survey results, and customer support records. Some or all of the above-described processing in the provision unit may be performed using AI, or may be performed without using AI. For example, the provision unit can input the company's past feedback into the generation AI and cause the generation AI to customize the learning method.

[0072] The operation unit can estimate the user's emotions and adjust the material generation method based on the estimated user emotions. For example, when the user is relaxed, the operation unit causes the generation AI to generate detailed materials. Furthermore, when the user is in a hurry, the operation unit can also cause the generation AI to generate concise materials. Furthermore, when the user is excited, the operation unit can also cause the generation AI to generate visually appealing materials. This enables efficient material generation by adjusting the material generation method according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the operation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the operation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the material generation method.

[0073] The operating unit can adjust the level of detail of the generated material based on the importance of the material when generating the material. For example, in the case of important material, the operating unit causes the generation AI to generate material with detailed content. In addition, in the case of less important material, the operating unit can cause the generation AI to generate material with concise content. Furthermore, the operating unit can cause the generation AI to select an optimal level of detail depending on the importance of the material and generate the material. This enables efficient material generation by adjusting the level of detail of the generated material depending on the importance of the material. Examples of the importance of the material include, but are not limited to, project priorities, management instructions, and customer requests. Some or all of the above-mentioned processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input material importance data into the generation AI and cause the generation AI to adjust the level of detail of the generated material.

[0074] When generating materials, the operating unit can apply different generation algorithms depending on the category of the materials. For example, in the case of technical materials, the operating unit causes the generation AI to apply an algorithm specialized for technical content. Furthermore, in the case of marketing materials, the operating unit can cause the generation AI to apply an algorithm specialized for marketing. Furthermore, the operating unit can cause the generation AI to select an optimal generation algorithm depending on the category of the materials and generate the materials. This enables efficient material generation by applying an optimal generation algorithm depending on the category of the materials. Examples of material categories include, but are not limited to, technical documents, marketing materials, financial reports, etc. Some or all of the above-mentioned processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input material category data into the generation AI and cause the generation AI to apply a generation algorithm.

[0075] When generating materials, the operating unit can improve the accuracy of generation by referring to the user's past generation results. For example, the operating unit analyzes the user's past generation results, and the generation AI generates optimal materials. The operating unit can also improve the accuracy of generation by referring to the user's past generation results. Furthermore, the operating unit can select the optimal generation method for the generation AI based on the user's past generation results. This improves the accuracy of generation by referring to the user's past generation results. The user's past generation results include, for example, past project materials, review results, feedback, etc., but are not limited to these examples. Some or all of the above-mentioned processing in the operating unit may be performed using AI, for example, or may be performed without using AI. For example, the operating unit can input the user's past generation result data into the generation AI and cause the generation AI to improve the accuracy of generation.

[0076] The operation unit can estimate the user's emotions and adjust the length of the generated materials based on the estimated user emotions. For example, if the user is in a hurry, the operation unit causes the generation AI to generate short, concise materials. Furthermore, if the user is relaxed, the operation unit can cause the generation AI to generate longer materials with detailed explanations. Furthermore, if the user is excited, the operation unit can cause the generation AI to generate materials with visually stimulating effects. This enables efficient material generation by adjusting the length of the materials according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the operation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the operation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the length of the materials.

[0077] The operating unit can determine the generation priority based on the submission date of the materials when generating the materials. For example, the operating unit prioritizes the generation of materials with an upcoming deadline. The operating unit can also postpone materials with a more distant submission date. Furthermore, the operating unit can cause the generation AI to select the optimal priority based on the submission date of the materials and generate the materials. This enables efficient material generation by determining the generation priority based on the submission date of the materials. The submission date of the materials includes, but is not limited to, project deadlines, customer requests, internal schedules, etc. Some or all of the above-mentioned processing in the operating unit can be performed using, for example, AI, or can be performed without using AI. For example, the operating unit can input data on the submission date of the materials to the generation AI and cause the generation AI to determine the generation priority.

[0078] The operating unit can adjust the order of generation based on the relevance of the materials when generating the materials. For example, the operating unit can prioritize generating highly relevant materials. The operating unit can also postpone generating less relevant materials. Furthermore, the operating unit can cause the generation AI to select an optimal order based on the relevance of the materials and generate the materials. This enables efficient material generation by adjusting the order of generation based on the relevance of the materials. Examples of the relevance of the materials include, but are not limited to, a common theme, overlapping content, and commonality of purpose. Some or all of the above-described processing in the operating unit can be performed using, or without, AI. For example, the operating unit can input relevance data of the materials into the generation AI and cause the generation AI to adjust the order of generation.

[0079] The operating unit can adjust the use of technical terminology in generating materials according to the user's level of expertise. For example, if the user has technical expertise, the operating unit can cause the generation AI to generate materials that use a lot of technical terminology. Alternatively, if the user does not have technical expertise, the operating unit can cause the generation AI to generate materials that avoid technical terminology. Furthermore, the operating unit can cause the generation AI to select the most appropriate technical terminology to be used according to the user's level of expertise and generate materials. This enables appropriate materials to be generated by adjusting the use of technical terminology according to the user's level of expertise. Examples of the user's level of expertise include, but are not limited to, work experience, educational background, and past project experience. Some or all of the above-described processing by the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terminology.

[0080] The subscription unit can estimate the user's emotions and adjust the subscription content based on the estimated user emotions. For example, if the user is stressed, the generation AI can provide simple subscription content. Furthermore, if the user is relaxed, the subscription unit can provide detailed subscription content. Furthermore, if the user is excited, the generation AI can provide visually appealing subscription content. This enables appropriate service provision by adjusting the subscription content according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the subscription unit can be performed using, for example, AI, or without AI. For example, the subscription unit can input the user's emotion data into the generation AI and have the generation AI adjust the subscription content.

[0081] When providing a subscription, the subscription unit can analyze the company's past usage history and select the optimal service. For example, the subscription unit can have a generation AI propose the optimal subscription service based on the company's past usage history. The subscription unit can also analyze the company's past usage history and have the generation AI select the optimal service content. Furthermore, the subscription unit can have the generation AI provide the optimal subscription content by referring to the company's past usage history. This allows the optimal service to be provided by analyzing the company's past usage history. The company's past usage history includes, for example, past service usage status, contract history, feedback, etc., but is not limited to these examples. Some or all of the above-described processing in the subscription unit may be performed using, or without, AI. For example, the subscription unit can input the company's past usage history data into the generation AI and have the generation AI select the optimal service.

[0082] The subscription department can customize the service content based on the company's current needs when providing a subscription. For example, the subscription department can have the generation AI provide the optimal subscription content based on the company's current needs. The subscription department can also have the generation AI customize the service content according to the company's current needs. Furthermore, the subscription department can also have the generation AI select the optimal service content taking the company's current needs into consideration. This enables appropriate service provision by customizing the service content based on the company's current needs. The company's current needs include, but are not limited to, current project requirements, management policies, and customer requests. Some or all of the above-described processing in the subscription department can be performed using, or without, AI. For example, the subscription department can input the company's current needs data into the generation AI and have the generation AI customize the service content.

[0083] The subscription unit can improve the service content by reflecting the company's feedback when providing a subscription. For example, the subscription unit allows the generation AI to improve the service content based on the company's feedback. The subscription unit can also allow the generation AI to select the optimal service content by reflecting the company's feedback. Furthermore, the subscription unit can also allow the generation AI to customize the service content by taking the company's feedback into consideration. This allows the service content to be improved by reflecting the company's feedback. Examples of company feedback include, but are not limited to, user reviews, survey results, and customer support records. Some or all of the above-described processing in the subscription unit may be performed using, or without, AI. For example, the subscription unit can input company feedback data into the generation AI and have the generation AI improve the service content.

[0084] The subscription unit can estimate the user's emotions and determine the priority of subscriptions based on the estimated user emotions. For example, if the user is feeling stressed, the subscription unit can cause the generation AI to prioritize relaxing content. Furthermore, if the user is concentrating, the subscription unit can cause the generation AI to prioritize content useful for learning or work. Furthermore, if the user is tired, the subscription unit can cause the generation AI to prioritize refreshing content. This enables appropriate service provision by determining subscription priorities according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the subscription unit can be performed using, for example, an AI. For example, the subscription unit can input the user's emotion data into the generation AI and have the generation AI determine the subscription priorities.

[0085] When providing a subscription, the subscription unit can select the optimal service by taking into account the company's geographic location information. For example, the subscription unit can prioritize services related to the company's location. The subscription unit can also cause the generation AI to provide region-specific services based on the company's geographic location information. Furthermore, the subscription unit can cause the generation AI to select the optimal service by taking into account the company's geographic location information. This allows the optimal service to be provided by taking into account the company's geographic location information. Examples of the company's geographic location information include, but are not limited to, countries, regions, and cities. Some or all of the above-described processing in the subscription unit may be performed using AI, or may be performed without using AI. For example, the subscription unit can input the company's geographic location information data into the generation AI and cause the generation AI to select the optimal service.

[0086] When providing a subscription, the subscription unit can analyze the company's social media activity and suggest service content. For example, the subscription unit analyzes the company's social media posts, and the generation AI suggests related services. The subscription unit can also select the most appropriate service content based on the company's social media activity. Furthermore, the subscription unit can prioritize related services based on the company's social media activity. This allows related services to be provided by analyzing the company's social media activity. Examples of the company's social media activity include, but are not limited to, post content, follower reactions, and engagement rates. Some or all of the above-mentioned processing in the subscription unit may be performed using AI, or may be performed without AI. For example, the subscription unit can input the company's social media activity data into the generation AI and have the generation AI suggest service content.

[0087] When providing a subscription, the subscription unit can customize the service content by reflecting the company's past feedback. For example, the subscription unit allows the generation AI to adjust the service content based on the company's past feedback. The subscription unit can also allow the generation AI to select optimal service content by reflecting the company's past feedback. Furthermore, the subscription unit can also allow the generation AI to customize the service content by taking the company's past feedback into consideration. This allows optimal services to be provided by reflecting the company's past feedback. Examples of the company's past feedback include, but are not limited to, user reviews, survey results, and customer support records. Some or all of the above-described processing in the subscription unit may be performed using, or without, AI. For example, the subscription unit can input the company's past feedback data into the generation AI and have the generation AI customize the service content. === Hard Collateral 1-1 === Each of the multiple elements, including the providing unit, operating unit, and subscription unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the providing unit is realized by the control unit 46A of the smart device 14, and uses materials previously created by a company as input data, and the generation AI learns the format and content of the materials. The operating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and when a user inputs the theme of the material and necessary information, the generation AI automatically generates optimal materials. The subscription unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides a learning environment for the material generation AI in a subscription format, providing support for a material generation model optimized for each company. === Hard Collateral 1-2 === Each of the multiple elements, including the providing unit, operating unit, and subscription unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the providing unit is realized by the control unit 46A of the smart glasses 214, and uses materials previously created by a company as input data, and the generation AI learns the format and content of the materials. The operating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and when a user inputs the theme of the material and necessary information, the generation AI automatically generates optimal materials. The subscription unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides a learning environment for the material generation AI in a subscription format and provides support for a material generation model optimized for each company. === Hard Collateral 1-3 === Each of the multiple elements, including the providing unit, operating unit, and subscription unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the providing unit is realized by the control unit 46A of the headset-type terminal 314, and uses materials previously created by a company as input data, and the generation AI learns the format and content of the materials. Furthermore, the operating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and when a user inputs the theme of the material and necessary information, the generation AI automatically generates optimal materials. The subscription unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides a learning environment for the material generation AI in a subscription format and provides support for a material generation model optimized for each company. === Hard Collateral 1-4 === Each of the multiple elements, including the providing unit, operating unit, and subscription unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the providing unit is realized by the control unit 46A of the robot 414, and uses materials previously created by a company as input data, and the generation AI learns the format and content of the materials. Furthermore, the operating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and when a user inputs the theme of the material and necessary information, the generation AI automatically generates optimal materials. The subscription unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides a learning environment for the material generation AI in a subscription format, providing support for a material generation model optimized for each company.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The providing unit can analyze the company's past document creation history and select the optimal learning method. For example, the format of documents created by the company in the past can be analyzed, and the generation AI can learn based on that format. The providing unit can also identify frequently used templates from the company's past document creation history and have the generation AI prioritize learning from those templates. The providing unit can also analyze the company's past document creation history and select the most efficient learning method for the generation AI. In this way, an efficient learning method can be selected by analyzing the company's past document creation history. Optimal learning methods include, but are not limited to, supervised learning, unsupervised learning, and reinforcement learning. Some or all of the above-described processing in the providing unit can be performed using, for example, AI, or without AI. For example, the providing unit can input the company's past document creation history into the generation AI and have the generation AI select the optimal learning method.

[0090] When generating documents, the operating unit can adjust the level of detail of the generated documents based on the importance of the documents. For example, in the case of important documents, the generation AI can generate documents with detailed content. In addition, in the case of documents with low importance, the operating unit can also generate documents with concise content. Furthermore, the operating unit can generate documents by having the generation AI select an optimal level of detail depending on the importance of the documents. This enables efficient document generation by adjusting the level of detail of the generated documents based on the importance of the documents. Examples of the importance of documents include, but are not limited to, project priorities, management instructions, and customer requests. Some or all of the above-described processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input data on the importance of the documents into the generation AI and cause the generation AI to adjust the level of detail of the generated documents.

[0091] When learning materials, the providing unit can filter them based on the company's current projects and areas of interest. For example, materials related to the company's current projects can be prioritized for learning. The providing unit can also filter and learn materials related to the generation AI based on the company's areas of interest. Furthermore, the providing unit can also select and learn optimal materials based on the company's current projects and areas of interest. This allows related materials to be learned preferentially based on the company's current projects and areas of interest. Examples of the company's current projects and areas of interest include, but are not limited to, research and development projects and marketing campaigns. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input data on the company's current projects and areas of interest into the generation AI and have the generation AI perform filtering.

[0092] When generating materials, the operating unit can apply different generation algorithms depending on the category of the materials. For example, in the case of technical materials, the generation AI can apply an algorithm specialized for technical content. In addition, in the case of marketing materials, the operating unit can also cause the generation AI to apply an algorithm specialized for marketing. Furthermore, the operating unit can cause the generation AI to select an optimal generation algorithm depending on the category of the materials and generate the materials. This enables efficient material generation by applying an optimal generation algorithm depending on the category of the materials. Examples of material categories include, but are not limited to, technical documents, marketing materials, financial reports, etc. Some or all of the above-mentioned processing in the operating unit can be performed using AI, for example, or without AI. For example, the operating unit can input material category data into the generation AI and cause the generation AI to apply a generation algorithm.

[0093] When studying the materials, the providing unit can select the optimal learning means depending on the company's input method. For example, if the company uses voice input, the generation AI can learn the voice data. Furthermore, if the company uses text input, the providing unit can also have the generation AI learn the text data. Furthermore, if the company uses image input, the providing unit can also have the generation AI learn the image data. This enables efficient learning by selecting the optimal learning means depending on the company's input method. Examples of company input methods include, but are not limited to, voice input, text input, and image input. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input the company's input data into the generation AI and have the generation AI select the optimal learning means.

[0094] The providing unit can estimate the user's emotions and adjust the timing of studying the materials based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI temporarily suspends studying the materials and resumes when the user is able to relax. The providing unit can also have the generation AI continuously study the materials when the user is concentrating, thereby efficiently building a model. Furthermore, if the user is tired, the generation AI can reduce the frequency of study, thereby reducing the user's burden. This enables efficient study by adjusting the study timing according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without AI. For example, the providing unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0095] The operation unit can estimate the user's emotions and adjust the method for generating materials based on the estimated user emotions. For example, if the user is relaxed, the generation AI can generate detailed materials. Furthermore, if the user is in a hurry, the operation unit can also generate concise materials. Furthermore, if the user is excited, the operation unit can also generate visually appealing materials. This enables efficient material generation by adjusting the method for generating materials according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the operation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the operation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the method for generating materials.

[0096] The providing unit can estimate the user's emotions and prioritize the learning materials based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can start learning from simple materials. The providing unit can also cause the generation AI to prioritize learning from complex materials if the user is concentrating. Furthermore, if the user is tired, the providing unit can prioritize materials that the generation AI can learn in a short time. This enables efficient learning by prioritizing learning materials according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit can be performed using, for example, an AI. For example, the providing unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0097] The operation unit can estimate the user's emotions and adjust the length of the generated materials based on the estimated user emotions. For example, if the user is in a hurry, the generation AI can generate short, concise materials. Furthermore, if the user is relaxed, the operation unit can generate longer materials with detailed explanations. Furthermore, if the user is excited, the operation unit can generate materials with visually stimulating effects. This allows for efficient material generation by adjusting the length of the materials according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the operation unit can be performed using, for example, an AI, or without an AI. For example, the operation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the length of the materials.

[0098] The subscription unit can estimate the user's emotions and adjust the subscription content based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can provide simple subscription content. Furthermore, if the user is relaxed, the subscription unit can provide detailed subscription content. Furthermore, if the user is excited, the subscription unit can provide visually appealing subscription content. This enables appropriate service provision by adjusting the subscription content according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the subscription unit can be performed using, for example, AI, or without AI. For example, the subscription unit can input the user's emotion data into the generation AI and have the generation AI adjust the subscription content.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The provision department uses documents previously created by the company as input data, and the generation AI learns the format and content of those documents. For example, the provision department uses reports, presentation materials, technical documents, etc. previously created by the company as input data. The provision department can also provide datasets, hardware, software tools, etc. for the generation AI to learn the format and content of those documents. Step 2: In the operating unit, the user inputs the document theme and necessary information, and the generation AI automatically generates the optimal document. For example, when the user inputs information such as a project outline, technical specifications, and market analysis, the generation AI generates the document based on that information. In addition, the operating unit uses a document generation model optimized for each company, so the generation AI can generate documents that meet the company's needs. Step 3: The Subscription Department provides a learning environment for the document generation AI on a subscription basis and provides support for document generation models optimized for each company. For example, if a company introduces a new document format, the Subscription Department provides consulting services to train that format.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0103] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0104] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0107] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0108] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0109] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0111] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0112] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0113] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0114] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0156] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0157] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0158] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0162] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0163] 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.

[0164] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0165] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0166] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0167] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0169] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0170] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0171] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0172] [Explanation of symbols]

[0173] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A system comprising: a provision unit that provides a learning environment for a material generation AI; an operation unit that runs the material generation model learned by the provision unit on a local PC; and a subscription unit that provides the learning environment for the material generation AI in a subscription format.

2. The system described in claim 1 uses documents previously created by a company as input data, and the generation AI learns the format and content of those documents.

3. The system described in claim 1, characterized in that when a user inputs the theme of the material and necessary information, the generation AI automatically generates the material.

4. 2. The system according to claim 1, wherein when a company introduces a new document format, a service is provided for learning the format.

5. 2. The system according to claim 1, wherein the system estimates a user's emotions and adjusts the timing of learning the material based on the estimated user's emotions.

6. The providing unit Analyze the company's past document creation history and select the most appropriate learning method 2. The system of claim 1.

7. The providing unit When studying materials, filter based on the company's current projects and areas of interest 2. The system of claim 1.

8. The providing unit When studying materials, choose the most appropriate learning method according to the company's input method 2. The system of claim 1.

Images