system

Abstract

The system according to this embodiment aims to streamline the generation and rights check of images used in proposals and meeting materials. [Solution] The system according to the embodiment comprises an image generation unit, a rights checking unit, an image embedding unit, and a process management unit. The image generation unit generates images to be used in proposals and meeting materials. The rights checking unit checks for rights infringement of the images generated by the image generation unit. The image embedding unit embeds the images checked by the rights checking unit into proposals and meeting materials. The process management unit manages the entire process of creating proposals and meeting materials.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it takes a great deal of time and cost to select and check the rights of images used in proposal documents and meeting materials.

[0005] The system according to the embodiment aims to improve the efficiency of generating and checking the rights of images used in proposal documents and meeting materials.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an image generation unit, a rights checking unit, an image embedding unit, and a process management unit. The image generation unit generates images to be used in proposals and meeting materials. The rights checking unit checks for rights infringement in the images generated by the image generation unit. The image embedding unit incorporates the images checked by the rights checking unit into proposals and meeting materials. The process management unit manages the entire process of creating proposals and meeting materials. [Effects of the Invention]

[0007] The system according to this embodiment can streamline the generation of images used in proposals and meeting materials, as well as the checking of rights. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages 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), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The image generation system according to an embodiment of the present invention is a system that achieves an annual cost reduction of 50 million yen by limiting the images used in proposals and meeting materials to those generated by an image generation AI. This image generation system establishes a rule that limits the images used in proposals and meeting materials to those generated by an image generation AI. Next, a multimodal AI is used to check for copyright infringement of the generated images. This significantly reduces the time required to create proposals and meeting materials, thereby achieving cost reductions. Furthermore, by introducing AI tools to streamline the revision and supervisor review processes, further cost reductions can be expected. For example, by establishing a rule that limits the images used in proposals and meeting materials to those generated by an image generation AI, the work of finding appropriate images from internal materials or external copyright-free sites becomes unnecessary, significantly reducing work time. Specifically, while normal image searching takes an average of 3 minutes per page, using an image generation AI can reduce this to an average of 1 minute per page. This is expected to reduce 15,000 hours annually. Next, a multimodal AI is used to check for copyright infringement of the generated images. This allows for automatic checking of whether the generated images infringe on copyright. Specifically, the multimodal AI checks the similarity and reliance of generated images, outputting them only if there are no problems. This reduces the risk of copyright infringement. Furthermore, AI tools will be introduced to streamline the entire process of creating proposals and meeting materials. For example, by introducing AI tools to streamline the revision and supervisor review processes, further cost reductions can be expected. Specifically, revisions usually take an average of 3 minutes per page, but by using AI, this can be reduced to an average of 1 minute per page. This is expected to save 1,800 hours per year. Meeting time for supervisor reviews can also be reduced. Supervisors record their comments via voice, and the AI ​​automatically transcribes and summarizes them, reducing a monthly 30-minute meeting to about 10 minutes. This is expected to save 12,000 hours per year. In this way, by using image generation AI, the time required to create proposals and meeting materials will be significantly reduced, resulting in an annual cost reduction of 50 million yen.Furthermore, the risk of copyright infringement is reduced, and by accumulating internal knowledge, it can be used as material for proposals to corporate clients. As a result, the image generation system can significantly reduce the time required to create proposals and meeting materials, and achieve annual cost savings of 50 million yen.

[0029] The image generation system according to this embodiment comprises an image generation unit, a rights checking unit, an image embedding unit, and a process management unit. The image generation unit generates images to be used in proposals and meeting materials. The image generation unit generates images using, for example, a generation AI. The generation AI is a text generation AI (e.g., LLM) or an image generation AI, and the generation AI generates images based on prompts. For example, the image generation unit inputs the prompt "Generate an image of a business meeting" to the generation AI and obtains the generated image. The image generation unit can also input the prompt "Generate a graph suitable for a proposal" to the generation AI and obtain the generated graph. Furthermore, the image generation unit can input the prompt "Generate an illustration suitable for meeting materials" to the generation AI and obtain the generated illustration. The rights checking unit checks for copyright infringement of the images generated by the image generation unit. The rights checking unit checks for similarity and reliance of the generated images using, for example, a multimodal AI. The multimodal AI analyzes both images and text to confirm whether the generated images infringe copyright. For example, the rights check unit inputs the generated images into a multimodal AI to check for similarity and reliance. The rights check unit can also analyze the metadata of the generated images to verify copyright information. Furthermore, the rights check unit can refer to a database of past case precedents to assess the infringement risk of the generated images. The image embedding unit incorporates the images checked by the rights check unit into proposals and meeting materials. For example, the image embedding unit places the generated images in specific locations within the proposal or meeting materials. The image embedding unit adjusts the size and position of images to maintain overall page balance. For example, the image embedding unit automatically adjusts image size to maintain overall page balance. It can also automatically adjust image position to improve visibility. Furthermore, the image embedding unit can automatically generate image captions to clearly communicate the content of the proposal or meeting materials. The process management unit manages the entire process of creating proposals and meeting materials. For example, the process management unit provides real-time updates on the progress of the work.The process management department visualizes the progress of work and shares it with team members. For example, the process management department displays the progress of work as graphs and charts to improve visibility. The process management department can also link with project management tools to update task progress in real time. Furthermore, the process management department can estimate the user's emotions and adjust process priorities based on the estimated user emotions. As a result, the image generation system according to this embodiment can significantly reduce the time required to create proposals and meeting materials, thereby achieving cost reductions.

[0030] The image generation unit generates images for use in proposals and meeting materials. The image generation unit generates images using, for example, a generation AI. This generation AI could be a text generation AI (e.g., LLM) or an image generation AI, and it generates images based on prompts. Specifically, the image generation unit inputs the prompt "Generate an image of a business meeting" to the generation AI and retrieves the generated image. This prompt can include details such as the layout of the meeting room, the attire of the participants, and the progress of the meeting to concretely depict the business meeting scene. Based on these details, the generation AI generates a realistic image of a business meeting. The image generation unit can also input the prompt "Generate a graph suitable for a proposal" to the generation AI and retrieve the generated graph. In this case, the prompt includes the type of graph (e.g., bar graph, line graph, pie chart), the range and units of the data to display, and color specifications. The generation AI generates a visually easy-to-understand graph according to these instructions. Furthermore, the image generation unit can also input the prompt "Generate an illustration suitable for meeting materials" to the generation AI and retrieve the generated illustration. This prompt includes details such as the illustration's theme, style, color scheme, and specific elements (e.g., people, objects, background). Based on these instructions, the generating AI creates illustrations suitable for meeting materials. This allows the image generation unit to quickly produce a variety of images to meet user needs, improving the quality of proposals and meeting materials.

[0031] The rights checking unit checks for copyright infringement in images generated by the image generation unit. For example, the rights checking unit checks the similarity and reliance of images generated using a multimodal AI. The multimodal AI analyzes both images and text to confirm whether the generated images infringe copyright. Specifically, the rights checking unit inputs the generated images into the multimodal AI and checks for similarity and reliance. This AI compares the generated images with existing image databases to detect if there are images with a high degree of similarity. It also compares them with text databases to confirm whether the generated images rely on specific text or concepts. Furthermore, the rights checking unit can also analyze the metadata of the generated images to verify copyright information. The metadata includes the date and time the image was generated, the version of the generating AI, and the content of the prompts used, and the risk of copyright infringement is assessed based on this information. The rights checking unit can also refer to a database of past case precedents to assess the risk of copyright infringement of the generated images. The case precedent database contains past court cases and judgments regarding copyright infringement, and the risk of the generated images is assessed based on this. This allows the rights checking unit to verify that the generated images are legally sound, ensuring they can be used with confidence.

[0032] The image embedding unit incorporates images checked by the rights check unit into proposals and meeting materials. For example, the image embedding unit places the generated images in specific locations within the proposal or meeting materials. Specifically, the image embedding unit adjusts the size and position of images to maintain overall page balance. For instance, it automatically adjusts image size to maintain overall page balance. It can also automatically adjust image position to improve visibility. Furthermore, the image embedding unit can automatically generate image captions to clearly communicate the content of proposals and meeting materials. Captions concisely explain the content and intent of the image and are automatically generated using AI. For example, the image embedding unit analyzes the content of the generated image and generates an appropriate caption based on that content. This allows the image embedding unit to enhance the visual appeal of proposals and meeting materials and effectively communicate information. Additionally, the image embedding unit allows for manual adjustment of image placement and size, enabling customization to meet user needs. This allows the image embedding unit to improve the quality of proposals and meeting materials and support effective presentations.

[0033] The Process Management Department manages the entire process of creating proposals and meeting materials. For example, the Process Management Department provides real-time updates on work progress. Specifically, it visualizes and shares work progress with team members. For instance, it displays work progress as graphs and charts to improve visibility. It can also integrate with project management tools to update task progress in real time. This allows the entire team to understand the current progress and work efficiently. Furthermore, the Process Management Department can estimate user emotions and adjust process priorities based on these estimates. For example, it analyzes user stress levels and satisfaction levels, and makes adjustments to reduce the workload if stress levels are high. The Process Management Department also automatically sends reminders based on work progress to support meeting deadlines. This allows the Process Management Department to efficiently manage the proposal and meeting material creation process and prevent delays. Additionally, the Process Management Department can analyze past project data to identify areas for improvement to enhance work efficiency. This will allow the process management department to significantly reduce the time spent creating proposals and meeting materials, thereby achieving cost savings.

[0034] The revision response department handles revisions. For example, the revision response department revises proposals and meeting materials. The revision response department manages the revision process and verifies the revisions. For example, the revision response department identifies revisions in proposals and verifies the revisions. It can also identify revisions in meeting materials and verify the revisions. Furthermore, the revision response department can automatically reflect the revisions and update proposals and meeting materials. This streamlines the revision process and is expected to lead to further cost reductions. Some or all of the above processes in the revision response department may be performed using AI, for example, or not. For example, the revision response department can input the revision locations into AI and have AI verify the revisions.

[0035] The Review Management Department streamlines the supervisor review process. For example, the Review Management Department manages the points raised in supervisor reviews and verifies the review content. The Review Management Department allows supervisors to record their points of concern via voice, and AI automatically transcribes and summarizes them. For example, the Review Management Department inputs the supervisor's voice data into the AI ​​and has the AI ​​perform the transcription and summarization. The Review Management Department also reduces the meeting time for supervisor reviews. For example, the Review Management Department can reduce a monthly 30-minute meeting to about 10 minutes. This streamlines the supervisor review process and is expected to lead to further cost reductions. Some or all of the above processes in the Review Management Department may be performed using AI, or not. For example, the Review Management Department can input the supervisor's voice data into the AI ​​and have the AI ​​perform the transcription and summarization.

[0036] The image generation unit generates images using a generation AI. The image generation unit generates images by inputting prompts to the generation AI, for example. The generation AI can be a text generation AI (e.g., LLM) or an image generation AI, and the generation AI generates images based on the prompts. For example, the image generation unit inputs the prompt "Generate an image of a business meeting" to the generation AI and retrieves the generated image. The image generation unit can also input the prompt "Generate a graph suitable for a proposal" to the generation AI and retrieve the generated graph. Furthermore, the image generation unit can input the prompt "Generate an illustration suitable for meeting materials" to the generation AI and retrieve the generated illustration. This improves the efficiency of image generation by using a generation AI. Some or all of the above-described processes in the image generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the image generation unit inputs prompts to the generation AI and generates images.

[0037] The rights checking unit checks the similarity and reliance of images generated using a multimodal AI. For example, the rights checking unit inputs the generated image into the multimodal AI and checks its similarity and reliance. The multimodal AI analyzes both the image and text to confirm whether the generated image infringes copyright. For example, the rights checking unit inputs the generated image into the multimodal AI and checks its similarity and reliance. The rights checking unit can also analyze the metadata of the generated image to confirm copyright information. Furthermore, the rights checking unit can refer to a database of past case precedents to assess the risk of copyright infringement of the generated image. This reduces the risk of copyright infringement by using a multimodal AI. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or without AI. For example, the rights checking unit inputs the generated image into the multimodal AI and checks its similarity and reliance.

[0038] The image generation unit automatically selects the theme and color tone of the generated images according to the content of the proposal or meeting materials. For example, if the proposal is business-oriented, the image generation unit will select a professional color tone and design. If the meeting materials are creative, the image generation unit can also select a colorful and inspiring design. Furthermore, if the proposal is technical, the image generation unit can select a simple and technical design. This ensures that appropriate images are provided according to the content of the proposal or meeting materials. Some or all of the above processing in the image generation unit may be performed using, for example, a generation AI, or not. For example, the image generation unit can input the content of the proposal or meeting materials into a generation AI and have the generation AI select the image theme and color tone.

[0039] The image generation unit adds a function to the generated images that reflect the company's brand guidelines. For example, the image generation unit automatically generates images that reflect the company's logo and color palette. The image generation unit can also generate images that include text using the company's font style. Furthermore, the image generation unit can generate images that incorporate design elements based on the company's visual identity. This allows for the provision of images that comply with the company's brand guidelines. Some or all of the above processing in the image generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the image generation unit can input the company's brand guidelines into a generation AI and have the generation AI perform the image generation.

[0040] The image generation unit reflects the design patterns of the user's past proposals and meeting materials in the images it generates. For example, the image generation unit generates images that reflect the color tones and design elements the user has used in the past. The image generation unit can also generate images based on the layout patterns of the user's past proposals and meeting materials. Furthermore, the image generation unit can analyze the user's past design style and generate consistent images. This allows for the provision of consistent images based on the user's past design patterns. Some or all of the above processing in the image generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image generation unit can input the user's past design patterns into a generation AI and have the generation AI perform image generation.

[0041] The image generation unit incorporates the user's geographical background and cultural elements into the images it generates. For example, the image generation unit generates images that reflect geographical elements based on the user's location. The image generation unit can also generate images that incorporate design elements based on the user's cultural background. Furthermore, the image generation unit can generate images that use symbols or icons specific to the user's region. This allows the system to provide images that are tailored to the user's geographical background and cultural elements. Some or all of the above-described processes in the image generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image generation unit can input the user's geographical background and cultural elements into a generation AI and have the generation AI perform the image generation.

[0042] The rights checking unit adds a function to the rights infringement check of generated images that refers to a database of past case precedents. The rights checking unit evaluates the risk of the generated image based on past copyright infringement cases, for example. The rights checking unit can also refer to the case precedent database to check for the existence of similar cases. Furthermore, the rights checking unit can automatically evaluate the legal risk of the generated image based on the case precedent database. This allows for the evaluation of rights infringement risk by referring to the database of past case precedents. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or without AI. For example, the rights checking unit can input the generated image into the case precedent database and have AI perform the risk evaluation.

[0043] The rights checking unit adds a function to analyze the image metadata for checking the rights infringement of generated images. For example, the rights checking unit analyzes the metadata of the generated image and verifies the copyright information. The rights checking unit can also automatically check the source and rights information of the image based on the metadata. Furthermore, the rights checking unit can evaluate the rights infringement risk of the generated image through metadata analysis. This allows for the evaluation of rights infringement risk by analyzing the image metadata. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or without AI. For example, the rights checking unit can input the metadata of the generated image into AI and have the AI ​​perform the risk assessment.

[0044] The rights checking unit incorporates the user's industry-specific rights information into the rights infringement check of the generated images. For example, the rights checking unit performs rights checks based on copyright information specific to the user's industry. The rights checking unit can also refer to industry-specific rights information and assess the risks of the generated images. Furthermore, the rights checking unit can perform rights checks based on industry guidelines to minimize risks. This enables the provision of rights checks based on the user's industry-specific rights information. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or not using AI. For example, the rights checking unit can input industry-specific rights information into AI and have the AI ​​perform a risk assessment.

[0045] The rights checking unit refers to a rights information database that is updated in real time to check for rights infringement of the generated images. The rights checking unit performs rights checks based on copyright information that is updated in real time, for example. The rights checking unit can also refer to the latest rights information database and evaluate the risks of the generated images. Furthermore, the rights checking unit can automatically evaluate the legal risks of the generated images based on the real-time database. This allows the unit to provide checks based on the latest rights information by referring to a rights information database that is updated in real time. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or not using AI. For example, the rights checking unit can input a rights information database that is updated in real time into AI and have the AI ​​perform a risk assessment.

[0046] The image embedding unit adds a function to automatically generate context-appropriate captions when images are embedded in proposals or meeting materials. For example, the image embedding unit can automatically generate appropriate captions based on the content of the proposal. The image embedding unit can also automatically generate context-appropriate explanatory text for meeting materials. Furthermore, the image embedding unit can automatically generate relevant captions based on the content of the image. This allows for clearer communication of the content of proposals and meeting materials by automatically generating context-appropriate captions. Some or all of the above processing in the image embedding unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image embedding unit can input the content of an image into a generation AI and have the generation AI generate the caption.

[0047] The image embedding section adds a function to automatically adjust the overall balance of the page layout when embedding images. For example, the image embedding section automatically adjusts the size and position of images to maintain the overall balance of the page. The image embedding section can also optimize the placement of text and images to improve readability. Furthermore, the image embedding section can automatically adjust the placement of images while considering the overall design of the page layout. This allows for the provision of highly readable materials by automatically adjusting the overall balance of the page layout. Some or all of the above processing in the image embedding section may be performed using, for example, a generation AI, or not using a generation AI. For example, the image embedding section can input page layout information into a generation AI and have the generation AI perform the balance adjustment.

[0048] The image embedding unit incorporates the layout patterns of the user's past proposals and meeting materials when embedding images. For example, the image embedding unit adjusts the placement of images based on layout patterns previously used by the user. The image embedding unit can also provide image placement that reflects the design style of the user's past proposals and meeting materials. Furthermore, the image embedding unit can analyze the user's past layout patterns and provide consistent image placement. This allows for consistent image placement based on the user's past layout patterns. Some or all of the above processing in the image embedding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image embedding unit can input the user's past layout patterns into a generative AI and have the generative AI perform the placement adjustments.

[0049] The image embedding unit selects the optimal display method when embedding an image, taking into account the user's device information. For example, if the user is using a smartphone, the image embedding unit provides a display method that matches the screen size. If the user is using a tablet, the image embedding unit can also provide a display method optimized for a larger screen. Furthermore, if the user is using a desktop, the image embedding unit can provide a display method that supports high resolution. This allows the system to provide the optimal display method based on the user's device information. Some or all of the above processing in the image embedding unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image embedding unit can input the user's device information into a generation AI and have the generation AI select the display method.

[0050] The Process Management Department will add a function to link the entire process of creating proposals and meeting materials with the project management tool. For example, the Process Management Department will link with the project management tool to update the progress of tasks in real time. The Process Management Department can also integrate the process of creating proposals and meeting materials with the project management tool and manage it efficiently. Furthermore, the Process Management Department can facilitate communication among team members through the project management tool. In this way, linking with the project management tool will improve the efficiency of the creation process. Some or all of the above processes in the Process Management Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Process Management Department can input information from the project management tool into the generative AI and have the generative AI execute the linking function.

[0051] The process management department will add a function to notify the progress of work in real time. For example, the process management department will notify the progress of work in real time and share it with team members. The process management department can also customize the progress notifications and prioritize notifications for the progress of important tasks. In addition, the process management department can detect work delays early and take countermeasures through real-time notifications. This means that by notifying progress in real time, work delays can be detected early and countermeasures can be taken. Some or all of the above processes in the process management department may be performed using, for example, a generative AI, or not using a generative AI. For example, the process management department can input progress data into a generative AI and have the generative AI execute the notification function.

[0052] The process management unit optimizes the entire process of creating proposals and meeting materials by referring to the user's past work history. For example, the process management unit proposes an efficient work process based on the user's past work history. The process management unit can also analyze past work history and propose the optimal task sequence. Furthermore, the process management unit can learn the user's work patterns and automatically set the optimal work process. This allows it to provide an optimal work process based on the user's past work history. Some or all of the above processes in the process management unit may be performed using, for example, generative AI, or not using generative AI. For example, the process management unit can input the user's past work history into a generative AI and have the generative AI perform the optimization.

[0053] The process management unit will add a function to automatically generate work plans by reflecting the user's schedule information. For example, the process management unit will automatically generate an optimal work plan based on the user's schedule information. The process management unit can also refer to the schedule information and automatically set task priorities. Furthermore, the process management unit can flexibly adjust the work plan to match the user's schedule. This will enable the provision of an optimal work plan based on the user's schedule information. Some or all of the above processing in the process management unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the process management unit can input the user's schedule information into the generation AI and have the generation AI perform the automatic generation of a work plan.

[0054] The correction response unit adds a function to suggest the optimal correction method by referring to past correction history when making corrections. For example, the correction response unit suggests the optimal correction method based on past correction history. The correction response unit can also refer to the correction history and present similar correction cases. Furthermore, the correction response unit can analyze past correction patterns and suggest efficient correction methods. This enables the provision of the optimal correction method based on past correction history. Some or all of the above processing in the correction response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction response unit can input past correction history into a generation AI and have the generation AI execute the correction method suggestion.

[0055] The correction response unit proposes the optimal correction method when performing corrections, taking into account the user's device information. For example, if the user is using a smartphone, the correction response unit proposes a correction method that matches the screen size. If the user is using a tablet, the correction response unit can also propose a correction method optimized for a larger screen. Furthermore, if the user is using a desktop, the correction response unit can propose a correction method that supports high resolution. This allows the unit to provide the optimal correction method based on the user's device information. Some or all of the above processing in the correction response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction response unit can input the user's device information into a generation AI and have the generation AI execute the correction method proposal.

[0056] The review management unit will add a function to provide optimal feedback by referring to past review history. For example, the review management unit will provide optimal feedback based on past review history. The review management unit can also refer to the review history and suggest similar review cases. Furthermore, the review management unit can analyze past review history and propose efficient feedback methods. This will enable the provision of optimal feedback based on past review history. Some or all of the above processes in the review management unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the review management unit can input past review history into a generative AI and have the generative AI propose feedback methods.

[0057] The review management unit will add a function to optimize review timing by reflecting the user's schedule information. For example, the review management unit will automatically generate the optimal review timing based on the user's schedule information. The review management unit can also refer to the schedule information and automatically set review priorities. Furthermore, the review management unit can flexibly adjust the review timing to match the user's schedule. This will enable the provision of optimal review timing based on the user's schedule information. Some or all of the above processing in the review management unit may be performed using, for example, a generation AI, or without a generation AI. For example, the review management unit can input the user's schedule information into a generation AI and have the generation AI perform the timing optimization.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] The image generation unit can incorporate the design patterns of the user's past proposals and meeting materials into the images it generates. For example, it can generate images that reflect the color schemes and design elements the user has used in the past. It can also generate images based on the layout patterns of the user's past proposals and meeting materials. Furthermore, it can analyze the user's past design style and generate consistent images. This allows for the provision of consistent images based on the user's past design patterns.

[0060] The image generation unit can incorporate a company's brand guidelines into the images it generates. For example, it can automatically generate images that reflect the company's logo and color palette. It can also generate images that include text using the company's font style. Furthermore, it can generate images that incorporate design elements based on the company's visual identity. This allows the system to provide images that comply with the company's brand guidelines.

[0061] The rights checking unit can add a function to refer to a database of past case precedents when checking for rights infringement of generated images. For example, it can evaluate the risk of generated images based on past copyright infringement cases. It can also refer to the case precedent database to check for the existence of similar cases. Furthermore, it can automatically evaluate the legal risk of generated images based on the case precedent database. This allows for the evaluation of rights infringement risk by referring to the database of past case precedents.

[0062] The image embedding section can be enhanced to automatically generate context-appropriate captions when embedding images in proposals or meeting materials. For example, it can automatically generate appropriate captions based on the content of the proposal. It can also automatically generate explanatory text relevant to the context of meeting materials. Furthermore, it can automatically generate relevant captions based on the content of the image. By automatically generating context-appropriate captions, the content of proposals and meeting materials can be conveyed more clearly.

[0063] The process management department can add functionality to integrate the entire proposal and meeting material creation process with project management tools. For example, it can integrate with project management tools to update task progress in real time. It can also integrate the proposal and meeting material creation process with project management tools for efficient management. Furthermore, it can facilitate communication among team members through project management tools. In this way, integration with project management tools can improve the efficiency of the creation process.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The image generation unit generates images to be used in proposals and meeting materials. The image generation unit generates images using generation AI and generates images based on prompts. For example, if you input the prompt "Generate an image of a business meeting," you can obtain the generated image. You can also input prompts such as "Generate a graph suitable for a proposal" or "Generate an illustration suitable for meeting materials," and obtain the graph or illustration generated accordingly. Step 2: The rights checking unit checks for copyright infringement in the images generated by the image generation unit. The rights checking unit uses a multimodal AI to check the similarity and reliance of the generated images to confirm whether copyright is infringed. For example, the generated images are input into the multimodal AI to check for similarity and reliance. It can also analyze the metadata of the generated images to confirm copyright information. Furthermore, it can refer to a database of past case precedents to assess the risk of copyright infringement of the generated images. Step 3: The image embedding unit embeds the images checked by the rights check unit into the proposal or meeting materials. The image embedding unit places the generated images in specific locations on the proposal or meeting materials, and adjusts the size and position of the images to maintain the overall balance of the page. For example, it can automatically adjust the size of the images to maintain the overall balance of the page. It can also automatically adjust the position of the images to improve visibility. Furthermore, it can automatically generate image captions to clearly convey the content of the proposal or meeting materials. Step 4: The process management department manages the entire process of creating proposals and meeting materials. The process management department notifies and visualizes the progress of work in real time and shares it with team members. For example, it can display the progress of work as graphs and charts to improve visibility. It can also integrate with project management tools to update task progress in real time. Furthermore, it can estimate user sentiment and adjust process priorities based on the estimated user sentiment.

[0066] (Example of form 2) The image generation system according to an embodiment of the present invention is a system that achieves an annual cost reduction of 50 million yen by limiting the images used in proposals and meeting materials to those generated by an image generation AI. This image generation system establishes a rule that limits the images used in proposals and meeting materials to those generated by an image generation AI. Next, a multimodal AI is used to check for copyright infringement of the generated images. This significantly reduces the time required to create proposals and meeting materials, thereby achieving cost reductions. Furthermore, by introducing AI tools to streamline the revision and supervisor review processes, further cost reductions can be expected. For example, by establishing a rule that limits the images used in proposals and meeting materials to those generated by an image generation AI, the work of finding appropriate images from internal materials or external copyright-free sites becomes unnecessary, significantly reducing work time. Specifically, while normal image searching takes an average of 3 minutes per page, using an image generation AI can reduce this to an average of 1 minute per page. This is expected to reduce 15,000 hours annually. Next, a multimodal AI is used to check for copyright infringement of the generated images. This allows for automatic checking of whether the generated images infringe on copyright. Specifically, the multimodal AI checks the similarity and reliance of generated images, outputting them only if there are no problems. This reduces the risk of copyright infringement. Furthermore, AI tools will be introduced to streamline the entire process of creating proposals and meeting materials. For example, by introducing AI tools to streamline the revision and supervisor review processes, further cost reductions can be expected. Specifically, revisions usually take an average of 3 minutes per page, but by using AI, this can be reduced to an average of 1 minute per page. This is expected to save 1,800 hours per year. Meeting time for supervisor reviews can also be reduced. Supervisors record their comments via voice, and the AI ​​automatically transcribes and summarizes them, reducing a monthly 30-minute meeting to about 10 minutes. This is expected to save 12,000 hours per year. In this way, by using image generation AI, the time required to create proposals and meeting materials will be significantly reduced, resulting in an annual cost reduction of 50 million yen.Furthermore, the risk of copyright infringement is reduced, and by accumulating internal knowledge, it can be used as material for proposals to corporate clients. As a result, the image generation system can significantly reduce the time required to create proposals and meeting materials, resulting in annual cost savings of 50 million yen.

[0067] The image generation system according to this embodiment comprises an image generation unit, a rights checking unit, an image embedding unit, and a process management unit. The image generation unit generates images to be used in proposals and meeting materials. The image generation unit generates images using, for example, a generation AI. The generation AI is a text generation AI (e.g., LLM) or an image generation AI, and the generation AI generates images based on prompts. For example, the image generation unit inputs the prompt "Generate an image of a business meeting" to the generation AI and obtains the generated image. The image generation unit can also input the prompt "Generate a graph suitable for a proposal" to the generation AI and obtain the generated graph. Furthermore, the image generation unit can input the prompt "Generate an illustration suitable for meeting materials" to the generation AI and obtain the generated illustration. The rights checking unit checks for copyright infringement of the images generated by the image generation unit. The rights checking unit checks for similarity and reliance of the generated images using, for example, a multimodal AI. The multimodal AI analyzes both images and text to confirm whether the generated images infringe copyright. For example, the rights check unit inputs the generated images into a multimodal AI to check for similarity and reliance. The rights check unit can also analyze the metadata of the generated images to verify copyright information. Furthermore, the rights check unit can refer to a database of past case precedents to assess the infringement risk of the generated images. The image embedding unit incorporates the images checked by the rights check unit into proposals and meeting materials. For example, the image embedding unit places the generated images in specific locations within the proposal or meeting materials. The image embedding unit adjusts the size and position of images to maintain overall page balance. For example, the image embedding unit automatically adjusts image size to maintain overall page balance. It can also automatically adjust image position to improve visibility. Furthermore, the image embedding unit can automatically generate image captions to clearly communicate the content of the proposal or meeting materials. The process management unit manages the entire process of creating proposals and meeting materials. For example, the process management unit provides real-time updates on the progress of the work.The process management department visualizes the progress of work and shares it with team members. For example, the process management department displays the progress of work as graphs and charts to improve visibility. The process management department can also link with project management tools to update task progress in real time. Furthermore, the process management department can estimate the user's emotions and adjust process priorities based on the estimated user emotions. As a result, the image generation system according to this embodiment can significantly reduce the time required to create proposals and meeting materials, thereby achieving cost reductions.

[0068] The image generation unit generates images for use in proposals and meeting materials. The image generation unit generates images using, for example, a generation AI. This generation AI could be a text generation AI (e.g., LLM) or an image generation AI, and it generates images based on prompts. Specifically, the image generation unit inputs the prompt "Generate an image of a business meeting" to the generation AI and retrieves the generated image. This prompt can include details such as the layout of the meeting room, the attire of the participants, and the progress of the meeting to concretely depict the business meeting scene. Based on these details, the generation AI generates a realistic image of a business meeting. The image generation unit can also input the prompt "Generate a graph suitable for a proposal" to the generation AI and retrieve the generated graph. In this case, the prompt includes the type of graph (e.g., bar graph, line graph, pie chart), the range and units of the data to display, and color specifications. The generation AI generates a visually easy-to-understand graph according to these instructions. Furthermore, the image generation unit can also input the prompt "Generate an illustration suitable for meeting materials" to the generation AI and retrieve the generated illustration. This prompt includes details such as the illustration's theme, style, color scheme, and specific elements (e.g., people, objects, background). Based on these instructions, the generating AI creates illustrations suitable for meeting materials. This allows the image generation unit to quickly produce a variety of images to meet user needs, improving the quality of proposals and meeting materials.

[0069] The rights checking unit checks for copyright infringement in images generated by the image generation unit. For example, the rights checking unit checks the similarity and reliance of images generated using a multimodal AI. The multimodal AI analyzes both images and text to confirm whether the generated images infringe copyright. Specifically, the rights checking unit inputs the generated images into the multimodal AI and checks for similarity and reliance. This AI compares the generated images with existing image databases to detect if there are images with a high degree of similarity. It also compares them with text databases to confirm whether the generated images rely on specific text or concepts. Furthermore, the rights checking unit can also analyze the metadata of the generated images to verify copyright information. The metadata includes the date and time the image was generated, the version of the generating AI, and the content of the prompts used, and the risk of copyright infringement is assessed based on this information. The rights checking unit can also refer to a database of past case precedents to assess the risk of copyright infringement of the generated images. The case precedent database contains past court cases and judgments regarding copyright infringement, and the risk of the generated images is assessed based on this. This allows the rights checking unit to verify that the generated images are legally sound, ensuring they can be used with confidence.

[0070] The image embedding unit incorporates images checked by the rights check unit into proposals and meeting materials. For example, the image embedding unit places the generated images in specific locations within the proposal or meeting materials. Specifically, the image embedding unit adjusts the size and position of images to maintain overall page balance. For instance, it automatically adjusts image size to maintain overall page balance. It can also automatically adjust image position to improve visibility. Furthermore, the image embedding unit can automatically generate image captions to clearly communicate the content of proposals and meeting materials. Captions concisely explain the content and intent of the image and are automatically generated using AI. For example, the image embedding unit analyzes the content of the generated image and generates an appropriate caption based on that content. This allows the image embedding unit to enhance the visual appeal of proposals and meeting materials and effectively communicate information. Additionally, the image embedding unit allows for manual adjustment of image placement and size, enabling customization to meet user needs. This allows the image embedding unit to improve the quality of proposals and meeting materials and support effective presentations.

[0071] The Process Management Department manages the entire process of creating proposals and meeting materials. For example, the Process Management Department provides real-time updates on work progress. Specifically, it visualizes and shares work progress with team members. For instance, it displays work progress as graphs and charts to improve visibility. It can also integrate with project management tools to update task progress in real time. This allows the entire team to understand the current progress and work efficiently. Furthermore, the Process Management Department can estimate user emotions and adjust process priorities based on these estimates. For example, it analyzes user stress levels and satisfaction levels, and makes adjustments to reduce the workload if stress levels are high. The Process Management Department also automatically sends reminders based on work progress to support meeting deadlines. This allows the Process Management Department to efficiently manage the proposal and meeting material creation process and prevent delays. Additionally, the Process Management Department can analyze past project data to identify areas for improvement to enhance work efficiency. This will allow the process management department to significantly reduce the time spent creating proposals and meeting materials, thereby achieving cost savings.

[0072] The revision response department handles revisions. For example, the revision response department revises proposals and meeting materials. The revision response department manages the revision process and verifies the revisions. For example, the revision response department identifies revisions in proposals and verifies the revisions. It can also identify revisions in meeting materials and verify the revisions. Furthermore, the revision response department can automatically reflect the revisions and update proposals and meeting materials. This streamlines the revision process and is expected to lead to further cost reductions. Some or all of the above processes in the revision response department may be performed using AI, for example, or not. For example, the revision response department can input the revision locations into AI and have AI verify the revisions.

[0073] The Review Management Department streamlines the supervisor review process. For example, the Review Management Department manages the points raised in supervisor reviews and verifies the review content. The Review Management Department allows supervisors to record their points of concern via voice, and AI automatically transcribes and summarizes them. For example, the Review Management Department inputs the supervisor's voice data into the AI ​​and has the AI ​​perform the transcription and summarization. The Review Management Department also reduces the meeting time for supervisor reviews. For example, the Review Management Department can reduce a monthly 30-minute meeting to about 10 minutes. This streamlines the supervisor review process and is expected to lead to further cost reductions. Some or all of the above processes in the Review Management Department may be performed using AI, or not. For example, the Review Management Department can input the supervisor's voice data into the AI ​​and have the AI ​​perform the transcription and summarization.

[0074] The image generation unit generates images using a generation AI. The image generation unit generates images by inputting prompts to the generation AI, for example. The generation AI can be a text generation AI (e.g., LLM) or an image generation AI, and the generation AI generates images based on the prompts. For example, the image generation unit inputs the prompt "Generate an image of a business meeting" to the generation AI and retrieves the generated image. The image generation unit can also input the prompt "Generate a graph suitable for a proposal" to the generation AI and retrieve the generated graph. Furthermore, the image generation unit can input the prompt "Generate an illustration suitable for meeting materials" to the generation AI and retrieve the generated illustration. This improves the efficiency of image generation by using a generation AI. Some or all of the above-described processes in the image generation unit may be performed using a generation AI, for example, or without using a generation AI. For example, the image generation unit inputs prompts to the generation AI and generates images.

[0075] The rights checking unit checks the similarity and reliance of images generated using a multimodal AI. For example, the rights checking unit inputs the generated image into the multimodal AI and checks its similarity and reliance. The multimodal AI analyzes both the image and text to confirm whether the generated image infringes copyright. For example, the rights checking unit inputs the generated image into the multimodal AI and checks its similarity and reliance. The rights checking unit can also analyze the metadata of the generated image to confirm copyright information. Furthermore, the rights checking unit can refer to a database of past case precedents to assess the risk of copyright infringement of the generated image. This reduces the risk of copyright infringement by using a multimodal AI. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or without AI. For example, the rights checking unit inputs the generated image into the multimodal AI and checks its similarity and reliance.

[0076] The image generation unit estimates the user's emotions and adjusts the style of the generated image based on the estimated emotions. For example, if the user is tense, the image generation unit can generate an image with calm tones. If the user is relaxed, the image generation unit can also generate an image with bright and cheerful tones. Furthermore, if the user is in a hurry, the image generation unit can generate a simple and highly visible image. This allows for the generation of more appropriate images by providing image styles that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the image generation unit may be performed using AI, or not using AI. For example, the image generation unit can input user emotion data into an AI and have the AI ​​perform image style adjustments.

[0077] The image generation unit automatically selects the theme and color tone of the generated images according to the content of the proposal or meeting materials. For example, if the proposal is business-oriented, the image generation unit will select a professional color tone and design. If the meeting materials are creative, the image generation unit can also select a colorful and inspiring design. Furthermore, if the proposal is technical, the image generation unit can select a simple and technical design. This ensures that appropriate images are provided according to the content of the proposal or meeting materials. Some or all of the above processing in the image generation unit may be performed using, for example, a generation AI, or not. For example, the image generation unit can input the content of the proposal or meeting materials into a generation AI and have the generation AI select the image theme and color tone.

[0078] The image generation unit adds a function to the generated images that reflect the company's brand guidelines. For example, the image generation unit automatically generates images that reflect the company's logo and color palette. The image generation unit can also generate images that include text using the company's font style. Furthermore, the image generation unit can generate images that incorporate design elements based on the company's visual identity. This allows for the provision of images that comply with the company's brand guidelines. Some or all of the above processing in the image generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the image generation unit can input the company's brand guidelines into a generation AI and have the generation AI perform the image generation.

[0079] The image generation unit estimates the user's emotions and provides multiple variations of images based on the estimated emotions. For example, if the user is tense, the image generation unit can provide variations of images with calm tones and simple designs. If the user is relaxed, the image generation unit can also provide variations of images with bright, cheerful tones and creative designs. Furthermore, if the user is in a hurry, the image generation unit can provide variations of images with simple, highly visible designs and efficient designs. This allows for the provision of multiple image variations tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the image generation unit may be performed using AI, or not. For example, the image generation unit can input user emotion data into an AI and have the AI ​​generate image variations.

[0080] The image generation unit reflects the design patterns of the user's past proposals and meeting materials in the images it generates. For example, the image generation unit generates images that reflect the color tones and design elements the user has used in the past. The image generation unit can also generate images based on the layout patterns of the user's past proposals and meeting materials. Furthermore, the image generation unit can analyze the user's past design style and generate consistent images. This allows for the provision of consistent images based on the user's past design patterns. Some or all of the above processing in the image generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image generation unit can input the user's past design patterns into a generation AI and have the generation AI perform image generation.

[0081] The image generation unit incorporates the user's geographical background and cultural elements into the images it generates. For example, the image generation unit generates images that reflect geographical elements based on the user's location. The image generation unit can also generate images that incorporate design elements based on the user's cultural background. Furthermore, the image generation unit can generate images that use symbols or icons specific to the user's region. This allows the system to provide images that are tailored to the user's geographical background and cultural elements. Some or all of the above-described processes in the image generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image generation unit can input the user's geographical background and cultural elements into a generation AI and have the generation AI perform the image generation.

[0082] The rights check unit estimates the user's emotions and adjusts the strictness of the rights check based on the estimated emotions. For example, if the user is tense, the rights check unit performs a strict rights check to minimize risk. If the user is relaxed, the rights check unit can perform a normal rights check to maintain balance. Furthermore, if the user is in a hurry, the rights check unit can perform a rapid rights check to save time. This allows for providing a rights check strictness tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the rights check unit may be performed using AI or not. For example, the rights check unit can input user emotion data into an AI and have the AI ​​perform the adjustment of the rights check strictness.

[0083] The rights checking unit adds a function to the rights infringement check of generated images that refers to a database of past case precedents. The rights checking unit evaluates the risk of the generated image based on past copyright infringement cases, for example. The rights checking unit can also refer to the case precedent database to check for the existence of similar cases. Furthermore, the rights checking unit can automatically evaluate the legal risk of the generated image based on the case precedent database. This allows for the evaluation of rights infringement risk by referring to the database of past case precedents. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or without AI. For example, the rights checking unit can input the generated image into the case precedent database and have AI perform the risk evaluation.

[0084] The rights checking unit adds a function to analyze the image metadata for checking the rights infringement of generated images. For example, the rights checking unit analyzes the metadata of the generated image and verifies the copyright information. The rights checking unit can also automatically check the source and rights information of the image based on the metadata. Furthermore, the rights checking unit can evaluate the rights infringement risk of the generated image through metadata analysis. This allows for the evaluation of rights infringement risk by analyzing the image metadata. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or without AI. For example, the rights checking unit can input the metadata of the generated image into AI and have the AI ​​perform the risk assessment.

[0085] The rights check unit estimates the user's emotions and adjusts the order in which the rights check results are displayed based on the estimated emotions. For example, if the user is nervous, the rights check unit will display the most important rights check results first. If the user is relaxed, the rights check unit can also display the overall results in a balanced manner. Furthermore, if the user is in a hurry, the rights check unit can display concise results for quick review. This provides a display order of rights check results that is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the rights check unit may be performed using AI or not. For example, the rights check unit can input user emotion data into an AI and have the AI ​​adjust the display order.

[0086] The rights checking unit incorporates the user's industry-specific rights information into the rights infringement check of the generated images. For example, the rights checking unit performs rights checks based on copyright information specific to the user's industry. The rights checking unit can also refer to industry-specific rights information and assess the risks of the generated images. Furthermore, the rights checking unit can perform rights checks based on industry guidelines to minimize risks. This enables the provision of rights checks based on the user's industry-specific rights information. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or not using AI. For example, the rights checking unit can input industry-specific rights information into AI and have the AI ​​perform a risk assessment.

[0087] The rights checking unit refers to a rights information database that is updated in real time to check for rights infringement of the generated images. The rights checking unit performs rights checks based on copyright information that is updated in real time, for example. The rights checking unit can also refer to the latest rights information database and evaluate the risks of the generated images. Furthermore, the rights checking unit can automatically evaluate the legal risks of the generated images based on the real-time database. This allows the unit to provide checks based on the latest rights information by referring to a rights information database that is updated in real time. Some or all of the above processing in the rights checking unit may be performed using AI, for example, or not using AI. For example, the rights checking unit can input a rights information database that is updated in real time into AI and have the AI ​​perform a risk assessment.

[0088] The image embedding unit estimates the user's emotions and adjusts the image placement based on the estimated emotions. For example, if the user is tense, the image embedding unit can provide a simple and highly visible placement. If the user is relaxed, the image embedding unit can also provide a creative and fun placement. Furthermore, if the user is in a hurry, the image embedding unit can provide an efficient and quickly viewable placement. This allows for the provision of image placement methods that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the image embedding unit may be performed using AI, for example, or not using AI. For example, the image embedding unit can input user emotion data into AI and have the AI ​​perform the adjustment of the placement method.

[0089] The image embedding unit adds a function to automatically generate context-appropriate captions when images are embedded in proposals or meeting materials. For example, the image embedding unit can automatically generate appropriate captions based on the content of the proposal. The image embedding unit can also automatically generate context-appropriate explanatory text for meeting materials. Furthermore, the image embedding unit can automatically generate relevant captions based on the content of the image. This allows for clearer communication of the content of proposals and meeting materials by automatically generating context-appropriate captions. Some or all of the above processing in the image embedding unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image embedding unit can input the content of an image into a generation AI and have the generation AI generate the caption.

[0090] The image embedding section adds a function to automatically adjust the overall balance of the page layout when embedding images. For example, the image embedding section automatically adjusts the size and position of images to maintain the overall balance of the page. The image embedding section can also optimize the placement of text and images to improve readability. Furthermore, the image embedding section can automatically adjust the placement of images while considering the overall design of the page layout. This allows for the provision of highly readable materials by automatically adjusting the overall balance of the page layout. Some or all of the above processing in the image embedding section may be performed using, for example, a generation AI, or not using a generation AI. For example, the image embedding section can input page layout information into a generation AI and have the generation AI perform the balance adjustment.

[0091] The image embedding unit estimates the user's emotions and adjusts the size and position of the image based on the estimated emotions. For example, if the user is tense, the image embedding unit can provide a simple and highly visible size and position. If the user is relaxed, it can also provide a creative and fun size and position. Furthermore, if the user is in a hurry, it can provide an efficient and quickly viewable size and position. This allows for the provision of image sizes and positions that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the image embedding unit may be performed using AI, for example, or not using AI. For example, the image embedding unit can input user emotion data into AI and have the AI ​​perform the size and position adjustments.

[0092] The image embedding unit incorporates the layout patterns of the user's past proposals and meeting materials when embedding images. For example, the image embedding unit adjusts the placement of images based on layout patterns previously used by the user. The image embedding unit can also provide image placement that reflects the design style of the user's past proposals and meeting materials. Furthermore, the image embedding unit can analyze the user's past layout patterns and provide consistent image placement. This allows for consistent image placement based on the user's past layout patterns. Some or all of the above processing in the image embedding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the image embedding unit can input the user's past layout patterns into a generative AI and have the generative AI perform the placement adjustments.

[0093] The image embedding unit selects the optimal display method when embedding an image, taking into account the user's device information. For example, if the user is using a smartphone, the image embedding unit provides a display method that matches the screen size. If the user is using a tablet, the image embedding unit can also provide a display method optimized for a larger screen. Furthermore, if the user is using a desktop, the image embedding unit can provide a display method that supports high resolution. This allows the system to provide the optimal display method based on the user's device information. Some or all of the above processing in the image embedding unit may be performed using, for example, a generation AI, or without a generation AI. For example, the image embedding unit can input the user's device information into a generation AI and have the generation AI select the display method.

[0094] The process management unit estimates the user's emotions and adjusts the method of visualizing the process progress based on the estimated user emotions. For example, if the user is tense, the process management unit provides a simple and highly visible progress display. If the user is relaxed, the process management unit can also provide a detailed progress display. Furthermore, if the user is in a hurry, the process management unit can provide a concise progress display. This allows for a method of visualizing the process progress that is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the process management unit may be performed using AI, or not using AI. For example, the process management unit can input user emotion data into AI and have the AI ​​adjust the visualization method.

[0095] The Process Management Department will add a function to link the entire process of creating proposals and meeting materials with the project management tool. For example, the Process Management Department will link with the project management tool to update the progress of tasks in real time. The Process Management Department can also integrate the process of creating proposals and meeting materials with the project management tool and manage it efficiently. Furthermore, the Process Management Department can facilitate communication among team members through the project management tool. In this way, linking with the project management tool will improve the efficiency of the creation process. Some or all of the above processes in the Process Management Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Process Management Department can input information from the project management tool into the generative AI and have the generative AI execute the linking function.

[0096] The process management department will add a function to notify the progress of work in real time. For example, the process management department will notify the progress of work in real time and share it with team members. The process management department can also customize the progress notifications and prioritize notifications for the progress of important tasks. In addition, the process management department can detect work delays early and take countermeasures through real-time notifications. This means that by notifying progress in real time, work delays can be detected early and countermeasures can be taken. Some or all of the above processes in the process management department may be performed using, for example, a generative AI, or not using a generative AI. For example, the process management department can input progress data into a generative AI and have the generative AI execute the notification function.

[0097] The process management unit estimates the user's emotions and adjusts process priorities based on the estimated emotions. For example, if the user is stressed, the process management unit will prioritize important tasks. If the user is relaxed, the process management unit can also process tasks with normal priorities. Furthermore, if the user is in a hurry, the process management unit can prioritize tasks that can be completed quickly. This provides process priorities that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the process management unit may be performed using AI, for example, or not using AI. For example, the process management unit can input user emotion data into an AI and have the AI ​​perform the priority adjustment.

[0098] The process management unit optimizes the entire process of creating proposals and meeting materials by referring to the user's past work history. For example, the process management unit proposes an efficient work process based on the user's past work history. The process management unit can also analyze past work history and propose the optimal task sequence. Furthermore, the process management unit can learn the user's work patterns and automatically set the optimal work process. This allows it to provide an optimal work process based on the user's past work history. Some or all of the above processes in the process management unit may be performed using, for example, generative AI, or not using generative AI. For example, the process management unit can input the user's past work history into a generative AI and have the generative AI perform the optimization.

[0099] The process management unit will add a function to automatically generate work plans by reflecting the user's schedule information. For example, the process management unit will automatically generate an optimal work plan based on the user's schedule information. The process management unit can also refer to the schedule information and automatically set task priorities. Furthermore, the process management unit can flexibly adjust the work plan to match the user's schedule. This will enable the provision of an optimal work plan based on the user's schedule information. Some or all of the above processing in the process management unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the process management unit can input the user's schedule information into the generation AI and have the generation AI perform the automatic generation of a work plan.

[0100] The correction response unit estimates the user's emotions and adjusts the priority of corrections based on the estimated emotions. For example, if the user is stressed, the correction response unit will prioritize important corrections. If the user is relaxed, the correction response unit can also process corrections with normal priority. Furthermore, if the user is in a hurry, the correction response unit can prioritize corrections that can be completed quickly. This provides correction priorities that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the correction response unit may be performed using AI, for example, or not using AI. For example, the correction response unit can input user emotion data into an AI and have the AI ​​perform the priority adjustment.

[0101] The correction response unit adds a function to suggest the optimal correction method by referring to past correction history when making corrections. For example, the correction response unit suggests the optimal correction method based on past correction history. The correction response unit can also refer to the correction history and present similar correction cases. Furthermore, the correction response unit can analyze past correction patterns and suggest efficient correction methods. This enables the provision of the optimal correction method based on past correction history. Some or all of the above processing in the correction response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction response unit can input past correction history into a generation AI and have the generation AI execute the correction method suggestion.

[0102] The correction response unit estimates the user's emotions and adjusts the display method of the correction based on the estimated user emotions. For example, if the user is tense, the correction response unit provides a simple and highly visible display method. If the user is relaxed, the correction response unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the correction response unit can provide a concise display method. This allows for the display of corrections to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the correction response unit may be performed using AI, for example, or not using AI. For example, the correction response unit can input user emotion data into AI and have the AI ​​perform the adjustment of the display method.

[0103] The correction response unit proposes the optimal correction method when performing corrections, taking into account the user's device information. For example, if the user is using a smartphone, the correction response unit proposes a correction method that matches the screen size. If the user is using a tablet, the correction response unit can also propose a correction method optimized for a larger screen. Furthermore, if the user is using a desktop, the correction response unit can propose a correction method that supports high resolution. This allows the unit to provide the optimal correction method based on the user's device information. Some or all of the above processing in the correction response unit may be performed using, for example, a generation AI, or without a generation AI. For example, the correction response unit can input the user's device information into a generation AI and have the generation AI execute the correction method proposal.

[0104] The review management unit estimates the user's emotions and adjusts the review feedback method based on the estimated emotions. For example, if the user is nervous, the review management unit provides simple and easy-to-understand feedback. If the user is relaxed, the review management unit can also provide detailed feedback. Furthermore, if the user is in a hurry, the review management unit can provide concise feedback. This allows for review feedback methods tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review management unit may be performed using AI or not. For example, the review management unit can input user emotion data into AI and have the AI ​​adjust the feedback method.

[0105] The review management unit will add a function to provide optimal feedback by referring to past review history. For example, the review management unit will provide optimal feedback based on past review history. The review management unit can also refer to the review history and suggest similar review cases. Furthermore, the review management unit can analyze past review history and propose efficient feedback methods. This will enable the provision of optimal feedback based on past review history. Some or all of the above processes in the review management unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the review management unit can input past review history into a generative AI and have the generative AI propose feedback methods.

[0106] The review management unit estimates the user's emotions and adjusts the review priority based on the estimated emotions. For example, if the user is stressed, the review management unit will prioritize important reviews. If the user is relaxed, the review management unit may process reviews with normal priority. Also, if the user is in a hurry, the review management unit may prioritize reviews that can be completed quickly. This provides review prioritization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the review management unit may be performed using AI or not. For example, the review management unit can input user emotion data into an AI and have the AI ​​perform the priority adjustment.

[0107] The review management unit will add a function to optimize review timing by reflecting the user's schedule information. For example, the review management unit will automatically generate the optimal review timing based on the user's schedule information. The review management unit can also refer to the schedule information and automatically set review priorities. Furthermore, the review management unit can flexibly adjust the review timing to match the user's schedule. This will enable the provision of optimal review timing based on the user's schedule information. Some or all of the above processing in the review management unit may be performed using, for example, a generation AI, or without a generation AI. For example, the review management unit can input the user's schedule information into a generation AI and have the generation AI perform the timing optimization.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The image generation unit can incorporate the design patterns of the user's past proposals and meeting materials into the images it generates. For example, it can generate images that reflect the color schemes and design elements the user has used in the past. It can also generate images based on the layout patterns of the user's past proposals and meeting materials. Furthermore, it can analyze the user's past design style and generate consistent images. This allows for the provision of consistent images based on the user's past design patterns.

[0110] The image generation unit can incorporate a company's brand guidelines into the images it generates. For example, it can automatically generate images that reflect the company's logo and color palette. It can also generate images that include text using the company's font style. Furthermore, it can generate images that incorporate design elements based on the company's visual identity. This allows the system to provide images that comply with the company's brand guidelines.

[0111] The image generation unit can estimate the user's emotions and adjust the style of the generated images based on those emotions. For example, if the user is stressed, it can generate images with calm tones. If the user is relaxed, it can generate images with bright and cheerful tones. Furthermore, if the user is in a hurry, it can generate simple and highly visible images. This allows the system to provide image styles that match the user's emotions.

[0112] The rights checking unit can add a function to refer to a database of past case precedents when checking for rights infringement of generated images. For example, it can evaluate the risk of generated images based on past copyright infringement cases. It can also refer to the case precedent database to check for the existence of similar cases. Furthermore, it can automatically evaluate the legal risk of generated images based on the case precedent database. This allows for the evaluation of rights infringement risk by referring to the database of past case precedents.

[0113] The rights check unit can estimate the user's emotions and adjust the rigor of the rights check based on those emotions. For example, if the user is stressed, a rigorous rights check can be performed to minimize risk. If the user is relaxed, a standard rights check can be performed to maintain balance. Furthermore, if the user is in a hurry, a rapid rights check can be performed to save time. This allows for a level of rights check rigor that is tailored to the user's emotions.

[0114] The image embedding section can be enhanced to automatically generate context-appropriate captions when embedding images in proposals or meeting materials. For example, it can automatically generate appropriate captions based on the content of the proposal. It can also automatically generate explanatory text relevant to the context of meeting materials. Furthermore, it can automatically generate relevant captions based on the content of the image. By automatically generating context-appropriate captions, the content of proposals and meeting materials can be conveyed more clearly.

[0115] The image embedding section can estimate the user's emotions and adjust the image placement based on those emotions. For example, if the user is stressed, it can provide a simple and highly visible placement. If the user is relaxed, it can provide a creative and enjoyable placement. Furthermore, if the user is in a hurry, it can provide an efficient and quick-to-view placement. This allows for image placement tailored to the user's emotions.

[0116] The process management unit can estimate the user's emotions and adjust the method of visualizing the process progress based on those emotions. For example, if the user is stressed, a simple and highly visible progress display can be provided. If the user is relaxed, a detailed progress display can be provided. Furthermore, if the user is in a hurry, a concise progress display can be provided. This allows for a method of visualizing the process progress that is tailored to the user's emotions.

[0117] The process management department can add functionality to integrate the entire proposal and meeting material creation process with project management tools. For example, it can integrate with project management tools to update task progress in real time. It can also integrate the proposal and meeting material creation process with project management tools for efficient management. Furthermore, it can facilitate communication among team members through project management tools. In this way, integration with project management tools can improve the efficiency of the creation process.

[0118] The correction response unit can estimate the user's emotions and adjust the priority of corrections based on those emotions. For example, if the user is stressed, important corrections can be prioritized. If the user is relaxed, corrections can be processed with normal priority. Furthermore, if the user is in a hurry, corrections that can be completed quickly can be prioritized. This allows for correction prioritization that is tailored to the user's emotions.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The image generation unit generates images to be used in proposals and meeting materials. The image generation unit generates images using generation AI and generates images based on prompts. For example, if you input the prompt "Generate an image of a business meeting," you can obtain the generated image. You can also input prompts such as "Generate a graph suitable for a proposal" or "Generate an illustration suitable for meeting materials," and obtain the graph or illustration generated accordingly. Step 2: The rights checking unit checks for copyright infringement in the images generated by the image generation unit. The rights checking unit uses a multimodal AI to check the similarity and reliance of the generated images to confirm whether copyright is infringed. For example, the generated images are input into the multimodal AI to check for similarity and reliance. It can also analyze the metadata of the generated images to confirm copyright information. Furthermore, it can refer to a database of past case precedents to assess the risk of copyright infringement of the generated images. Step 3: The image embedding unit embeds the images checked by the rights check unit into the proposal or meeting materials. The image embedding unit places the generated images in specific locations on the proposal or meeting materials, and adjusts the size and position of the images to maintain the overall balance of the page. For example, it can automatically adjust the size of the images to maintain the overall balance of the page. It can also automatically adjust the position of the images to improve visibility. Furthermore, it can automatically generate image captions to clearly convey the content of the proposal or meeting materials. Step 4: The process management department manages the entire process of creating proposals and meeting materials. The process management department notifies and visualizes the progress of work in real time and shares it with team members. For example, it can display the progress of work as graphs and charts to improve visibility. It can also integrate with project management tools to update task progress in real time. Furthermore, it can estimate user sentiment and adjust process priorities based on the estimated user sentiment.

[0121] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0123] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] Each of the multiple elements described above, including the image generation unit, rights check unit, image embedding unit, process management unit, modification response unit, and review management unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the image generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The rights check unit is implemented by the specific processing unit 290 of the data processing device 12. The image embedding unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The process management unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The modification response unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The review management unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0127] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0128] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0129] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0130] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0131] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0132] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0133] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0134] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0135] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0136] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0138] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the image generation unit, rights check unit, image embedding unit, process management unit, modification response unit, and review management unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the image generation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The rights check unit is implemented by the specific processing unit 290 of the data processing unit 12. The image embedding unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The process management unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The modification response unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The review management unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0144] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0148] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0149] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the image generation unit, rights check unit, image embedding unit, process management unit, modification response unit, and review management unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the image generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The rights check unit is implemented by the specific processing unit 290 of the data processing unit 12. The image embedding unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The process management unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The modification response unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The review management unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0164] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0165] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0166] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0167] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0168] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the image generation unit, rights check unit, image embedding unit, process management unit, modification response unit, and review management unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the image generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The rights check unit is implemented by the specific processing unit 290 of the data processing unit 12. The image embedding unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The process management unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The modification response unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The review management unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0174] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0175] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0176] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0177] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0178] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0179] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0180] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0181] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0182] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0183] 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.

[0184] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0185] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0186] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0187] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0188] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0189] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0190] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0191] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0192] (Note 1) An image generation unit that generates images to be used in proposals and meeting materials, A rights checking unit checks for rights infringement of the image generated by the image generation unit, The image embedding unit incorporates the images checked by the aforementioned rights checking unit into proposals and meeting materials. It includes a process management department that manages the entire process of creating proposals and meeting materials. A system characterized by the following features. (Note 2) A correction support department is prepared to handle the corrections. The system described in Appendix 1, characterized by the features described herein. (Note 3) We have a review management department to streamline the supervisor review process. The system described in Appendix 1, characterized by the features described herein. (Note 4) The image generation unit, Generate images using generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned rights checking unit is, Check the similarity and reliance of images generated using multimodal AI. The system described in Appendix 1, characterized by the features described herein. (Note 6) The image generation unit, It estimates the user's emotions and adjusts the style of the generated images based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The image generation unit, The system automatically selects the theme and color tone of the generated images according to the content of the proposal or meeting materials. The system described in Appendix 1, characterized by the features described herein. (Note 8) The image generation unit, Add a feature to reflect the company's brand guidelines in the generated images. The system described in Appendix 1, characterized by the features described herein. (Note 9) The image generation unit, It estimates the user's emotions and provides multiple variations of images generated based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The image generation unit, The generated images will reflect the design patterns of the user's past proposals and meeting materials. The system described in Appendix 1, characterized by the features described herein. (Note 11) The image generation unit, The generated images incorporate the user's geographical background and cultural elements. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned rights checking unit is, We estimate user sentiment and adjust the strictness of rights checks based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned rights checking unit is, Add a feature to check for copyright infringement in generated images by referencing a database of past case precedents. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned rights checking unit is, Add a feature to analyze image metadata for checking the rights infringement of generated images. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned rights checking unit is, The system estimates the user's sentiment and adjusts the order in which the results of the rights check are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned rights checking unit is, The rights infringement check for generated images will incorporate the user's industry-specific rights information. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned rights checking unit is, The generated images are checked for copyright infringement by referencing a real-time updated rights information database. The system described in Appendix 1, characterized by the features described herein. (Note 18) The image embedding unit is, It estimates the user's emotions and adjusts the image placement based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The image embedding unit is, We will add a feature that automatically generates contextually appropriate captions when images are incorporated into proposals and meeting materials. The system described in Appendix 1, characterized by the features described herein. (Note 20) The image embedding unit is, Add a feature that automatically adjusts the overall balance of the page layout when incorporating images. The system described in Appendix 1, characterized by the features described herein. (Note 21) The image embedding unit is, It estimates the user's emotions and adjusts the size and position of images based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The image embedding unit is, When incorporating images, reflect the layout patterns of the user's past proposals and meeting materials. The system described in Appendix 1, characterized by the features described herein. (Note 23) The image embedding unit is, When embedding images, the optimal display method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned process control unit, We estimate user emotions and adjust how we visualize process progress based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned process control unit, Add a feature that integrates the entire process of creating proposals and meeting materials with project management tools. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned process control unit, Add a feature to notify users of the progress of their work in real time. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned process control unit, It estimates the user's emotions and adjusts process priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned process control unit, The entire process of creating proposals and meeting materials is optimized by referencing the user's past work history. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned process control unit, Add a feature to automatically generate a work plan by incorporating the user's schedule information. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned correction response unit is: It estimates the user's emotions and adjusts the priority of modifications based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned correction response unit is: When making corrections, we will add a function that suggests the optimal correction method by referring to past correction history. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned correction response unit is: It estimates the user's sentiment and adjusts how the correction is displayed based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned correction response unit is: When implementing a fix, we will propose the optimal fix method considering the user's device information. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned review management department, It estimates user sentiment and adjusts how review feedback is provided based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned review management department, Add a feature that provides optimal feedback by referring to past review history. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned review management department, It estimates user sentiment and adjusts review priorities based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned review management department, Add a feature to optimize review timing by reflecting the user's schedule information. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An image generation unit that generates images to be used in proposals and meeting materials, A rights checking unit checks for rights infringement of the image generated by the image generation unit, The image embedding unit incorporates the images checked by the aforementioned rights checking unit into proposals and meeting materials. It includes a process management department that manages the entire process of creating proposals and meeting materials. A system characterized by the following features.

2. A correction support department is prepared to handle the corrections. The system according to feature 1.

3. We have a review management department to streamline the supervisor review process. The system according to feature 1.

4. The image generation unit, Generate images using generative AI. The system according to feature 1.

5. The aforementioned rights checking unit is, Check the similarity and reliance of images generated using multimodal AI. The system according to feature 1.

6. The image generation unit, It estimates the user's emotions and adjusts the style of the generated images based on those estimated emotions. The system according to feature 1.

7. The image generation unit, The system automatically selects the theme and color tone of the generated images according to the content of the proposal or meeting materials. The system according to feature 1.

8. The image generation unit, Add a feature to reflect the company's brand guidelines in the generated images. The system according to feature 1.

9. The image generation unit, It estimates the user's emotions and provides multiple variations of images generated based on the estimated user emotions. The system according to feature 1.

10. The image generation unit, The generated images will reflect the design patterns of the user's past proposals and meeting materials. The system according to feature 1.

Images