System

Abstract

An object of a system according to an embodiment is to automatically generate a subject of a mail and a title of a slide.SOLUTION: A system includes a mail text analysis part, a summary generation part, a subject generation part, a slide analysis part, a title generation part, an image analysis part, and a point generation part. The mail text analysis unit analyzes a mail text. The summary generation unit summarizes the mail text analyzed by the mail text analysis unit. The subject generation unit generates a subject based on the summary generated by the summary generation unit. The slide analysis unit analyzes the content of the slide. The title generation unit generates a title based on the content of the slide analyzed by the slide analysis unit. The image analysis unit analyzes an image included in the slide. The point generation unit generates a point based on the image analyzed by the image analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the drawback of making it difficult and time-consuming to generate appropriate email subject lines or slide titles.

[0005] The system according to the embodiment aims to automatically generate email subjects and slide titles. [Means for solving the problem]

[0006] The system according to the embodiment includes an email body analysis unit, a summary generation unit, a subject generation unit, a slide analysis unit, a title generation unit, an image analysis unit, and a points generation unit. The email body analysis unit analyzes the email body. The summary generation unit summarizes the email body analyzed by the email body analysis unit. The subject generation unit generates a subject based on the summary generated by the summary generation unit. The slide analysis unit analyzes the content of the slide. The title generation unit generates a title based on the content of the slide analyzed by the slide analysis unit. The image analysis unit analyzes images included in the slide. The points generation unit generates points based on the images analyzed by the image analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically generate email subjects and slide titles. [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) The automatic generation system according to the embodiment of the present invention automatically analyzes the content of email text and slides, and the generation AI generates appropriate subjects and titles. This reduces the burden on users and enables efficient information transmission.

[0029] The automatic generation system according to the embodiment includes an email body analysis unit, a summary generation unit, a subject generation unit, a slide analysis unit, a title generation unit, an image analysis unit, and a key point generation unit. The email body analysis unit analyzes the email body. For example, the email body analysis unit analyzes email bodies in text format. The email body analysis unit can also analyze email bodies in HTML format. The email body analysis unit can also analyze the presence or absence of attachments. The summary generation unit summarizes the email body analyzed by the email body analysis unit. For example, the summary generation unit converts a long email body into a short summary. The summary generation unit can also extract important points and generate a summary. The summary generation unit can also generate a summary based on the length of the text. The subject generation unit generates a subject based on the summary generated by the summary generation unit. For example, the subject generation unit generates a subject based on the content of the summary. The subject generation unit can also generate a subject based on the results of sentiment analysis. The subject generation unit can also generate a subject based on the importance of the summary. The slide analysis unit analyzes the content of the slide. For example, the slide analysis unit analyzes the text of the slide. The slide analysis unit can also analyze the images of the slide. The slide analysis unit can also analyze the graphs of the slide. The title generation unit generates a title based on the content of the slide analyzed by the slide analysis unit. For example, the title generation unit generates a title based on the main points of the slide. The title generation unit can also generate a title by referencing external data. The title generation unit can also generate a title taking into account the overall structure of the presentation. The image analysis unit analyzes images included in the slide. For example, the image analysis unit extracts text from the image using OCR technology. The image analysis unit can also recognize objects in the image. The image analysis unit can also analyze the color and shape of the image. The score generation unit generates scores based on the image analyzed by the image analysis unit. For example, the score generation unit generates scores based on the text extracted using OCR technology. The score generation unit can also generate scores by analyzing the meaning of the object.The point generation unit can also generate points based on visual features. This allows the automatic generation system according to the embodiment to reduce the burden on the user and achieve efficient information transmission. For example, by automatically generating email subjects and slide titles, the user can save time and effort. Furthermore, the generated subjects and titles are easy for recipients and audiences to understand, allowing for smooth information transmission. Furthermore, visual information can also be effectively transmitted by extracting points through image analysis.

[0030] The email body analysis unit evaluates the importance of the email body, and the subject generation unit can generate a subject based on the importance. For example, the email body analysis unit evaluates the importance of the email body, and generates a subject including keywords such as "urgent" or "important" for emails with a high level of urgency. For example, it generates a subject such as "Urgent response required." The email body analysis unit also generates a subject that calls for appropriate attention for emails with a medium level of importance. For example, it generates a subject such as "Please confirm." The email body analysis unit also generates a subject with a lighter tone for emails with a low level of importance. For example, it generates a subject such as "Notice." In this way, by generating a subject based on the importance of the email body, the recipient can grasp the priority of the email at a glance.

[0031] The email body analysis unit analyzes the contents of the email body, and the subject generation unit can generate a subject by referencing related past emails and documents. For example, the email body analysis unit analyzes the contents of the email body and generates a subject such as "Meeting minutes (2nd)" by referencing related past meeting minutes. The email body analysis unit also references past project reports and generates a subject such as "Project progress report" for a progress report email. The email body analysis unit also references past customer correspondence history and generates a subject such as "Response based on customer correspondence history" for an inquiry email from a customer. In this way, consistent subjects can be generated by referencing past emails and documents.

[0032] The email body analysis unit can summarize email bodies and generate subject lines in different languages. For example, the email body analysis unit translates Japanese email bodies into English and generates an English subject line. For example, for a Japanese email body such as "I'm sending you the minutes of the meeting," it generates an English subject line such as "Meeting Minutes." The email body analysis unit also translates English email bodies into French and generates a French subject line. For example, for an English email body such as "Project Update," it generates a French subject line such as "Mise a jour du projet." The email body analysis unit also builds a multilingual email summary and subject line generation system and generates an appropriate subject line according to the language selected by the user. For example, it generates a Spanish subject line for a Spanish email body. This allows for support of different languages, facilitating smooth international communication.

[0033] The email body analysis unit supports voice input and can summarize the email body and generate a subject. For example, the email body analysis unit analyzes the content of an email input via voice, generates a summary, and generates a subject. For example, if the user inputs "I'm sending you the minutes of the meeting," the email body analysis unit generates a subject such as "Meeting minutes." The email body analysis unit also uses voice recognition technology to convert the voice-input email body into text and generates a subject based on that text. For example, if the user inputs "Please report on the progress of the project," the email body analysis unit generates a subject such as "Project progress report." The email body analysis unit also analyzes the emotion of the voice-input email body and generates a subject based on that emotion. For example, if the user inputs a message expressing gratitude, the email body analysis unit generates a subject such as "With gratitude." This allows for hands-free email creation by supporting voice input.

[0034] The slide analysis unit analyzes the content of the slides, extracts the key points of each slide, and the title generation unit generates a title. The slide analysis unit, for example, analyzes the text of the slides and generates a title by listing the key points of each slide. For example, a key point such as "Features of the new product" is extracted and a title such as "Features of the new product" is generated. The slide analysis unit also analyzes the content of the slides and extracts important keywords to generate a title. For example, a keyword such as "market strategy" is extracted and a title such as "Market Strategy" is generated. The slide analysis unit also summarizes the content of the slides and generates a title that concisely summarizes the key points. For example, a key point such as "Increasing sales trend" is extracted and a title such as "Increasing sales trend" is generated. In this way, by extracting the key points of each slide and generating a title, the structure of the presentation becomes clear.

[0035] The slide analysis unit analyzes the content of the slide, and the title generation unit can generate a title by referring to external data. The slide analysis unit, for example, analyzes the content of the slide and generates a title by referring to related statistical data. For example, a title such as "Market Growth Forecast" is generated based on the statistical data. The slide analysis unit also analyzes the content of the slide and generates a title by referring to related market reports. For example, a title such as "Competitive Analysis" is generated based on the market reports. The slide analysis unit also analyzes the content of the slide and generates a title by referring to related academic papers. For example, a title such as "Trends in Technological Innovation" is generated based on academic papers. In this way, by referring to external data, more accurate titles can be generated.

[0036] The slide analysis unit analyzes the content of the slides, and the title generation unit can generate titles taking into account the overall structure of the presentation. The slide analysis unit, for example, analyzes the content of the slides and generates titles that follow the flow of the presentation. For example, it generates a title such as "Introduction" for an introductory slide. The slide analysis unit also generates titles for each section taking into account the overall structure of the presentation. For example, it generates titles for each section such as "Background," "Objective," and "Results." The slide analysis unit also analyzes the content of the slides and generates titles that follow the theme of the presentation. For example, it generates a title that follows the theme such as "Importance of Environmental Protection." In this way, titles that follow the flow can be generated by taking into account the overall structure of the presentation.

[0037] The slide analysis unit can analyze slide content and generate titles in different languages. For example, the slide analysis unit translates Japanese slides into English and generates English titles. For example, it generates an English title such as "New Product Features and Market Strategy" for a Japanese slide titled "New Product Features and Market Strategy." The slide analysis unit can also translate English slides into French and generate French titles. For example, it generates a French title such as "Analyse du marche" for an English slide titled "Market Analysis." The slide analysis unit can also build a multilingual slide content analysis and title generation system and generate appropriate titles according to the language selected by the user. For example, it generates a Spanish title for a Spanish slide. This allows for support of different languages, making international presentations smoother.

[0038] The slide analysis unit is compatible with video presentations and can analyze the content of slides and generate titles. The slide analysis unit, for example, analyzes the content of a video presentation and generates titles for each section. For example, it analyzes the content of the video and generates titles such as "Introduction," "Main Content," and "Conclusion." The slide analysis unit also analyzes the audio in the video and generates titles based on the audio content. For example, it uses voice recognition technology to generate a title such as "New Product Features." The slide analysis unit also summarizes the content of the video presentation and generates a title that concisely summarizes the main points. For example, it extracts key points such as "Market Strategy" and generates a title such as "Market Strategy." This allows for effective visual information transmission by supporting video presentations.

[0039] The image analysis unit can extract text from an image using OCR technology, and the point generation unit can generate points based on that text. For example, the image analysis unit can extract text from an image using OCR technology and generate points such as "sales trend increasing" based on the extracted text. For example, it can extract graph captions and generate points such as "sales trend increasing." The image analysis unit can also extract text from an image using OCR technology and generate points by summarizing the extracted text. For example, it can summarize long descriptions and generate points such as "new product features." The image analysis unit can also extract text from an image using OCR technology and generate points by referencing related data based on the extracted text. For example, it can generate points such as "market growth forecast" based on statistical data. In this way, extracting text from an image can effectively convey visual information.

[0040] The image analysis unit recognizes objects in an image, analyzes the meaning of the objects, and the point generation unit can generate points. For example, the image analysis unit recognizes objects in an image, analyzes the meaning of the objects, and generates points such as "features of a new product." For example, it recognizes an image of a product and generates points such as "features of a new product." The image analysis unit also recognizes objects in an image, analyzes the meaning of the objects, and generates points such as "sales growth trend." For example, it recognizes an image of a graph and generates points such as "sales growth trend." The image analysis unit also recognizes objects in an image, analyzes the meaning of the objects, and generates points such as "market growth forecast." For example, it recognizes an image showing statistical data and generates points such as "market growth forecast." In this way, visual information can be effectively conveyed by recognizing objects in an image.

[0041] The image analysis unit analyzes the colors and shapes in the image, and the point generation unit can generate points based on the visual features. The image analysis unit, for example, analyzes color changes in the image and generates points such as "seasonal changes." For example, it analyzes an image of autumn leaves and generates points such as "the arrival of autumn." The image analysis unit also analyzes shapes in the image and generates points such as "product design." For example, it analyzes the shape of a new product and generates points such as "new product design." The image analysis unit also analyzes a combination of colors and shapes in the image and generates points such as "brand identity." For example, it analyzes a company logo and generates points such as "brand identity." In this way, visual information can be effectively conveyed by analyzing the colors and shapes in the image.

[0042] The image analysis unit can support different media formats and extract points through image analysis. The image analysis unit, for example, analyzes frames in a video to generate important points. For example, it analyzes each frame of a presentation video to generate points such as "features of a new product." The image analysis unit can also analyze audio data to generate points based on the audio content. For example, it can use voice recognition technology to generate points such as "market strategy." The image analysis unit can also analyze text data to generate points based on the text content. For example, it can summarize long sentences to generate points such as "sales growth trend." This allows the system to support different media formats and effectively analyze information in various formats to extract points.

[0043] The image analysis unit performs image analysis in real time, and the point generation unit can generate points during a live presentation. The image analysis unit, for example, analyzes images during live streaming and displays important points in real time. For example, it generates points such as "features of a new product" during a live presentation. The image analysis unit also analyzes images in real time and immediately presents points to viewers. For example, it generates points such as "market strategy" during a live event. The image analysis unit also analyzes images during a live presentation and adjusts points according to viewer reactions. For example, it generates points such as "sales increase trend" for parts that are of high interest to viewers. In this way, by performing image analysis in real time, points can be generated instantly during a live presentation.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The automatic generation system can further include a history reference unit that references the user's past email sending history. The history reference unit, for example, analyzes the subject lines and content of emails sent in the past and generates consistent subject lines for similar emails. For example, if an email was sent in the past with a subject line such as "Meeting Minutes," it can generate a subject line such as "Meeting Minutes (2nd)" for emails with similar content. The history reference unit can also reference the sending date and time of past emails and recipient information to generate appropriate subject lines. For example, it can generate a subject line such as "Monthly Report (October 2023)" for periodic report emails. By referencing the past email sending history, consistent subject lines can be generated, enabling email management that is easy for recipients to understand.

[0046] The automatic generation system may further include a schedule reference unit that references the user's schedule information. The schedule reference unit, for example, analyzes the user's calendar information and generates a subject line based on the schedule. For example, if a meeting is scheduled, it generates a subject line such as "Meeting Information." The schedule reference unit can also send emails at appropriate times based on the user's schedule. For example, when sending a reminder email the day before an important meeting, it generates a subject line such as "Tomorrow's Meeting Information." The schedule reference unit can also adjust the priority of the subject line based on the user's schedule. For example, for a highly urgent event, it generates a subject line such as "Urgent Response Required." This enables efficient information communication by generating subjects based on the user's schedule.

[0047] The automatic generation system can further include a project reference unit that references the user's project management information. The project reference unit, for example, analyzes the progress of a project managed by the user and generates subject lines for emails related to the project. For example, it generates a subject line such as "Project Progress Report" for an email reporting the progress of a project. The project reference unit can also generate subject lines based on important milestones in the project. For example, it generates a subject line such as "Project Completion Report" for an email reporting the completion of a project. The project reference unit can also adjust the subject line based on the priority of the project. For example, it generates a subject line such as "Important: Project Progress Report" for a highly important project. In this way, by referencing the project management information, it is possible to appropriately generate subject lines for emails related to the project.

[0048] The automatic generation system may further include a browser history reference unit that references the user's browser history. The browser history reference unit, for example, analyzes the content of web pages viewed by the user and generates related email subjects. For example, if the user views a specific product page, it generates a subject such as "Product Information Guide." The browser history reference unit can also analyze the user's search history and generate subjects based on search keywords. For example, if a user searches for "new product features," it generates a subject such as "About the Features of the New Product." The browser history reference unit can also adjust the tone of the subject based on the user's browsing history. For example, if the user views many business-related pages, it generates a subject such as "Business Information Guide." In this way, by referencing the browser history, it is possible to generate subjects based on the user's interests and concerns.

[0049] The automatic generation system may further include a location information reference unit that references the user's location information. The location information reference unit, for example, analyzes the user's current location and generates a subject line based on the location information. For example, if the user is at a specific event venue, it generates a subject line such as "Event Information." The location information reference unit may also analyze the user's movement history and generate a subject line based on past visited places. For example, it may generate a subject line such as "Restaurant Information" for an email about a restaurant the user has visited in the past. The location information reference unit may also adjust the tone of the subject line based on the user's location information. For example, if the user is at a tourist spot, it may generate a subject line such as "Tourist Information." In this way, by referencing the location information, it is possible to generate a subject line based on the user's current location and movement history.

[0050] The automatic generation system may further include a purchase history reference unit that references the user's purchase history. The purchase history reference unit, for example, analyzes information about products the user has purchased in the past and generates a subject line for the related email. For example, if the user purchases a specific product, it generates a subject line such as "Thank you for your purchase." The purchase history reference unit can also generate a subject line that provides information about related products based on the user's purchase history. For example, if the user purchases a camera, it generates a subject line such as "Information about camera accessories." The purchase history reference unit can also adjust the tone of the subject line based on the user's purchase history. For example, if a high-priced product is purchased, it generates a subject line such as "Special information." In this way, by referencing the purchase history, it is possible to generate a subject line based on the user's purchasing behavior.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The email body analysis unit analyzes the email body. For example, the email body analysis unit analyzes the email body in text format or HTML format, and also analyzes whether or not there is an attachment. Step 2: The summary generator summarizes the email body analyzed by the email body analyzer. For example, the summary generator converts a long email body into a short summary and extracts important points to generate a summary. It can also generate a summary based on the length of the text. Step 3: The subject line generator generates a subject line based on the summary generated by the summary generator. For example, the subject line generator generates a subject line based on the content of the summary, the results of sentiment analysis, and the importance of the summary. Step 4: The slide analyzer analyzes the content of the slide, for example, the slide analyzer analyzes the text, images, and graphs of the slide. Step 5: The title generator generates a title based on the content of the slide analyzed by the slide analyzer. For example, the title generator generates a title by taking into account the main points of the slide, external data, and the overall structure of the presentation. Step 6: The image analysis unit analyzes the images included in the slides. For example, the image analysis unit extracts text from the images using OCR technology and analyzes the objects, colors, and shapes in the images. Step 7: The point generator generates points based on the image analyzed by the image analyzer. For example, the point generator generates points based on the meaning and visual features of text and objects extracted using OCR technology.

[0053] (Example 2) The automatic generation system according to the embodiment of the present invention automatically analyzes the content of email text and slides, and the generation AI generates appropriate subjects and titles. This reduces the burden on users and enables efficient information transmission.

[0054] The automatic generation system according to the embodiment includes an email body analysis unit, a summary generation unit, a subject generation unit, a slide analysis unit, a title generation unit, an image analysis unit, and a key point generation unit. The email body analysis unit analyzes the email body. For example, the email body analysis unit analyzes email bodies in text format. The email body analysis unit can also analyze email bodies in HTML format. The email body analysis unit can also analyze the presence or absence of attachments. The summary generation unit summarizes the email body analyzed by the email body analysis unit. For example, the summary generation unit converts a long email body into a short summary. The summary generation unit can also extract important points and generate a summary. The summary generation unit can also generate a summary based on the length of the text. The subject generation unit generates a subject based on the summary generated by the summary generation unit. For example, the subject generation unit generates a subject based on the content of the summary. The subject generation unit can also generate a subject based on the results of sentiment analysis. The subject generation unit can also generate a subject based on the importance of the summary. The slide analysis unit analyzes the content of the slide. For example, the slide analysis unit analyzes the text of the slide. The slide analysis unit can also analyze the images of the slide. The slide analysis unit can also analyze the graphs of the slide. The title generation unit generates a title based on the content of the slide analyzed by the slide analysis unit. For example, the title generation unit generates a title based on the main points of the slide. The title generation unit can also generate a title by referencing external data. The title generation unit can also generate a title taking into account the overall structure of the presentation. The image analysis unit analyzes images included in the slide. For example, the image analysis unit extracts text from the image using OCR technology. The image analysis unit can also recognize objects in the image. The image analysis unit can also analyze the color and shape of the image. The score generation unit generates scores based on the image analyzed by the image analysis unit. For example, the score generation unit generates scores based on the text extracted using OCR technology. The score generation unit can also generate scores by analyzing the meaning of the object.The point generation unit can also generate points based on visual features. This allows the automatic generation system according to the embodiment to reduce the burden on the user and achieve efficient information transmission. For example, by automatically generating email subjects and slide titles, the user can save time and effort. Furthermore, the generated subjects and titles are easy for recipients and audiences to understand, allowing for smooth information transmission. Furthermore, visual information can also be effectively transmitted by extracting points through image analysis.

[0055] The email body analysis unit performs sentiment analysis of the email body, and the subject line generation unit can adjust the subject line based on the sentiment. For example, the email body analysis unit performs sentiment analysis of the email body, and generates a cheerful subject line if the sentiment is strong. For example, for an email expressing gratitude, it generates a subject line such as "With gratitude." The email body analysis unit also generates a subject line that softens the sentiment for an email body containing negative sentiment. For example, for a complaint email, it generates a subject line such as "Thank you for your feedback." The email body analysis unit also generates a subject line according to the strength of the sentiment based on the results of the sentiment analysis. For example, if the sentiment is very strong, it generates a subject line such as "We are very grateful." This allows for communication that takes emotions into consideration by generating appropriate subject lines based on the sentiment of the email body.

[0056] The email body analysis unit evaluates the importance of the email body, and the subject generation unit can generate a subject based on the importance. For example, the email body analysis unit evaluates the importance of the email body, and generates a subject including keywords such as "urgent" or "important" for emails with a high level of urgency. For example, it generates a subject such as "Urgent response required." The email body analysis unit also generates a subject that calls for appropriate attention for emails with a medium level of importance. For example, it generates a subject such as "Please confirm." The email body analysis unit also generates a subject with a lighter tone for emails with a low level of importance. For example, it generates a subject such as "Notice." In this way, by generating a subject based on the importance of the email body, the recipient can grasp the priority of the email at a glance.

[0057] The email body analysis unit analyzes the contents of the email body, and the subject generation unit can generate a subject by referencing related past emails and documents. For example, the email body analysis unit analyzes the contents of the email body and generates a subject such as "Meeting minutes (2nd)" by referencing related past meeting minutes. The email body analysis unit also references past project reports and generates a subject such as "Project progress report" for a progress report email. The email body analysis unit also references past customer correspondence history and generates a subject such as "Response based on customer correspondence history" for an inquiry email from a customer. In this way, consistent subjects can be generated by referencing past emails and documents.

[0058] The email body analysis unit can summarize email bodies and generate subject lines in different languages. For example, the email body analysis unit translates Japanese email bodies into English and generates an English subject line. For example, for a Japanese email body such as "I'm sending you the minutes of the meeting," it generates an English subject line such as "Meeting Minutes." The email body analysis unit also translates English email bodies into French and generates a French subject line. For example, for an English email body such as "Project Update," it generates a French subject line such as "Mise a jour du projet." The email body analysis unit also builds a multilingual email summary and subject line generation system and generates an appropriate subject line according to the language selected by the user. For example, it generates a Spanish subject line for a Spanish email body. This allows for support of different languages, facilitating smooth international communication.

[0059] The email body analysis unit supports voice input and can summarize the email body and generate a subject. For example, the email body analysis unit analyzes the content of an email input via voice, generates a summary, and generates a subject. For example, if the user inputs "I'm sending you the minutes of the meeting," the email body analysis unit generates a subject such as "Meeting minutes." The email body analysis unit also uses voice recognition technology to convert the voice-input email body into text and generates a subject based on that text. For example, if the user inputs "Please report on the progress of the project," the email body analysis unit generates a subject such as "Project progress report." The email body analysis unit also analyzes the emotion of the voice-input email body and generates a subject based on that emotion. For example, if the user inputs a message expressing gratitude, the email body analysis unit generates a subject such as "With gratitude." This allows for hands-free email creation by supporting voice input.

[0060] The slide analysis unit analyzes the content of the slides, extracts the key points of each slide, and the title generation unit generates a title. The slide analysis unit, for example, analyzes the text of the slides and generates a title by listing the key points of each slide. For example, a key point such as "Features of the new product" is extracted and a title such as "Features of the new product" is generated. The slide analysis unit also analyzes the content of the slides and extracts important keywords to generate a title. For example, a keyword such as "market strategy" is extracted and a title such as "Market Strategy" is generated. The slide analysis unit also summarizes the content of the slides and generates a title that concisely summarizes the key points. For example, a key point such as "Increasing sales trend" is extracted and a title such as "Increasing sales trend" is generated. In this way, by extracting the key points of each slide and generating a title, the structure of the presentation becomes clear.

[0061] The slide analysis unit analyzes the content of the slide, and the title generation unit can generate a title by referring to external data. The slide analysis unit, for example, analyzes the content of the slide and generates a title by referring to related statistical data. For example, a title such as "Market Growth Forecast" is generated based on the statistical data. The slide analysis unit also analyzes the content of the slide and generates a title by referring to related market reports. For example, a title such as "Competitive Analysis" is generated based on the market reports. The slide analysis unit also analyzes the content of the slide and generates a title by referring to related academic papers. For example, a title such as "Trends in Technological Innovation" is generated based on academic papers. In this way, by referring to external data, more accurate titles can be generated.

[0062] The slide analysis unit analyzes the content of the slides, and the title generation unit can generate titles taking into account the overall structure of the presentation. The slide analysis unit, for example, analyzes the content of the slides and generates titles that follow the flow of the presentation. For example, it generates a title such as "Introduction" for an introductory slide. The slide analysis unit also generates titles for each section taking into account the overall structure of the presentation. For example, it generates titles for each section such as "Background," "Objective," and "Results." The slide analysis unit also analyzes the content of the slides and generates titles that follow the theme of the presentation. For example, it generates a title that follows the theme such as "Importance of Environmental Protection." In this way, titles that follow the flow can be generated by taking into account the overall structure of the presentation.

[0063] The slide analysis unit can analyze slide content and generate titles in different languages. For example, the slide analysis unit translates Japanese slides into English and generates English titles. For example, it generates an English title such as "New Product Features and Market Strategy" for a Japanese slide titled "New Product Features and Market Strategy." The slide analysis unit can also translate English slides into French and generate French titles. For example, it generates a French title such as "Analyse du marche" for an English slide titled "Market Analysis." The slide analysis unit can also build a multilingual slide content analysis and title generation system and generate appropriate titles according to the language selected by the user. For example, it generates a Spanish title for a Spanish slide. This allows for support of different languages, making international presentations smoother.

[0064] The slide analysis unit is compatible with video presentations and can analyze the content of slides and generate titles. The slide analysis unit, for example, analyzes the content of a video presentation and generates titles for each section. For example, it analyzes the content of the video and generates titles such as "Introduction," "Main Content," and "Conclusion." The slide analysis unit also analyzes the audio in the video and generates titles based on the audio content. For example, it uses voice recognition technology to generate a title such as "New Product Features." The slide analysis unit also summarizes the content of the video presentation and generates a title that concisely summarizes the main points. For example, it extracts key points such as "Market Strategy" and generates a title such as "Market Strategy." This allows for effective visual information transmission by supporting video presentations.

[0065] The slide analysis unit uses an emotion estimation function to analyze the audience's emotions regarding the slide content, and the title generation unit can generate titles based on the emotions. For example, the slide analysis unit analyzes the audience's emotions regarding the slide content and generates a title such as "Moving Moment" for an emotionally moving slide. For example, a title such as "Moving Moment" is generated for a slide containing a moving story. The slide analysis unit also analyzes the audience's emotions in real time and generates titles based on the emotions. For example, a title such as "Exciting Moment" is generated for an exciting slide. The slide analysis unit also generates titles according to the intensity of the emotions based on the results of the emotion analysis. For example, if the emotion is very positive, a title such as "Very Moving" is generated. In this way, generating titles based on the audience's emotions can enhance the effectiveness of the presentation.

[0066] The image analysis unit can extract text from an image using OCR technology, and the point generation unit can generate points based on that text. For example, the image analysis unit can extract text from an image using OCR technology and generate points such as "sales trend increasing" based on the extracted text. For example, it can extract graph captions and generate points such as "sales trend increasing." The image analysis unit can also extract text from an image using OCR technology and generate points by summarizing the extracted text. For example, it can summarize long descriptions and generate points such as "new product features." The image analysis unit can also extract text from an image using OCR technology and generate points by referencing related data based on the extracted text. For example, it can generate points such as "market growth forecast" based on statistical data. In this way, extracting text from an image can effectively convey visual information.

[0067] The image analysis unit recognizes objects in an image, analyzes the meaning of the objects, and the point generation unit can generate points. For example, the image analysis unit recognizes objects in an image, analyzes the meaning of the objects, and generates points such as "features of a new product." For example, it recognizes an image of a product and generates points such as "features of a new product." The image analysis unit also recognizes objects in an image, analyzes the meaning of the objects, and generates points such as "sales growth trend." For example, it recognizes an image of a graph and generates points such as "sales growth trend." The image analysis unit also recognizes objects in an image, analyzes the meaning of the objects, and generates points such as "market growth forecast." For example, it recognizes an image showing statistical data and generates points such as "market growth forecast." In this way, visual information can be effectively conveyed by recognizing objects in an image.

[0068] The image analysis unit analyzes the colors and shapes in the image, and the point generation unit can generate points based on the visual features. The image analysis unit, for example, analyzes color changes in the image and generates points such as "seasonal changes." For example, it analyzes an image of autumn leaves and generates points such as "the arrival of autumn." The image analysis unit also analyzes shapes in the image and generates points such as "product design." For example, it analyzes the shape of a new product and generates points such as "new product design." The image analysis unit also analyzes a combination of colors and shapes in the image and generates points such as "brand identity." For example, it analyzes a company logo and generates points such as "brand identity." In this way, visual information can be effectively conveyed by analyzing the colors and shapes in the image.

[0069] The image analysis unit can support different media formats and extract points through image analysis. The image analysis unit, for example, analyzes frames in a video to generate important points. For example, it analyzes each frame of a presentation video to generate points such as "features of a new product." The image analysis unit can also analyze audio data to generate points based on the audio content. For example, it can use voice recognition technology to generate points such as "market strategy." The image analysis unit can also analyze text data to generate points based on the text content. For example, it can summarize long sentences to generate points such as "sales growth trend." This allows the system to support different media formats and effectively analyze information in various formats to extract points.

[0070] The image analysis unit performs image analysis in real time, and the point generation unit can generate points during a live presentation. The image analysis unit, for example, analyzes images during live streaming and displays important points in real time. For example, it generates points such as "features of a new product" during a live presentation. The image analysis unit also analyzes images in real time and immediately presents points to viewers. For example, it generates points such as "market strategy" during a live event. The image analysis unit also analyzes images during a live presentation and adjusts points according to viewer reactions. For example, it generates points such as "sales increase trend" for parts that are of high interest to viewers. In this way, by performing image analysis in real time, points can be generated instantly during a live presentation.

[0071] The image analysis unit uses an emotion estimation function to analyze the viewer's emotions toward an image, and the point generation unit can generate points based on the emotions. For example, the image analysis unit analyzes the viewer's emotions toward an image and generates a point such as "Moving Moment" for a moving image. For example, it generates a point such as "Moving Moment" for an image that includes a moving story. The image analysis unit also analyzes the viewer's emotions in real time and generates points based on the emotions. For example, it generates a point such as "Exciting Moment" for an exciting image. The image analysis unit also generates points according to the intensity of the emotion based on the results of the emotion analysis. For example, if the emotion is very strong, it generates a point such as "Very Moving." In this way, generating points based on the viewer's emotions can enhance the effectiveness of a presentation.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The automatic generation system can further include a history reference unit that references the user's past email sending history. The history reference unit, for example, analyzes the subject lines and content of emails sent in the past and generates consistent subject lines for similar emails. For example, if an email was sent in the past with a subject line such as "Meeting Minutes," it can generate a subject line such as "Meeting Minutes (2nd)" for emails with similar content. The history reference unit can also reference the sending date and time of past emails and recipient information to generate appropriate subject lines. For example, it can generate a subject line such as "Monthly Report (October 2023)" for periodic report emails. By referencing the past email sending history, consistent subject lines can be generated, enabling email management that is easy for recipients to understand.

[0074] The email body analysis unit estimates the user's emotions, and the subject generation unit can adjust the subject line based on the estimated user emotions. For example, if the user has very positive emotions, a cheerful subject line is generated. For example, when a user sends an email expressing gratitude, a subject line such as "With gratitude" is generated. Also, if the user has negative emotions, a subject line that softens the emotion is generated. For example, when sending a complaint email, a subject line such as "Thank you for your feedback" is generated. The subject line can also be adjusted according to the strength of the user's emotions. For example, if the user has very strong positive emotions, a subject line such as "We are very grateful" is generated. This enables communication that takes the user's emotions into consideration.

[0075] The automatic generation system may further include a schedule reference unit that references the user's schedule information. The schedule reference unit, for example, analyzes the user's calendar information and generates a subject line based on the schedule. For example, if a meeting is scheduled, it generates a subject line such as "Meeting Information." The schedule reference unit can also send emails at appropriate times based on the user's schedule. For example, when sending a reminder email the day before an important meeting, it generates a subject line such as "Tomorrow's Meeting Information." The schedule reference unit can also adjust the priority of the subject line based on the user's schedule. For example, for a highly urgent event, it generates a subject line such as "Urgent Response Required." This enables efficient information communication by generating subjects based on the user's schedule.

[0076] The automatic generation system can further include a project reference unit that references the user's project management information. The project reference unit, for example, analyzes the progress of a project managed by the user and generates subject lines for emails related to the project. For example, it generates a subject line such as "Project Progress Report" for an email reporting the progress of a project. The project reference unit can also generate subject lines based on important milestones in the project. For example, it generates a subject line such as "Project Completion Report" for an email reporting the completion of a project. The project reference unit can also adjust the subject line based on the priority of the project. For example, it generates a subject line such as "Important: Project Progress Report" for a highly important project. In this way, by referencing the project management information, it is possible to appropriately generate subject lines for emails related to the project.

[0077] The automatic generation system may further include a social media reference unit that references the user's social media information. The social media reference unit, for example, analyzes the content of the user's social media posts and generates a related email subject line. For example, if the user announces an event on social media, the social media reference unit generates a subject line such as "Event Information." The social media reference unit can also analyze the reactions of the user's followers and friends and generate a subject line based on their emotions. For example, if there are many positive reactions, the social media reference unit generates a subject line such as "Very Popular Event." The social media reference unit can also adjust the tone of the subject line based on the user's social media activity. For example, if there are many casual posts, the social media reference unit generates a subject line with a lighter tone such as "Announcement." In this way, by referencing the social media information, it is possible to generate a subject line based on the user's online activity.

[0078] The automatic generation system may further include a voice memo analysis unit that analyzes a user's voice memo. The voice memo analysis unit, for example, analyzes a voice memo recorded by a user, generates a summary, and generates a subject line. For example, if a voice memo says, "I'm sending you the minutes of the meeting," the voice memo analysis unit generates a subject line such as "Meeting Minutes." The voice memo analysis unit also uses voice recognition technology to convert the voice memo into text and generates a subject line based on that text. For example, if a voice memo says, "Please report on the progress of the project," the voice memo analysis unit generates a subject line such as "Project Progress Report." The voice memo analysis unit can also analyze the emotion in the voice memo and generate a subject line based on that emotion. For example, for a voice memo expressing gratitude, the voice memo analysis unit generates a subject line such as "With gratitude." This allows hands-free email creation by analyzing voice memos.

[0079] The automatic generation system may further include a browser history reference unit that references the user's browser history. The browser history reference unit, for example, analyzes the content of web pages viewed by the user and generates related email subjects. For example, if the user views a specific product page, it generates a subject such as "Product Information Guide." The browser history reference unit can also analyze the user's search history and generate subjects based on search keywords. For example, if a user searches for "new product features," it generates a subject such as "About the Features of the New Product." The browser history reference unit can also adjust the tone of the subject based on the user's browsing history. For example, if the user views many business-related pages, it generates a subject such as "Business Information Guide." In this way, by referencing the browser history, it is possible to generate subjects based on the user's interests and concerns.

[0080] The automatic generation system may further include a location information reference unit that references the user's location information. The location information reference unit, for example, analyzes the user's current location and generates a subject line based on the location information. For example, if the user is at a specific event venue, it generates a subject line such as "Event Information." The location information reference unit may also analyze the user's movement history and generate a subject line based on past visited places. For example, it may generate a subject line such as "Restaurant Information" for an email about a restaurant the user has visited in the past. The location information reference unit may also adjust the tone of the subject line based on the user's location information. For example, if the user is at a tourist spot, it may generate a subject line such as "Tourist Information." In this way, by referencing the location information, it is possible to generate a subject line based on the user's current location and movement history.

[0081] The automatic generation system may further include a purchase history reference unit that references the user's purchase history. The purchase history reference unit, for example, analyzes information about products the user has purchased in the past and generates a subject line for the related email. For example, if the user purchases a specific product, it generates a subject line such as "Thank you for your purchase." The purchase history reference unit can also generate a subject line that provides information about related products based on the user's purchase history. For example, if the user purchases a camera, it generates a subject line such as "Information about camera accessories." The purchase history reference unit can also adjust the tone of the subject line based on the user's purchase history. For example, if a high-priced product is purchased, it generates a subject line such as "Special information." In this way, by referencing the purchase history, it is possible to generate a subject line based on the user's purchasing behavior.

[0082] The automatic generation system may further include a health data reference unit that references the user's health data. The health data reference unit, for example, analyzes the user's fitness data and generates a related email subject line. For example, if the user performs a specific exercise, it generates a subject line such as "Exercise Record Guide." The health data reference unit can also generate a subject line that provides health information based on the user's health condition. For example, if the user achieves a certain number of steps, it generates a subject line such as "Congratulations on achieving that number of steps." The health data reference unit can also adjust the tone of the subject line based on the user's health data. For example, if the user is feeling stressed, it generates a subject line such as "Relaxation Suggestions." In this way, by referencing the health data, it is possible to generate a subject line based on the user's health condition.

[0083] The processing flow of the second embodiment will be briefly explained below.

[0084] Step 1: The email body analysis unit analyzes the email body. For example, the email body analysis unit analyzes the email body in text format or HTML format, and also analyzes whether or not there is an attachment. Step 2: The summary generator summarizes the email body analyzed by the email body analyzer. For example, the summary generator converts a long email body into a short summary and extracts important points to generate a summary. It can also generate a summary based on the length of the text. Step 3: The subject line generator generates a subject line based on the summary generated by the summary generator. For example, the subject line generator generates a subject line based on the content of the summary, the results of sentiment analysis, and the importance of the summary. Step 4: The slide analyzer analyzes the content of the slide, for example, the slide analyzer analyzes the text, images, and graphs of the slide. Step 5: The title generator generates a title based on the content of the slide analyzed by the slide analyzer. For example, the title generator generates a title by taking into account the main points of the slide, external data, and the overall structure of the presentation. Step 6: The image analysis unit analyzes the images included in the slides. For example, the image analysis unit extracts text from the images using OCR technology and analyzes the objects, colors, and shapes in the images. Step 7: The point generator generates points based on the image analyzed by the image analyzer. For example, the point generator generates points based on the meaning and visual features of text and objects extracted using OCR technology.

[0085] 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.

[0086] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0087] 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.

[0088] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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).

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0102] 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.

[0103] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0104] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] In the headset type terminal 314, 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. 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 specific processing unit 290 using these models.

[0114] 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.

[0115] 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.

[0116] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0117] 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.

[0118] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0119] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0130] 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.

[0131] 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.

[0132] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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."

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0151] 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. [Explanation of symbols]

[0152] 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 email body analysis unit that analyzes an email body; a summary generation unit that summarizes the email body analyzed by the email body analysis unit; a subject line generation unit that generates a subject line based on the summary generated by the summary generation unit; a slide analysis unit that analyzes the content of the slide; a title generation unit that generates a title based on the content of the slide analyzed by the slide analysis unit; an image analysis unit that analyzes an image included in a slide; a point generation unit that generates points based on the image analyzed by the image analysis unit. A system characterized by:

2. The email body analysis unit A sentiment analysis is performed on the email body, and the subject line generator adjusts the subject line based on the sentiment.

2. The system of claim 1.

3. The email body analysis unit The importance of the email body is evaluated, and the subject line generation unit generates a subject line based on the importance.

2. The system of claim 1.

4. The email body analysis unit The subject line generation unit generates a subject line by analyzing the content of the email body and referring to related past emails and documents.

2. The system of claim 1.

5. The email body analysis unit Summarizing the email body and generating a subject line corresponding to the different languages 2. The system of claim 1.

6. The email body analysis unit Responds to voice input and generates a summary of the email body and a subject line 2. The system of claim 1.

7. The slide analysis unit The content of the slides is analyzed, and the main points of each slide are extracted, and the title generating unit generates a title.

2. The system of claim 1.

Images