system

Abstract

The system according to the embodiment aims to provide the compilation of a company history as an attractive content. [Solution] A system according to an embodiment includes an input unit, an image generation unit, a text generation unit, and a providing unit. The input unit inputs the content of the company history. The image generation unit generates related images based on the content input by the input unit. The text generation unit generates text using different expressions based on the content input by the input unit. The providing unit provides the content generated by the image generation unit and the text generation unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, compiling a company history was considered a mundane and tedious task, making it difficult to provide it as attractive content for both inside and outside the company.

[0005] The system according to the embodiment aims to provide the compilation of a company history as an attractive content. [Means for solving the problem]

[0006] The system according to the embodiment includes an input unit, an image generation unit, a text generation unit, and a providing unit. The input unit inputs the content of the company history. The image generation unit generates related images based on the content input by the input unit. The text generation unit generates text in different expressions based on the content input by the input unit. The providing unit provides the content generated by the image generation unit and the text generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide the compilation of a company history as an attractive content. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A corporate history compilation system according to an embodiment of the present invention utilizes image generation AI and language generation AI to revolutionize the traditional image of corporate history compilation and provide new and interesting content both inside and outside the company. This system allows users to input the content of a company history. The image generation AI generates related images based on the content, and the language generation AI then translates the content into text using a variety of expressions, enriching the company history visually and writtenly. This eliminates the traditional image of a dull and boring company history, providing new interest to both inside and outside the company, and potentially leading to a change in attitudes toward work. For example, when inputting the content of a company history, users enter detailed descriptions of each episode and important milestone in the history. For example, they can input stories from the company's founding and success stories of important projects. This information is then input into the image generation AI and language generation AI. The image generation AI then generates related images based on the input content. For example, based on a story from the company's founding, it generates a picture of the company's office at the time of its founding and a portrait of the founder. Based on success stories of important projects, it can also generate project deliverables and group photos of the project team. This visually enriches the company history. Furthermore, the language generation AI then translates the input content into text using a variety of expressions. For example, an episode from the company's founding can be written as an inspiring story, or a success story from an important project can be written as a humorous anecdote. This enriches the text of the company history, making it more interesting for readers. This system can completely change the traditional image of compiling a company history as dull and boring, providing new excitement both inside and outside the company. For example, when introducing a company history at an internal event, using the generated images and text can attract participants' attention and increase their interest in the history. Furthermore, when making the company history public, providing rich content both visually and textually can have an impact on society and lead to a change in attitudes toward work. In this way, the company history compilation system enriches the content of company histories visually and textually, dispelling the traditional image of them as dull and boring.

[0029] A company history compilation system according to an embodiment includes an input unit, an image generation unit, a text generation unit, and a provision unit. The input unit inputs the content of the company history. The content of the company history includes, but is not limited to, the company's founding history, important events, and project success stories. The input unit can input, for example, detailed information about each episode and important event in the company history. For example, the input unit inputs information about the company's founding and important project success stories. This information is input to an image generation AI and a language generation AI. The image generation unit uses the generation AI to generate related images based on the content input by the input unit. For example, the image generation unit generates an office at the time of the company's founding and a portrait of the founder based on the founding episodes. The image generation unit can also generate project deliverables and group photos of the project team based on important project success stories. For example, the image generation unit generates the office layout and equipment at the time of the company's founding and a portrait of the founder. Project deliverables include, for example, products, services, and reports. Project team group photos include, for example, official group photos and photos of the team working together. The text generation unit uses a generation AI to generate text in a variety of expressions based on the content input by the input unit. The text generation unit, for example, writes an episode from the company's founding as an inspiring story. The text generation unit can also write a success story of an important project as a humorous story. For example, the text generation unit writes an episode from the company's founding as an inspiring story and a success story of an important project as a humorous story. The provision unit provides the generated images and text. The provision unit, for example, introduces the generated images and text at an internal event. The provision unit can also make the generated images and text publicly available. For example, the provision unit introduces the generated images and text at an internal event to attract participants' attention and increase interest in the company history. When publicly available, providing content that is rich in both visual and textual content can have an impact on society and lead to a change in attitudes toward work. As a result, the corporate history compilation system according to the embodiment can enrich the content of company histories visually and textually, dispelling the conventional image of them as dull and boring.

[0030] The image generation unit can generate the office or a portrait of the founder at the time of the company's founding based on the episodes from the company's founding. The image generation unit can, for example, generate the layout and equipment of the office at the time of the company's founding and a portrait of the founder based on the episodes from the company's founding. For example, the image generation unit can recreate the layout of the office at the time of the company's founding and depict the equipment and furniture from that time in detail. The image generation unit can also generate a portrait of the founder and faithfully reproduce his or her features. This visually recreates the episodes from the company's founding, thereby enhancing the appeal of the company's history. Some or all of the above-mentioned processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input data on the office layout and equipment at the time of the company's founding into the generation AI, and the generation AI can generate an image based on that data.

[0031] The image generation unit can generate a group photo of the project deliverables or the project team based on important project success stories. For example, the image generation unit can depict the project deliverables in detail and visually express the features of the product or service. The image generation unit can also generate a group photo of the project team, faithfully reproducing the faces and postures of the team members. This visually reproduces the success stories of important projects, thereby enhancing the appeal of the company history. Some or all of the above-described processing in the image generation unit may be performed using or without a generation AI. For example, the image generation unit can input data on the project deliverables or the project team into the generation AI, which then generates an image based on the data.

[0032] The text generation unit can write down the founding episode as an emotional story. For example, the text generation unit can write down the founding episode as a moving story. For example, the text generation unit can generate a story that moves the reader by describing the founder's struggles and efforts. The text generation unit can also write down the founding episode as a humorous story. For example, the text generation unit can generate a story that describes humorous events and episodes of the founder and provides laughter to the reader. This can enhance the appeal of the company history by portraying the founding episode in a moving way. Some or all of the above-described processing in the text generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the text generation unit can input data on the founding episode into the generation AI, which can then generate a moving story based on that data.

[0033] The text generation unit can write down success stories of important projects as funny anecdotes. For example, the text generation unit can write down success stories of important projects as humorous anecdotes. For example, the text generation unit can generate stories that describe humorous events and anecdotes that occurred during the progress of the project to make readers laugh. The text generation unit can also generate stories that humorously describe the struggles and efforts that led to the project's success to attract readers' interest. This makes it possible to humorously portray success stories of important projects and enhance the appeal of the company history. Some or all of the above-mentioned processing in the text generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the text generation unit can input data on success stories of projects into a generation AI, which can then generate humorous anecdotes based on that data.

[0034] The provision unit can introduce the generated images and text at internal company events. For example, the provision unit can introduce the generated images and text at internal company events. For example, the provision unit can introduce the generated content at events such as internal meetings, training sessions, and parties to attract participants' interest and increase interest in the company's history. The provision unit can also provide the generated images and text in digital format. For example, the provision unit can provide the generated content as a website or presentation materials so that participants can access it at any time. In this way, introducing the generated content at internal company events can increase interest in the company's history. Some or all of the above-mentioned processing in the provision unit may be performed using or without the generation AI. For example, the provision unit can input the generated content into the generation AI, and the generation AI can suggest how to introduce it at the event based on that data.

[0035] The providing unit can publish the generated images and text outside the company. For example, the providing unit publishes the generated images and text outside the company. For example, the providing unit can publish the generated content on a website, in a press release, on social media, etc., to have an impact on society and lead to a change in attitudes toward work. The providing unit can also provide the generated images and text as printed materials. For example, the providing unit can print the generated content as a pamphlet or report and distribute it to relevant parties outside the company. In this way, publishing it outside the company can have an impact on society and lead to a change in attitudes toward work. Some or all of the above-mentioned processing in the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the generated content into a generation AI, and the generation AI can suggest a publication method based on that data.

[0036] The input unit can check the consistency of the input content based on past company history data. For example, the input unit automatically checks whether an episode entered by a user is consistent with past company history data. For example, the input unit can compare an episode entered by a user with past company history data to check for inconsistencies. The input unit can also automatically complete the content entered by a user if it matches past company history data. For example, the input unit can automatically add detailed information related to the episode if the episode entered by a user matches past company history data. Furthermore, the input unit can suggest corrections if the content entered by a user differs from past company history data. For example, if the episode entered by a user differs from past company history data, the input unit can suggest corrections to the episode and ask the user for confirmation. This allows the consistency of the input content to be maintained by referring to past company history data. Some or all of the above-mentioned processing in the input unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the input unit can input past company history data into a generation AI, and the generation AI can check the consistency of the input content based on that data.

[0037] The input unit can customize input guides based on the user's position or department. For example, if the user is a manager, the input unit provides input guides related to important projects and strategic decisions. For example, the input unit can present detailed questions related to project progress and strategic decisions to a managerial user, prompting the user to enter specific information. Furthermore, if the user is in the technical department, the input unit can provide input guides related to technical details and project progress. For example, the input unit can present questions related to technical issues and project progress to a user in the technical department, prompting the user to enter detailed information. Furthermore, if the user is in the sales department, the input unit can provide input guides related to interactions with customers and sales performance. For example, the input unit can present questions related to interactions with customers and sales performance to a user in the sales department, prompting the user to enter specific information. This allows for more appropriate input by providing input guides tailored to the user's position or department. Some or all of the above-described processing in the input unit may be performed using or without a generation AI. For example, the input unit can input data related to the user's position or department into a generation AI, which can then customize the input guide based on that data.

[0038] The input unit can prioritize input of highly relevant episodes based on the user's geographical location information. For example, when the user is at the head office, the input unit guides the user to prioritize input of episodes related to the head office. For example, when the user is at the head office, the input unit can prioritize questions related to events and episodes related to the head office and prompt the user to input specific information. Furthermore, when the user is at a branch office, the input unit can guide the user to prioritize input of episodes related to the branch office. For example, when the user is at the branch office, the input unit can prioritize questions related to events and episodes related to the branch office and prompt the user to input detailed information. Furthermore, when the user is on a business trip, the input unit can guide the user to prioritize input of episodes related to the business trip destination. For example, when the user is on a business trip, the input unit can prioritize questions related to events and episodes related to the business trip destination and prompt the user to input specific information. This prioritizes input of highly relevant episodes based on the user's geographical location information, enabling more appropriate input. Some or all of the above-described processing in the input unit may be performed using or without a generation AI. For example, the input unit can input the user's geographical location information to the generation AI, and the generation AI can prioritize inputting highly relevant episodes based on that data.

[0039] The input unit can analyze the user's social media activity and input related episodes. The input unit, for example, automatically inputs episodes shared by the user on social media. For example, the input unit can analyze posts shared by the user on social media and automatically input the episodes. The input unit can also input projects and events mentioned by the user on social media. For example, the input unit can collect information about projects and events mentioned by the user on social media and input the episodes. The input unit can also suggest related episodes from the user's social media activity. For example, the input unit can analyze the user's social media activity, suggest related episodes, and prompt the user to input them. This allows related episodes to be efficiently input by analyzing the user's social media activity. Some or all of the above-mentioned processing in the input unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the input unit can input data about the user's social media activity to a generation AI, and the generation AI can input related episodes based on the data.

[0040] The image generation unit can maintain consistency of the generated image based on past image data. For example, the image generation unit generates a new image in the same style as a previously generated image. For example, the image generation unit can reference the style or design of a previously generated image and generate a new image that matches it. The image generation unit can also generate an image with the same theme based on past image data. For example, the image generation unit can reference photos from past projects or images from official events and generate a new image with the same theme based on the images. Furthermore, the image generation unit can generate a new image using color tones and composition that match the past image data. For example, the image generation unit can analyze the color tones and composition of the past image data and generate a new image that matches the color tones and composition. In this way, by referencing the past image data, consistency of the generated image can be maintained. Some or all of the above-mentioned processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input past image data into a generation AI, and the generation AI can generate a new image based on that data.

[0041] The image generation unit can adjust the specificity of the image based on the importance of the episode. For example, the image generation unit generates a detailed image for an important episode. For example, the image generation unit can generate an image that is depicted in detail based on detailed information about an important episode. The image generation unit can also generate a simplified image for a general episode. For example, the image generation unit can generate an image with a simplified image based on information about a general episode. Furthermore, the image generation unit can generate multiple detailed images for a particularly important episode. For example, the image generation unit can generate detailed images depicted from multiple perspectives based on information about a particularly important episode. This allows for adjusting the level of detail of the image according to the importance of the episode, thereby generating a more appropriate image. Some or all of the above-mentioned processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input data about the importance of the episode to the generation AI, and the generation AI can adjust the level of detail of the image based on that data.

[0042] The image generation unit can generate highly relevant images based on the user's geographical location information. For example, when the user is at the head office, the image generation unit generates an image related to the head office. For example, when the user is at the head office, the image generation unit can generate an image depicting the interior of the head office building or office. Furthermore, when the user is at a branch office, the image generation unit can generate an image related to the branch office. For example, when the user is at the branch office, the image generation unit can generate an image depicting the interior of the branch office building or office. Furthermore, when the user is on a business trip, the image generation unit can generate an image related to the business trip destination. For example, when the user is on a business trip, the image generation unit can generate an image depicting the scenery or buildings of the business trip destination. In this way, by generating highly relevant images based on the user's geographical location information, more appropriate images can be generated. Some or all of the above-described processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input the user's geographical location information into the generation AI, and the generation AI can generate highly relevant images based on that data.

[0043] The image generation unit can analyze a user's social media activity and generate related images. For example, the image generation unit can generate new images based on images shared by the user on social media. For example, the image generation unit can analyze posts shared by the user on social media and generate new images based on the content. The image generation unit can also generate images related to events or projects mentioned by the user on social media. For example, the image generation unit can collect information about events or projects mentioned by the user on social media and generate new images based on the content. Furthermore, the image generation unit can suggest related images based on the user's social media activity. For example, the image generation unit can analyze the user's social media activity, suggest related images, and prompt the user to select one. This makes it possible to efficiently generate related images by analyzing the user's social media activity. Some or all of the above-described processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input data about the user's social media activity into a generation AI, which can then generate related images based on the data.

[0044] The sentence generation unit can maintain consistency of the generated sentence based on past sentence data. For example, the sentence generation unit generates new sentence in the same style as previously generated sentence. For example, the sentence generation unit can refer to the style and tone of previously generated sentence and generate new sentence that matches the style and tone. The sentence generation unit can also generate sentences on the same theme based on past sentence data. For example, the sentence generation unit can refer to past reports, emails, or presentation materials and generate new sentences on the same theme based on them. Furthermore, the sentence generation unit can generate new sentences using tones and expressions that match the past sentence data. For example, the sentence generation unit can analyze the tone and expressions of past sentence data and generate new sentences that match the tone and expressions. In this way, by referring to the past sentence data, consistency of the generated sentences can be maintained. Some or all of the above-mentioned processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input past sentence data into a generation AI, and the generation AI can generate new sentences based on that data.

[0045] The sentence generation unit can adjust the specificity of the sentence based on the importance of the episode. For example, the sentence generation unit generates detailed sentences for important episodes. For example, the sentence generation unit can generate sentences that describe in detail based on detailed information about important episodes. The sentence generation unit can also generate simplified sentences for general episodes. For example, the sentence generation unit can generate sentences with simplified images based on information about general episodes. The sentence generation unit can also generate multiple detailed sentences for particularly important episodes. For example, the sentence generation unit can generate detailed sentences that describe from multiple perspectives based on information about particularly important episodes. This allows for adjusting the level of detail of the sentences according to the importance of the episodes, thereby generating more appropriate sentences. Some or all of the above-mentioned processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input data on the importance of episodes to the generation AI, and the generation AI can adjust the level of detail of the sentences based on that data.

[0046] The sentence generation unit can generate highly relevant sentences based on the user's geographical location information. For example, when the user is at the head office, the sentence generation unit generates sentences about episodes related to the head office. For example, when the user is at the head office, the sentence generation unit can generate sentences about events and episodes related to the head office. Furthermore, when the user is at a branch office, the sentence generation unit can generate sentences about episodes related to the branch office. For example, when the user is at the branch office, the sentence generation unit can generate sentences about events and episodes related to the branch office. Furthermore, when the user is on a business trip, the sentence generation unit can generate sentences about episodes related to the business trip destination. For example, when the user is on a business trip, the sentence generation unit can generate sentences about events and episodes related to the business trip destination. In this way, by generating highly relevant sentences based on the user's geographical location information, more appropriate sentences can be generated. Some or all of the above-mentioned processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input the user's geographical location information into the generation AI, and the generation AI can generate highly relevant sentences based on that data.

[0047] The sentence generation unit can analyze a user's social media activity and generate related sentences. The sentence generation unit can generate new sentences based on, for example, episodes shared by the user on social media. For example, the sentence generation unit can analyze posts shared by the user on social media and generate new sentences based on the content. The sentence generation unit can also generate sentences related to projects or events mentioned by the user on social media. For example, the sentence generation unit can collect information about projects or events mentioned by the user on social media and generate new sentences based on the content. Furthermore, the sentence generation unit can suggest related episodes from the user's social media activity. For example, the sentence generation unit can analyze the user's social media activity, suggest related episodes, and prompt the user to select one. This allows for efficient generation of related sentences by analyzing the user's social media activity. Some or all of the above-described processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input data about the user's social media activity into a generation AI, which can then generate related sentences based on the data.

[0048] The provision unit can maintain consistency of the content provided based on past provision data. For example, the provision unit can provide new content in the same style as previously provided content. For example, the provision unit can refer to the style and tone of previously provided content and provide new content that matches that style and tone. The provision unit can also provide content on the same theme based on the past provision data. For example, the provision unit can refer to past presentations, reports, and event materials and provide new content on the same theme based on that style and tone. The provision unit can also provide new content using a tone and expression that matches the previously provided data. For example, the provision unit can analyze the tone and expression of the previously provided data and provide new content that matches that tone and expression. This allows consistency of the content provided to be maintained by referring to the previously provided data. Some or all of the above-described processing in the provision unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the provision unit can input previously provided data into a generation AI, which can then provide new content based on that data.

[0049] The providing unit can adjust the specificity of the provision based on the importance of the content. For example, the providing unit provides detailed information for important content. For example, the providing unit can provide detailed information based on detailed information about the important content. The providing unit can also provide simplified information for general content. For example, the providing unit can provide simplified information based on information about general content. Furthermore, the providing unit can provide multiple pieces of detailed information for particularly important content. For example, the providing unit can provide detailed information described from multiple perspectives based on information about particularly important content. This enables more appropriate provision by adjusting the level of detail provided according to the importance of the content. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input data on the importance of the content to the generation AI, and the generation AI can adjust the level of detail provided based on that data.

[0050] The providing unit can provide highly relevant content based on the user's geographical location information. For example, when the user is at the head office, the providing unit can provide content related to the head office. For example, when the user is at the head office, the providing unit can provide information about the interior of the head office building or office. Furthermore, when the user is at a branch office, the providing unit can provide content related to the branch office. For example, when the user is at the branch office, the providing unit can provide information about the interior of the branch office building or office. Furthermore, when the user is on a business trip, the providing unit can provide content related to the business trip destination. For example, when the user is on a business trip, the providing unit can provide information about the scenery and buildings of the business trip destination. This enables more appropriate content to be provided by providing highly relevant content based on the user's geographical location information. Some or all of the above-described processing by the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's geographical location information into the generation AI, and the generation AI can provide highly relevant content based on that data.

[0051] The providing unit can analyze a user's social media activity and provide related content. The providing unit can, for example, provide new content based on episodes shared by the user on social media. For example, the providing unit can analyze posts shared by the user on social media and provide new content based on the content. The providing unit can also provide content related to projects or events mentioned by the user on social media. For example, the providing unit can collect information about projects or events mentioned by the user on social media and provide new content based on the content. The providing unit can also suggest related episodes from the user's social media activity. For example, the providing unit can analyze the user's social media activity, suggest related episodes, and prompt the user to select one. This makes it possible to efficiently provide related content by analyzing the user's social media activity. Some or all of the above-described processing by the providing unit can be performed using a generation AI, or can be performed without using a generation AI. For example, the providing unit can input data about the user's social media activity into a generation AI, which can then provide related content based on the data.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The corporate history compilation system can further include an audio generation unit. The audio generation unit can generate relevant audio based on the content of the input corporate history. For example, based on anecdotes from the company's founding, audio of an interview with the founder and environmental sounds from that time can be generated. Also, based on success stories of important projects, audio of interviews with project members and narration explaining the progress of the project can be generated. Furthermore, the audio generation unit can play the generated audio at internal events and external public events. This can further enhance the appeal of the corporate history by providing auditory information in addition to visual and written information.

[0054] The image generation unit can add interactive elements to the generated image. For example, the user can add comments or tags to the generated image. The image generation unit can also provide a function that allows the user to rate the generated image. Furthermore, the image generation unit can also provide a function that allows the user to share the generated image with other users. This allows the user to actively participate in the generated image, further enhancing the appeal of the company history.

[0055] The text generation unit can add interactive elements to the generated text. For example, the user can add comments or tags to the generated text. The text generation unit can also provide a function that allows the user to rate the generated text. Furthermore, the text generation unit can also provide a function that allows the user to share the generated text with other users. This allows the user to actively participate in the generated text, further enhancing the appeal of the company history.

[0056] The providing unit can provide the generated content in multiple languages. For example, the generated images and text can be translated into multiple languages ​​such as English, Chinese, and Spanish and provided. The providing unit can also provide an interface for displaying the generated content in multiple languages. Furthermore, the providing unit can automatically translate and display the content based on a language selected by a user. In this way, providing the content of the company history in multiple languages ​​can enhance the appeal of the company history from an international perspective.

[0057] The input unit can check the consistency of the input content based on past company history data. For example, it can automatically check whether the episodes entered by the user are consistent with past company history data. In addition, if the content entered by the user matches the past company history data, it can automatically complete the content. Furthermore, if the content entered by the user differs from the past company history data, it can suggest corrections. In this way, the consistency of the input content can be maintained by referring to the past company history data.

[0058] The input unit can customize input guides based on the user's job title or department. For example, if the user is a manager, input guides regarding important projects and strategic decisions can be provided. If the user is in the technical department, input guides regarding technical details and project progress can be provided. Furthermore, if the user is in the sales department, input guides regarding interactions with customers and sales results can be provided. This allows for more appropriate input by providing input guides according to the user's job title or department.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The input section inputs the details of the company history. The details of the company history include the history of the company's founding, important events, and examples of successful projects. For example, enter details of episodes from the company's founding and examples of successful projects. Step 2: The image generation unit uses generative AI to generate relevant images based on the content entered by the input unit. For example, it generates a portrait of the company's original office or founder based on anecdotes from the company's founding. It also generates project deliverables and group photos of the project team based on key project success stories. Step 3: The text generation unit uses AI to generate text in a variety of expressions based on the content entered by the input unit. For example, it might write an inspiring story about the company's founding, or a humorous anecdote about the success of an important project. Step 4: The provision department provides the generated images and text. For example, the generated images and text can be introduced at an internal event to attract participants' attention and increase interest in the company's history. Furthermore, when released to the public, providing rich content both visually and textually can have an impact on society and lead to a change in attitudes toward work.

[0061] (Example 2) A corporate history compilation system according to an embodiment of the present invention utilizes image generation AI and language generation AI to revolutionize the traditional image of corporate history compilation and provide new and interesting content both inside and outside the company. This system allows users to input the content of a company history. The image generation AI generates related images based on the content, and the language generation AI then translates the content into text using a variety of expressions, enriching the company history visually and writtenly. This eliminates the traditional image of a dull and boring company history, providing new interest to both inside and outside the company, and potentially leading to a change in attitudes toward work. For example, when inputting the content of a company history, users enter detailed descriptions of each episode and important milestone in the history. For example, they can input stories from the company's founding and success stories of important projects. This information is then input into the image generation AI and language generation AI. The image generation AI then generates related images based on the input content. For example, based on a story from the company's founding, it generates a picture of the company's office at the time of its founding and a portrait of the founder. Based on success stories of important projects, it can also generate project deliverables and group photos of the project team. This visually enriches the company history. Furthermore, the language generation AI then translates the input content into text using a variety of expressions. For example, an episode from the company's founding can be written as an inspiring story, or a success story from an important project can be written as a humorous anecdote. This enriches the text of the company history, making it more interesting for readers. This system can completely change the traditional image of compiling a company history as dull and boring, providing new excitement both inside and outside the company. For example, when introducing a company history at an internal event, using the generated images and text can attract participants' attention and increase their interest in the history. Furthermore, when making the company history public, providing rich content both visually and textually can have an impact on society and lead to a change in attitudes toward work. In this way, the company history compilation system enriches the content of company histories visually and textually, dispelling the traditional image of them as dull and boring.

[0062] A company history compilation system according to an embodiment includes an input unit, an image generation unit, a text generation unit, and a provision unit. The input unit inputs the content of the company history. The content of the company history includes, but is not limited to, the company's founding history, important events, and project success stories. The input unit can input, for example, detailed information about each episode and important event in the company history. For example, the input unit inputs information about the company's founding and important project success stories. This information is input to an image generation AI and a language generation AI. The image generation unit uses the generation AI to generate related images based on the content input by the input unit. For example, the image generation unit generates an office at the time of the company's founding and a portrait of the founder based on the founding episodes. The image generation unit can also generate project deliverables and group photos of the project team based on important project success stories. For example, the image generation unit generates the office layout and equipment at the time of the company's founding and a portrait of the founder. Project deliverables include, for example, products, services, and reports. Project team group photos include, for example, official group photos and photos of the team working together. The text generation unit uses a generation AI to generate text in a variety of expressions based on the content input by the input unit. The text generation unit, for example, writes an episode from the company's founding as an inspiring story. The text generation unit can also write a success story of an important project as a humorous story. For example, the text generation unit writes an episode from the company's founding as an inspiring story and a success story of an important project as a humorous story. The provision unit provides the generated images and text. The provision unit, for example, introduces the generated images and text at an internal event. The provision unit can also make the generated images and text publicly available. For example, the provision unit introduces the generated images and text at an internal event to attract participants' attention and increase interest in the company history. When publicly available, providing content that is rich in both visual and textual content can have an impact on society and lead to a change in attitudes toward work. As a result, the corporate history compilation system according to the embodiment can enrich the content of company histories visually and textually, dispelling the conventional image of them as dull and boring.

[0063] The image generation unit can generate the office or a portrait of the founder at the time of the company's founding based on the episodes from the company's founding. The image generation unit can, for example, generate the layout and equipment of the office at the time of the company's founding and a portrait of the founder based on the episodes from the company's founding. For example, the image generation unit can recreate the layout of the office at the time of the company's founding and depict the equipment and furniture from that time in detail. The image generation unit can also generate a portrait of the founder and faithfully reproduce his or her features. This visually recreates the episodes from the company's founding, thereby enhancing the appeal of the company's history. Some or all of the above-mentioned processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input data on the office layout and equipment at the time of the company's founding into the generation AI, and the generation AI can generate an image based on that data.

[0064] The image generation unit can generate a group photo of the project deliverables or the project team based on important project success stories. For example, the image generation unit can depict the project deliverables in detail and visually express the features of the product or service. The image generation unit can also generate a group photo of the project team, faithfully reproducing the faces and postures of the team members. This visually reproduces the success stories of important projects, thereby enhancing the appeal of the company history. Some or all of the above-described processing in the image generation unit may be performed using or without a generation AI. For example, the image generation unit can input data on the project deliverables or the project team into the generation AI, which then generates an image based on the data.

[0065] The text generation unit can write down the founding episode as an emotional story. For example, the text generation unit can write down the founding episode as a moving story. For example, the text generation unit can generate a story that moves the reader by describing the founder's struggles and efforts. The text generation unit can also write down the founding episode as a humorous story. For example, the text generation unit can generate a story that describes humorous events and episodes of the founder and provides laughter to the reader. This can enhance the appeal of the company history by portraying the founding episode in a moving way. Some or all of the above-described processing in the text generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the text generation unit can input data on the founding episode into the generation AI, which can then generate a moving story based on that data.

[0066] The text generation unit can write down success stories of important projects as funny anecdotes. For example, the text generation unit can write down success stories of important projects as humorous anecdotes. For example, the text generation unit can generate stories that describe humorous events and anecdotes that occurred during the progress of the project to make readers laugh. The text generation unit can also generate stories that humorously describe the struggles and efforts that led to the project's success to attract readers' interest. This makes it possible to humorously portray success stories of important projects and enhance the appeal of the company history. Some or all of the above-mentioned processing in the text generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the text generation unit can input data on success stories of projects into a generation AI, which can then generate humorous anecdotes based on that data.

[0067] The provision unit can introduce the generated images and text at internal company events. For example, the provision unit can introduce the generated images and text at internal company events. For example, the provision unit can introduce the generated content at events such as internal meetings, training sessions, and parties to attract participants' interest and increase interest in the company's history. The provision unit can also provide the generated images and text in digital format. For example, the provision unit can provide the generated content as a website or presentation materials so that participants can access it at any time. In this way, introducing the generated content at internal company events can increase interest in the company's history. Some or all of the above-mentioned processing in the provision unit may be performed using or without the generation AI. For example, the provision unit can input the generated content into the generation AI, and the generation AI can suggest how to introduce it at the event based on that data.

[0068] The providing unit can publish the generated images and text outside the company. For example, the providing unit publishes the generated images and text outside the company. For example, the providing unit can publish the generated content on a website, in a press release, on social media, etc., to have an impact on society and lead to a change in attitudes toward work. The providing unit can also provide the generated images and text as printed materials. For example, the providing unit can print the generated content as a pamphlet or report and distribute it to relevant parties outside the company. In this way, publishing it outside the company can have an impact on society and lead to a change in attitudes toward work. Some or all of the above-mentioned processing in the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the generated content into a generation AI, and the generation AI can suggest a publication method based on that data.

[0069] The input unit can estimate the user's emotions and adjust the specificity of the input content based on the estimated user emotions. For example, when the user is excited, the input unit provides detailed input options, allowing the user to input even the smallest details of the episode. For example, when the user is excited, the input unit can present detailed questions to prompt the user to input specific information. Furthermore, when the user is tired, the input unit can provide simplified input options, allowing the user to input only the minimum necessary information. For example, when the user is tired, the input unit can present simple options to allow the user to complete input in a short time. Furthermore, when the user is relaxed, the input unit can provide customizable input options, allowing the user to proceed with input at their own pace. For example, when the user is relaxed, the input unit can provide a free-form input option, allowing the user to input the episode in their own words. This allows the level of detail of the input content to be adjusted according to the user's emotions, enabling more appropriate input. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using or without the generation AI. For example, the input unit may input user emotion data to the generation AI, and the generation AI may adjust the level of detail of the input content based on that data.

[0070] The input unit can check the consistency of the input content based on past company history data. For example, the input unit automatically checks whether an episode entered by a user is consistent with past company history data. For example, the input unit can compare an episode entered by a user with past company history data to check for inconsistencies. The input unit can also automatically complete the content entered by a user if it matches past company history data. For example, the input unit can automatically add detailed information related to the episode if the episode entered by a user matches past company history data. Furthermore, the input unit can suggest corrections if the content entered by a user differs from past company history data. For example, if the episode entered by a user differs from past company history data, the input unit can suggest corrections to the episode and ask the user for confirmation. This allows the consistency of the input content to be maintained by referring to past company history data. Some or all of the above-mentioned processing in the input unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the input unit can input past company history data into a generation AI, and the generation AI can check the consistency of the input content based on that data.

[0071] The input unit can customize input guides based on the user's position or department. For example, if the user is a manager, the input unit provides input guides related to important projects and strategic decisions. For example, the input unit can present detailed questions related to project progress and strategic decisions to a managerial user, prompting the user to enter specific information. Furthermore, if the user is in the technical department, the input unit can provide input guides related to technical details and project progress. For example, the input unit can present questions related to technical issues and project progress to a user in the technical department, prompting the user to enter detailed information. Furthermore, if the user is in the sales department, the input unit can provide input guides related to interactions with customers and sales performance. For example, the input unit can present questions related to interactions with customers and sales performance to a user in the sales department, prompting the user to enter specific information. This allows for more appropriate input by providing input guides tailored to the user's position or department. Some or all of the above-described processing in the input unit may be performed using or without a generation AI. For example, the input unit can input data related to the user's position or department into a generation AI, which can then customize the input guide based on that data.

[0072] The input unit can estimate the user's emotions and determine the importance of input content based on the estimated user emotions. For example, when the user is in a hurry, the input unit guides the user to input important episodes first. For example, when the user is in a hurry, the input unit can prioritize questions related to important episodes, allowing the user to complete the input quickly. The input unit can also guide the user to sequentially input detailed episodes when the user is relaxed. For example, when the user is relaxed, the input unit can sequentially present detailed questions, allowing the user to input even the smallest details of the episodes. Furthermore, when the user is excited, the input unit can guide the user to prioritize input of emotional episodes. For example, when the user is excited, the input unit can prioritize questions related to emotional episodes, allowing the user to input content that reflects the user's heightened emotions. This allows the user to prioritize input content according to the user's emotions, thereby enabling more appropriate input. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using or without the generation AI. For example, the input unit may input user emotion data to the generation AI, and the generation AI may determine the priority of the input content based on that data.

[0073] The input unit can prioritize input of highly relevant episodes based on the user's geographical location information. For example, when the user is at the head office, the input unit guides the user to prioritize input of episodes related to the head office. For example, when the user is at the head office, the input unit can prioritize questions related to events and episodes related to the head office and prompt the user to input specific information. Furthermore, when the user is at a branch office, the input unit can guide the user to prioritize input of episodes related to the branch office. For example, when the user is at the branch office, the input unit can prioritize questions related to events and episodes related to the branch office and prompt the user to input detailed information. Furthermore, when the user is on a business trip, the input unit can guide the user to prioritize input of episodes related to the business trip destination. For example, when the user is on a business trip, the input unit can prioritize questions related to events and episodes related to the business trip destination and prompt the user to input specific information. This prioritizes input of highly relevant episodes based on the user's geographical location information, enabling more appropriate input. Some or all of the above-described processing in the input unit may be performed using or without a generation AI. For example, the input unit can input the user's geographical location information to the generation AI, and the generation AI can prioritize inputting highly relevant episodes based on that data.

[0074] The input unit can analyze the user's social media activity and input related episodes. The input unit, for example, automatically inputs episodes shared by the user on social media. For example, the input unit can analyze posts shared by the user on social media and automatically input the episodes. The input unit can also input projects and events mentioned by the user on social media. For example, the input unit can collect information about projects and events mentioned by the user on social media and input the episodes. The input unit can also suggest related episodes from the user's social media activity. For example, the input unit can analyze the user's social media activity, suggest related episodes, and prompt the user to input them. This allows related episodes to be efficiently input by analyzing the user's social media activity. Some or all of the above-mentioned processing in the input unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the input unit can input data about the user's social media activity to a generation AI, and the generation AI can input related episodes based on the data.

[0075] The image generation unit can estimate the user's emotion and adjust the design of the generated image based on the estimated user's emotion. For example, when the user is relaxed, the image generation unit generates an image with soft colors. For example, when the user is relaxed, the image generation unit can generate an image with soft colors and a calm design. Furthermore, when the user is excited, the image generation unit can generate an image with vivid colors. For example, when the user is excited, the image generation unit can generate an image with vivid colors and a dynamic design. Furthermore, when the user is sad, the image generation unit can generate an image with calm colors and a calm design. This allows for adjusting the style of the image according to the user's emotion to generate a more appropriate image. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the image generation unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the image generation unit can input the user's emotional data into the generation AI, which can then adjust the image design based on that data.

[0076] The image generation unit can maintain consistency of the generated image based on past image data. For example, the image generation unit generates a new image in the same style as a previously generated image. For example, the image generation unit can reference the style or design of a previously generated image and generate a new image that matches it. The image generation unit can also generate an image with the same theme based on past image data. For example, the image generation unit can reference photos from past projects or images from official events and generate a new image with the same theme based on the images. Furthermore, the image generation unit can generate a new image using color tones and composition that match the past image data. For example, the image generation unit can analyze the color tones and composition of the past image data and generate a new image that matches the color tones and composition. In this way, by referencing the past image data, consistency of the generated image can be maintained. Some or all of the above-mentioned processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input past image data into a generation AI, and the generation AI can generate a new image based on that data.

[0077] The image generation unit can adjust the specificity of the image based on the importance of the episode. For example, the image generation unit generates a detailed image for an important episode. For example, the image generation unit can generate an image that is depicted in detail based on detailed information about an important episode. The image generation unit can also generate a simplified image for a general episode. For example, the image generation unit can generate an image with a simplified image based on information about a general episode. Furthermore, the image generation unit can generate multiple detailed images for a particularly important episode. For example, the image generation unit can generate detailed images depicted from multiple perspectives based on information about a particularly important episode. This allows for adjusting the level of detail of the image according to the importance of the episode, thereby generating a more appropriate image. Some or all of the above-mentioned processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input data about the importance of the episode to the generation AI, and the generation AI can adjust the level of detail of the image based on that data.

[0078] The image generation unit can estimate the user's emotion and determine the importance of the image to be generated based on the estimated user's emotion. For example, when the user is excited, the image generation unit prioritizes generating visually stimulating images. For example, when the user is excited, the image generation unit can prioritize generating images with visually stimulating designs and color tones. Furthermore, when the user is relaxed, the image generation unit can prioritize generating calming images. For example, when the user is relaxed, the image generation unit can prioritize generating images with calming designs and color tones. Furthermore, when the user is sad, the image generation unit can prioritize generating images that soothe emotions. For example, when the user is sad, the image generation unit can prioritize generating images with soothing designs and color tones. This allows for generating more appropriate images by determining the priority of images according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit may input user emotion data into the generation AI, and the generation AI may determine the priority of images based on that data.

[0079] The image generation unit can generate highly relevant images based on the user's geographical location information. For example, when the user is at the head office, the image generation unit generates an image related to the head office. For example, when the user is at the head office, the image generation unit can generate an image depicting the interior of the head office building or office. Furthermore, when the user is at a branch office, the image generation unit can generate an image related to the branch office. For example, when the user is at the branch office, the image generation unit can generate an image depicting the interior of the branch office building or office. Furthermore, when the user is on a business trip, the image generation unit can generate an image related to the business trip destination. For example, when the user is on a business trip, the image generation unit can generate an image depicting the scenery or buildings of the business trip destination. In this way, by generating highly relevant images based on the user's geographical location information, more appropriate images can be generated. Some or all of the above-described processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input the user's geographical location information into the generation AI, and the generation AI can generate highly relevant images based on that data.

[0080] The image generation unit can analyze a user's social media activity and generate related images. For example, the image generation unit can generate new images based on images shared by the user on social media. For example, the image generation unit can analyze posts shared by the user on social media and generate new images based on the content. The image generation unit can also generate images related to events or projects mentioned by the user on social media. For example, the image generation unit can collect information about events or projects mentioned by the user on social media and generate new images based on the content. Furthermore, the image generation unit can suggest related images based on the user's social media activity. For example, the image generation unit can analyze the user's social media activity, suggest related images, and prompt the user to select one. This makes it possible to efficiently generate related images by analyzing the user's social media activity. Some or all of the above-described processing in the image generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the image generation unit can input data about the user's social media activity into a generation AI, which can then generate related images based on the data.

[0081] The sentence generation unit can estimate the user's emotions and adjust the tone of the sentences based on the estimated user emotions. For example, when the user is relaxed, the sentence generation unit generates sentences with a soft tone. For example, when the user is relaxed, the sentence generation unit can generate sentences with a soft tone or gentle expressions. Furthermore, when the user is excited, the sentence generation unit can generate sentences with a strong tone. For example, when the user is excited, the sentence generation unit can generate sentences with a strong tone or dynamic expressions. Furthermore, when the user is sad, the sentence generation unit can generate sentences with a comforting tone or gentle expressions. In this way, by adjusting the tone of the sentences according to the user's emotions, more appropriate sentences can be generated. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit may input user emotional data into the generation AI, which may then adjust the tone of the sentence based on that data.

[0082] The sentence generation unit can maintain consistency of the generated sentence based on past sentence data. For example, the sentence generation unit generates new sentence in the same style as previously generated sentence. For example, the sentence generation unit can refer to the style and tone of previously generated sentence and generate new sentence that matches the style and tone. The sentence generation unit can also generate sentences on the same theme based on past sentence data. For example, the sentence generation unit can refer to past reports, emails, or presentation materials and generate new sentences on the same theme based on them. Furthermore, the sentence generation unit can generate new sentences using tones and expressions that match the past sentence data. For example, the sentence generation unit can analyze the tone and expressions of past sentence data and generate new sentences that match the tone and expressions. In this way, by referring to the past sentence data, consistency of the generated sentences can be maintained. Some or all of the above-mentioned processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input past sentence data into a generation AI, and the generation AI can generate new sentences based on that data.

[0083] The sentence generation unit can adjust the specificity of the sentence based on the importance of the episode. For example, the sentence generation unit generates detailed sentences for important episodes. For example, the sentence generation unit can generate sentences that describe in detail based on detailed information about important episodes. The sentence generation unit can also generate simplified sentences for general episodes. For example, the sentence generation unit can generate sentences with simplified images based on information about general episodes. The sentence generation unit can also generate multiple detailed sentences for particularly important episodes. For example, the sentence generation unit can generate detailed sentences that describe from multiple perspectives based on information about particularly important episodes. This allows for adjusting the level of detail of the sentences according to the importance of the episodes, thereby generating more appropriate sentences. Some or all of the above-mentioned processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input data on the importance of episodes to the generation AI, and the generation AI can adjust the level of detail of the sentences based on that data.

[0084] The sentence generation unit can estimate the user's emotions and determine the importance of sentences to be generated based on the estimated user emotions. For example, when the user is excited, the sentence generation unit prioritizes emotional episodes in the sentence. For example, when the user is excited, the sentence generation unit can prioritize information about emotional episodes in the sentence. Furthermore, when the user is relaxed, the sentence generation unit can sequentially generate detailed episodes in the sentence. For example, when the user is relaxed, the sentence generation unit can sequentially generate detailed episodes in the sentence. Furthermore, when the user is sad, the sentence generation unit can prioritize episodes that soothe the user's emotions in the sentence. For example, when the user is sad, the sentence generation unit can prioritize information about episodes that soothe the user's emotions in the sentence. This allows for generating more appropriate sentences by determining the priority of sentences according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit may input user emotion data into the generation AI, and the generation AI may determine the priority of sentences based on that data.

[0085] The sentence generation unit can generate highly relevant sentences based on the user's geographical location information. For example, when the user is at the head office, the sentence generation unit generates sentences about episodes related to the head office. For example, when the user is at the head office, the sentence generation unit can generate sentences about events and episodes related to the head office. Furthermore, when the user is at a branch office, the sentence generation unit can generate sentences about episodes related to the branch office. For example, when the user is at the branch office, the sentence generation unit can generate sentences about events and episodes related to the branch office. Furthermore, when the user is on a business trip, the sentence generation unit can generate sentences about episodes related to the business trip destination. For example, when the user is on a business trip, the sentence generation unit can generate sentences about events and episodes related to the business trip destination. In this way, by generating highly relevant sentences based on the user's geographical location information, more appropriate sentences can be generated. Some or all of the above-mentioned processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input the user's geographical location information into the generation AI, and the generation AI can generate highly relevant sentences based on that data.

[0086] The sentence generation unit can analyze a user's social media activity and generate related sentences. The sentence generation unit can generate new sentences based on, for example, episodes shared by the user on social media. For example, the sentence generation unit can analyze posts shared by the user on social media and generate new sentences based on the content. The sentence generation unit can also generate sentences related to projects or events mentioned by the user on social media. For example, the sentence generation unit can collect information about projects or events mentioned by the user on social media and generate new sentences based on the content. Furthermore, the sentence generation unit can suggest related episodes from the user's social media activity. For example, the sentence generation unit can analyze the user's social media activity, suggest related episodes, and prompt the user to select one. This allows for efficient generation of related sentences by analyzing the user's social media activity. Some or all of the above-described processing in the sentence generation unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the sentence generation unit can input data about the user's social media activity into a generation AI, which can then generate related sentences based on the data.

[0087] The providing unit can estimate the user's emotion and adjust the display format of the content based on the estimated user's emotion. For example, when the user is relaxed, the providing unit displays the content in an interface with soft colors. For example, when the user is relaxed, the providing unit can display the content in an interface with soft colors and a calm design. Furthermore, when the user is excited, the providing unit can display the content in an interface with vivid colors. For example, when the user is excited, the providing unit can display the content in an interface with vivid colors and a dynamic design. Furthermore, when the user is sad, the providing unit can display the content in an interface with subdued colors. For example, when the user is sad, the providing unit can display the content in an interface with subdued colors and a calm design. This allows for more appropriate display by adjusting the content display method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit may input user emotion data to the generation AI, and the generation AI may adjust the display format of the content based on that data.

[0088] The provision unit can maintain consistency of the content provided based on past provision data. For example, the provision unit can provide new content in the same style as previously provided content. For example, the provision unit can refer to the style and tone of previously provided content and provide new content that matches that style and tone. The provision unit can also provide content on the same theme based on the past provision data. For example, the provision unit can refer to past presentations, reports, and event materials and provide new content on the same theme based on that style and tone. The provision unit can also provide new content using a tone and expression that matches the previously provided data. For example, the provision unit can analyze the tone and expression of the previously provided data and provide new content that matches that tone and expression. This allows consistency of the content provided to be maintained by referring to the previously provided data. Some or all of the above-described processing in the provision unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the provision unit can input previously provided data into a generation AI, which can then provide new content based on that data.

[0089] The providing unit can adjust the specificity of the provision based on the importance of the content. For example, the providing unit provides detailed information for important content. For example, the providing unit can provide detailed information based on detailed information about the important content. The providing unit can also provide simplified information for general content. For example, the providing unit can provide simplified information based on information about general content. Furthermore, the providing unit can provide multiple pieces of detailed information for particularly important content. For example, the providing unit can provide detailed information described from multiple perspectives based on information about particularly important content. This enables more appropriate provision by adjusting the level of detail provided according to the importance of the content. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit can input data on the importance of the content to the generation AI, and the generation AI can adjust the level of detail provided based on that data.

[0090] The providing unit can estimate the user's emotions and determine the importance of content to be provided based on the estimated user's emotions. For example, when the user is excited, the providing unit can prioritize providing visually stimulating content. For example, when the user is excited, the providing unit can prioritize providing content with visually stimulating designs and colors. Furthermore, when the user is relaxed, the providing unit can prioritize providing calming content. For example, when the user is relaxed, the providing unit can prioritize providing content with calming designs and colors. Furthermore, when the user is sad, the providing unit can prioritize providing content that soothes emotions. For example, when the user is sad, the providing unit can prioritize providing content with soothing designs and colors. This enables more appropriate content to be provided by determining the priority of content to be provided according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using or without the generation AI. For example, the providing unit may input user emotion data into the generation AI, and the generation AI may determine the priority of the content to be provided based on that data.

[0091] The providing unit can provide highly relevant content based on the user's geographical location information. For example, when the user is at the head office, the providing unit can provide content related to the head office. For example, when the user is at the head office, the providing unit can provide information about the interior of the head office building or office. Furthermore, when the user is at a branch office, the providing unit can provide content related to the branch office. For example, when the user is at the branch office, the providing unit can provide information about the interior of the branch office building or office. Furthermore, when the user is on a business trip, the providing unit can provide content related to the business trip destination. For example, when the user is on a business trip, the providing unit can provide information about the scenery and buildings of the business trip destination. This enables more appropriate content to be provided by providing highly relevant content based on the user's geographical location information. Some or all of the above-described processing by the providing unit may be performed using a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the user's geographical location information into the generation AI, and the generation AI can provide highly relevant content based on that data.

[0092] The providing unit can analyze a user's social media activity and provide related content. The providing unit can, for example, provide new content based on episodes shared by the user on social media. For example, the providing unit can analyze posts shared by the user on social media and provide new content based on the content. The providing unit can also provide content related to projects or events mentioned by the user on social media. For example, the providing unit can collect information about projects or events mentioned by the user on social media and provide new content based on the content. The providing unit can also suggest related episodes from the user's social media activity. For example, the providing unit can analyze the user's social media activity, suggest related episodes, and prompt the user to select one. This makes it possible to efficiently provide related content by analyzing the user's social media activity. Some or all of the above-described processing by the providing unit can be performed using a generation AI, or can be performed without using a generation AI. For example, the providing unit can input data about the user's social media activity into a generation AI, which can then provide related content based on the data. === Hard Collateral 1-1 === Each of the multiple elements, including the input unit, image generation unit, text generation unit, and providing unit, described above, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the input unit can input the contents of a company history using the reception device 38 of the smart device 14. The image generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates related images based on the input contents. The text generation unit is implemented by the specific processing unit 290 of the data processing device 12 and converts the input contents into text using various expressions. The providing unit can provide the generated images and text using the output device 40 of the smart device 14. For example, the input unit can estimate the user's emotions and adjust the specificity of the input contents based on the estimated emotions. The emotion estimation is implemented by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the input unit, image generation unit, text generation unit, and providing unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the input unit can input the content of a company history using the microphone 238 of the smart glasses 214. The image generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a related image based on the input content. The text generation unit is realized by the specific processing unit 290 of the data processing device 12 and converts the input content into text using various expressions. The providing unit can provide the generated images and text using the speaker 240 of the smart glasses 214. For example, the input unit can estimate the user's emotions and adjust the specificity of the input content based on the estimated emotions. The emotion estimation is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements, including the input unit, image generation unit, text generation unit, and providing unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the input unit can input the content of the company history using the microphone 238 of the headset terminal 314. The image generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a related image based on the input content. The text generation unit is realized by the specific processing unit 290 of the data processing device 12 and converts the input content into text using various expressions. The providing unit can provide the generated images and text using the display 343 of the headset terminal 314. For example, the input unit can estimate the user's emotions and adjust the specificity of the input content based on the estimated emotions. The emotion estimation is realized by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements, including the input unit, image generation unit, text generation unit, and providing unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the input unit can input the content of the company history using the microphone 238 of the robot 414. The image generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a related image based on the input content. The text generation unit is realized by the specific processing unit 290 of the data processing device 12 and converts the input content into text using various expressions. The providing unit can provide the generated images and text using the speaker 240 of the robot 414. For example, the input unit can estimate the user's emotions and adjust the specificity of the input content based on the estimated emotions. The emotion estimation is realized by the specific processing unit 290 of the data processing device 12.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The corporate history compilation system can further include an audio generation unit. The audio generation unit can generate relevant audio based on the content of the input corporate history. For example, based on anecdotes from the company's founding, audio of an interview with the founder and environmental sounds from that time can be generated. Also, based on success stories of important projects, audio of interviews with project members and narration explaining the progress of the project can be generated. Furthermore, the audio generation unit can play the generated audio at internal events and external public events. This can further enhance the appeal of the corporate history by providing auditory information in addition to visual and written information.

[0095] The image generation unit can estimate the user's emotion and adjust the style of the image to be generated based on the estimated user's emotion. For example, if the user is relaxed, an image with soft colors and a calm design can be generated. If the user is excited, an image with vivid colors and a dynamic design can be generated. Furthermore, if the user is sad, an image with muted colors and a calm design can be generated. In this way, by adjusting the style of the image according to the user's emotion, more appropriate images can be generated.

[0096] The image generation unit can add interactive elements to the generated image. For example, the user can add comments or tags to the generated image. The image generation unit can also provide a function that allows the user to rate the generated image. Furthermore, the image generation unit can also provide a function that allows the user to share the generated image with other users. This allows the user to actively participate in the generated image, further enhancing the appeal of the company history.

[0097] The sentence generation unit can estimate the user's emotions and adjust the tone of the sentence based on the estimated user's emotions. For example, if the user is relaxed, a soft-toned sentence can be generated. If the user is excited, a powerful sentence can be generated. Furthermore, if the user is sad, a comforting sentence can be generated. In this way, by adjusting the tone of the sentence according to the user's emotions, more appropriate sentences can be generated.

[0098] The text generation unit can add interactive elements to the generated text. For example, the user can add comments or tags to the generated text. The text generation unit can also provide a function that allows the user to rate the generated text. Furthermore, the text generation unit can also provide a function that allows the user to share the generated text with other users. This allows the user to actively participate in the generated text, further enhancing the appeal of the company history.

[0099] The providing unit can estimate the user's emotion and adjust the display format of the content based on the estimated user's emotion. For example, if the user is relaxed, the content can be displayed in an interface with soft colors. If the user is excited, the content can be displayed in an interface with vivid colors. Furthermore, if the user is sad, the content can be displayed in an interface with subdued colors. This allows for more appropriate display by adjusting the content display method according to the user's emotion.

[0100] The providing unit can provide the generated content in multiple languages. For example, the generated images and text can be translated into multiple languages ​​such as English, Chinese, and Spanish and provided. The providing unit can also provide an interface for displaying the generated content in multiple languages. Furthermore, the providing unit can automatically translate and display the content based on a language selected by a user. In this way, providing the content of the company history in multiple languages ​​can enhance the appeal of the company history from an international perspective.

[0101] The input unit can estimate the user's emotions and adjust the specificity of the input content based on the estimated user's emotions. For example, if the user is excited, detailed input options are provided, allowing the user to input details of an episode. If the user is tired, simplified input options are provided, allowing the user to input only the minimum necessary information. Furthermore, if the user is relaxed, customizable input options are provided, allowing the user to proceed with input at their own pace. This allows the user to input more appropriately by adjusting the level of detail of the input content according to the user's emotions.

[0102] The input unit can check the consistency of the input content based on past company history data. For example, it can automatically check whether the episodes entered by the user are consistent with past company history data. In addition, if the content entered by the user matches the past company history data, it can automatically complete the content. Furthermore, if the content entered by the user differs from the past company history data, it can suggest corrections. In this way, the consistency of the input content can be maintained by referring to the past company history data.

[0103] The input unit can customize input guides based on the user's job title or department. For example, if the user is a manager, input guides regarding important projects and strategic decisions can be provided. If the user is in the technical department, input guides regarding technical details and project progress can be provided. Furthermore, if the user is in the sales department, input guides regarding interactions with customers and sales results can be provided. This allows for more appropriate input by providing input guides according to the user's job title or department.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The input section inputs the details of the company history. The details of the company history include the history of the company's founding, important events, and examples of successful projects. For example, enter details of episodes from the company's founding and examples of successful projects. Step 2: The image generation unit uses generative AI to generate relevant images based on the content entered by the input unit. For example, it generates a portrait of the company's original office or founder based on anecdotes from the company's founding. It also generates project deliverables and group photos of the project team based on key project success stories. Step 3: The text generation unit uses AI to generate text in a variety of expressions based on the content entered by the input unit. For example, it might write an inspiring story about the company's founding, or a humorous anecdote about the success of an important project. Step 4: The provision department provides the generated images and text. For example, the generated images and text can be introduced at an internal event to attract participants' attention and increase interest in the company's history. Furthermore, when released to the public, providing rich content both visually and textually can have an impact on society and lead to a change in attitudes toward work.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0124] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 7, a 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.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0150] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0157] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] 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.

[0169] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an input section for inputting the contents of the company history; an image generating unit that generates a related image based on the content input by the input unit; a sentence generation unit that generates sentences in different expressions based on the content input by the input unit; a providing unit that provides the content generated by the image generating unit and the sentence generating unit. A system characterized by:

2. The image generation unit Generate a portrait of the founding office or founder based on anecdotes from the founding 2. The system of claim 1.

3. The image generation unit Generate project deliverables or project team group photos based on key project success stories 2. The system of claim 1.

4. The sentence generation unit Write down your founding story as an emotive story 2. The system of claim 1.

5. The sentence generation unit Documenting important project success stories as interesting anecdotes 2. The system of claim 1.

6. The providing unit Present the generated images and text at corporate events 2. The system of claim 1.

7. The providing unit Disclose the generated images and text outside the company 2. The system of claim 1.

8. The input unit Inferring the user's emotions and adjusting the specificity of the input content based on the estimated user emotions 2. The system of claim 1.

Images