System

Abstract

An object of a system according to an embodiment is to enable a visually impaired person to understand the content of an image.SOLUTION: A system includes an image analysis unit, a caption generation unit, a text storage unit, and a reading unit. The image analysis unit analyzes an image. The caption generation unit generates a caption on the basis of the image analyzed by the image analysis unit. The text storage unit stores the caption generated by the caption generation unit. The reading unit reads the caption stored by the text storage 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] With conventional technology, visually impaired people have difficulty distinguishing the content of images when using the internet or social networking sites.

[0005] The system according to the embodiment aims to enable visually impaired people to understand the content of images. [Means for solving the problem]

[0006] A system according to an embodiment includes an image analysis unit, a caption generation unit, a text storage unit, and a reading unit. The image analysis unit analyzes an image. The caption generation unit generates a caption based on the image analyzed by the image analysis unit. The text storage unit stores the caption generated by the caption generation unit. The reading unit reads the caption stored by the text storage unit. [Effects of the Invention]

[0007] A system according to an embodiment can enable visually impaired people to understand the content of an image. [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 caption generation system according to an embodiment of the present invention is a system that enables visually impaired people to distinguish what images are displayed when they use the Internet or social networking services on their PCs or smartphones. As a result, the automatic caption generation system allows visually impaired people to understand the content of images even when using a screen reader.

[0029] An automatic caption generation system according to an embodiment includes an image analysis unit, a caption generation unit, a text storage unit, and a reading unit. The image analysis unit analyzes an image. For example, the image analysis unit analyzes the content of the image using an image recognition algorithm. The image analysis unit can also identify the type of image being analyzed. The caption generation unit generates a caption based on the image analyzed by the image analysis unit. For example, the caption generation unit generates a caption using natural language generation technology. The caption generation unit can also specify the format of the generated caption. The text storage unit stores the caption generated by the caption generation unit. For example, the text storage unit stores the caption in a database. The text storage unit can also specify the file format for storage. The reading unit reads the caption stored by the text storage unit. For example, the reading unit reads the caption using speech synthesis technology. The reading unit can also specify the timing of reading. This enables visually impaired people to understand the content of the image. For example, visually impaired people can understand the content of images included in social media posts through audio, and visually impaired people can grasp the content of images on web pages.

[0030] The image analysis unit can analyze the background information of an image and generate a detailed caption based on the image context. For example, the image analysis unit uses a generative AI to analyze the background information of an image and generate a detailed caption based on the image context. For example, for a landscape image, it can generate a specific caption such as "Mountains and lake bathed in a sunset glow." The image analysis unit can also generate a caption such as "A birthday party with friends" for an image of a party. The image analysis unit can also generate a caption such as "New York City at night, the neon lights of Times Square shining" for an image of a cityscape. This makes it possible to generate detailed captions based on the image context.

[0031] The image analysis unit can recognize multiple objects in an image and generate individual captions for each. For example, the image analysis unit uses a generation AI to recognize multiple objects in an image and generate individual captions for each. For example, it can generate a caption such as "A mother and child are playing in the park" for a family photo. The image analysis unit can also generate a caption such as "A lion is resting in the grass" for an image of a zoo. The image analysis unit can also generate a caption such as "Pasta and salad laid out on the table" for an image of food. This makes it possible to generate individual captions for multiple objects.

[0032] The caption generation unit generates captions for each frame of a video and can summarize the content of the entire video in text. For example, the caption generation unit uses a generative AI to generate captions for each frame of a video and summarize the content of the entire video in text. For example, for a travel video, it generates a summary such as "Beautiful beaches, historical buildings, local cuisine." The caption generation unit can also generate a summary such as "Game highlights, player interviews, and crowd cheering" for a video of a sporting event. The caption generation unit can also generate a summary such as "Ingredient preparation, cooking steps, and finished dish" for a cooking video. This allows the content of the entire video to be summarized in text.

[0033] The caption generation unit can analyze the style or artistic quality of an image and generate captions from an artistic perspective. For example, the caption generation unit uses a generative AI to analyze the style or artistic quality of an image and generate captions from an artistic perspective. For example, a caption such as "Landscape painting influenced by Impressionism" can be generated for an image of a painting. The caption generation unit can also generate a caption such as "A work characterized by abstract shapes and vivid colors" for an image of modern art. The caption generation unit can also generate a caption such as "A beautiful monochrome portrait" for an image of a photograph. This allows captions to be generated from an artistic perspective.

[0034] The reading unit can read the captions generated by the generation AI in a natural voice using speech synthesis technology. For example, the reading unit can read the captions generated by the generation AI in a natural voice using speech synthesis technology. For example, the reading unit can read the caption "Beautiful mountain scenery" in a natural voice. The reading unit can also read the caption "Photo taken with friends" in a natural voice. The reading unit can also read the caption "Mountains and lake dyed in a sunset" in a natural voice. This makes it possible to read captions in a natural voice.

[0035] The reading unit can provide a function that allows the reading speed or tone of voice of the captions to be customized to suit the user's preferences. The reading unit can provide a function that allows the reading speed or tone of voice of the captions to be customized to suit the user's preferences. For example, the reading speed can be increased or the tone of voice can be raised. The reading unit can also slow down the reading speed or lower the tone of voice. The reading unit can also make the tone of voice more emotional or adjust the reading speed. This allows the reading speed and tone of voice to be customized.

[0036] The reading unit can display captions on a Braille display, allowing visually impaired people to understand the content through their sense of touch. The reading unit can, for example, display captions on a Braille display, allowing visually impaired people to understand the content through their sense of touch. For example, the reading unit can display the caption "Beautiful mountain scenery" in Braille. The reading unit can also display the caption "Photos taken with friends" in Braille. The reading unit can also display the caption "Mountains and lakes bathed in a sunset" in Braille. This allows visually impaired people to understand the content through their sense of touch.

[0037] The reading unit converts captions into sign language in real time, making it possible to provide information to people with hearing impairments. The reading unit, for example, converts captions into sign language in real time, making it possible to provide information to people with hearing impairments. For example, the caption "Beautiful mountain scenery" can be expressed in sign language. The reading unit can also express the caption "Photo taken with friends" in sign language. The reading unit can also express the caption "Mountains and lake bathed in a sunset" in sign language. This makes it possible to provide information to people with hearing impairments.

[0038] The image analysis unit can scan an entire webpage and detect images without alt text in bulk. For example, the image analysis unit uses a generative AI to scan an entire webpage and detect images without alt text in bulk. For example, it can scan all pages of a news site and list images without alt text. The image analysis unit can also scan all product pages of an online shop and identify images without alt text. The image analysis unit can also scan all articles on a blog site and extract images without alt text. This makes it possible to detect images without alt text in bulk.

[0039] The image analysis unit can evaluate the importance of images and prioritize generating captions for important images. For example, the image analysis unit uses a generation AI to evaluate the importance of images and prioritize generating captions for important images. For example, it prioritizes generating captions for the main image of a news article. The image analysis unit can also prioritize generating captions for the main product image on a product page. The image analysis unit can also prioritize generating captions for the top image of a blog article. This allows captions to be generated with priority for important images.

[0040] The image analysis unit can also detect images within documents such as PDFs and e-books and generate captions. For example, the image analysis unit uses a generative AI to detect images within documents such as PDFs and e-books and generate captions. For example, it can generate a caption such as "An illustration depicting a scene from a story" for an illustration in an e-book. The image analysis unit can also generate a caption such as "A graph showing data trends" for a diagram in a technical document. The image analysis unit can also generate a caption such as "A diagram showing experimental results" for a figure in an academic paper. This makes it possible to generate captions for images within documents.

[0041] The image analysis unit can also generate captions in real time for images on social media stories or during live streaming. For example, the image analysis unit uses a generation AI to generate captions in real time for images on social media stories or during live streaming. For example, it generates a caption such as "Current Scenery" for a scene during a live streaming. The image analysis unit can also generate a caption such as "Delicious Dinner" for an image of a meal posted to a story. The image analysis unit can also generate a caption such as "Event Scene" for an image of an event being live streamed. This makes it possible to generate captions in real time for images on social media stories or during live streaming.

[0042] The caption generation unit allows users to provide feedback on captions generated by the generation AI, and the generation AI learns based on that feedback to improve the accuracy of the captions. For example, the caption generation unit allows users to provide feedback on captions generated by the generation AI, and the generation AI learns based on that feedback to improve the accuracy of the captions. For example, the caption generation unit can correct "photo of a dog" to "photo of my beloved dog." The caption generation unit can also correct "sunset scenery" to "mountains with a beautiful sunset." The caption generation unit can also correct "photo of friends" to "photo taken with friends from college." This allows the accuracy of captions to be improved based on user feedback.

[0043] The caption generation unit can provide a function that saves the caption customization history and allows the user to refer to past customizations. The caption generation unit, for example, saves the caption customization history and allows the user to refer to past customizations. For example, it displays a list of captions that have been modified in the past. The caption generation unit can also display the customization history made to a specific image. The caption generation unit can also display the customization history in chronological order and check past changes. This allows the user to refer to past customizations.

[0044] The caption generator may provide a function that allows a user to share captions generated by the generation AI with other users and collaboratively customize them. For example, the caption generator may provide a function that allows a user to share captions generated by the generation AI with other users and collaboratively customize them. For example, revising captions together with family and friends. The caption generator may also allow a user to revise image captions for a project together with colleagues. The caption generator may also allow a user to share captions in an online community and exchange opinions. This allows a user to collaboratively customize captions with other users.

[0045] The caption generation unit may enable caption customization through voice input, making it easier for visually impaired people to customize captions. The caption generation unit may enable caption customization through voice input, making it easier for visually impaired people to customize captions. For example, the caption generation unit may voice input "Edit caption." The caption generation unit may also voice input "Add details to caption." The caption generation unit may also voice input "Delete caption." This allows visually impaired people to customize captions through voice input.

[0046] The caption generation unit can generate captions taking into account the nuances and cultural backgrounds of different languages. For example, the generation AI generates captions taking into account the nuances and cultural backgrounds of different languages. For example, cultural nuances can be reflected when translating Japanese image captions into English. The caption generation unit can also take cultural backgrounds into account when translating Spanish image captions into French. The caption generation unit can also reflect cultural nuances when translating Chinese image captions into German. This allows captions to be generated taking into account the nuances and cultural backgrounds of different languages.

[0047] The caption generation unit can also handle non-verbal expressions such as sign language and Braille, and provide information to the visually impaired and the hearing impaired. For example, the generation AI can handle non-verbal expressions such as sign language and Braille, and provide information to the visually impaired and the hearing impaired. For example, captions can be expressed in sign language. The caption generation unit can also display captions on a Braille display. The caption generation unit can also generate sign language video to express captions. This allows for support of non-verbal expressions such as sign language and Braille.

[0048] The caption generation unit can provide a function to read captions in different languages ​​in a natural voice using speech synthesis technology. The caption generation unit, for example, provides a function in which a generation AI reads captions in different languages ​​in a natural voice using speech synthesis technology. For example, English captions are read in a natural voice. The caption generation unit can also read Japanese captions in a natural voice. The caption generation unit can also read Spanish captions in a natural voice. This makes it possible to read captions in different languages ​​in a natural voice.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The caption generation unit can customize the style of captions based on the user's preferences. For example, if a user prefers a formal style, the unit can generate a caption such as "This image shows mountains and a lake bathed in a sunset glow." For a user who prefers a casual style, the unit can generate a caption such as "The mountains and lake at sunset are so beautiful!" For a user who prefers a humorous style, the unit can generate a caption such as "The mountains and lake look stylish in the sunset!" This allows the unit to provide captions that suit the user's preferences.

[0051] The caption generator can provide relevant information based on the content of an image. For example, for a landscape image, it can generate a caption such as "This mountain is Mount Fuji, and it is 3,776 meters high." For an image of a historical building, it can generate a caption such as "This building is the Eiffel Tower, completed in 1889." For an image of an animal, it can generate a caption such as "This animal is an African elephant, and it can weigh up to 6,000 kilograms." This allows it to provide detailed information related to the image.

[0052] The caption generator can personalize captions based on a user's past search history and interests. For example, if a user has performed many travel-related searches in the past, a caption such as "This place is the next place you want to visit" can be generated for a travel photo. If a user is interested in cooking, a caption such as "This is your favorite Italian dish" can be generated for an image of food. Furthermore, if a user is interested in sports, a caption such as "This game is for the team you support" can be generated for an image of a sporting event. This allows captions to be provided based on the user's interests.

[0053] The caption generator may provide a feature that allows users to share captions generated by the generation AI with other users and collaboratively customize them. For example, users can revise captions together with family and friends. The caption generator may also allow users to revise image captions for a project together with colleagues. The caption generator may also allow users to share captions in an online community and exchange opinions. This allows users to collaboratively customize captions with other users.

[0054] The caption generation unit can generate captions taking into account the nuances and cultural backgrounds of different languages. For example, cultural nuances can be reflected when translating Japanese image captions into English. The caption generation unit can also take into account cultural backgrounds when translating Spanish image captions into French. The caption generation unit can also take into account cultural nuances when translating Chinese image captions into German. This allows captions to be generated taking into account the nuances and cultural backgrounds of different languages.

[0055] The caption generator may allow for customization of captions through voice input, making it easier for visually impaired people to customize captions. For example, the caption generator may allow for voice input of "Edit caption." The caption generator may also allow for voice input of "Add details to caption." The caption generator may also allow for voice input of "Delete caption." This allows visually impaired people to customize captions through voice input.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The image analysis unit analyzes the image. For example, the image analysis unit may analyze the content of the image using an image recognition algorithm to identify the type of image being analyzed. Step 2: The caption generator generates a caption based on the image analyzed by the image analyzer. For example, the caption generator may generate a caption using natural language generation technology and may specify the format of the generated caption. Step 3: The text storage unit stores the captions generated by the caption generation unit. For example, the text storage unit may store the captions in a database and specify a file format for storing the captions. Step 4: The reading unit reads out the captions stored by the text storage unit. For example, the reading unit can use voice synthesis technology to read out the captions and can also specify the timing of reading out, which allows visually impaired people to understand the content of the images.

[0058] (Example 2) The automatic caption generation system according to an embodiment of the present invention is a system that enables visually impaired people to distinguish what images are displayed when they use the Internet or social networking services on their PCs or smartphones. As a result, the automatic caption generation system allows visually impaired people to understand the content of images even when using a screen reader.

[0059] An automatic caption generation system according to an embodiment includes an image analysis unit, a caption generation unit, a text storage unit, and a reading unit. The image analysis unit analyzes an image. For example, the image analysis unit analyzes the content of the image using an image recognition algorithm. The image analysis unit can also identify the type of image being analyzed. The caption generation unit generates a caption based on the image analyzed by the image analysis unit. For example, the caption generation unit generates a caption using natural language generation technology. The caption generation unit can also specify the format of the generated caption. The text storage unit stores the caption generated by the caption generation unit. For example, the text storage unit stores the caption in a database. The text storage unit can also specify the file format for storage. The reading unit reads the caption stored by the text storage unit. For example, the reading unit reads the caption using speech synthesis technology. The reading unit can also specify the timing of reading. This enables visually impaired people to understand the content of the image. For example, visually impaired people can understand the content of images included in social media posts through audio, and visually impaired people can grasp the content of images on web pages.

[0060] The image analysis unit can analyze the background information of an image and generate a detailed caption based on the image context. For example, the image analysis unit uses a generative AI to analyze the background information of an image and generate a detailed caption based on the image context. For example, for a landscape image, it can generate a specific caption such as "Mountains and lake bathed in a sunset glow." The image analysis unit can also generate a caption such as "A birthday party with friends" for an image of a party. The image analysis unit can also generate a caption such as "New York City at night, the neon lights of Times Square shining" for an image of a cityscape. This makes it possible to generate detailed captions based on the image context.

[0061] The image analysis unit can recognize multiple objects in an image and generate individual captions for each. For example, the image analysis unit uses a generation AI to recognize multiple objects in an image and generate individual captions for each. For example, it can generate a caption such as "A mother and child are playing in the park" for a family photo. The image analysis unit can also generate a caption such as "A lion is resting in the grass" for an image of a zoo. The image analysis unit can also generate a caption such as "Pasta and salad laid out on the table" for an image of food. This makes it possible to generate individual captions for multiple objects.

[0062] The image analysis unit can use the emotion estimation function to estimate an emotion associated with an image and generate a caption based on that emotion. For example, the image analysis unit can use the emotion estimation function to estimate an emotion associated with an image and generate a caption based on that emotion. For example, the image analysis unit can generate a caption such as "Friends laughing happily" for a photo of smiling faces. The image analysis unit can also generate a caption such as "Sad girl" for a photo of sad faces. The image analysis unit can also generate a caption such as "Man with a surprised expression" for a photo of surprised faces. In this way, captions based on emotions associated with images can be generated.

[0063] The caption generation unit generates captions for each frame of a video and can summarize the content of the entire video in text. For example, the caption generation unit uses a generative AI to generate captions for each frame of a video and summarize the content of the entire video in text. For example, for a travel video, it generates a summary such as "Beautiful beaches, historical buildings, local cuisine." The caption generation unit can also generate a summary such as "Game highlights, player interviews, and crowd cheering" for a video of a sporting event. The caption generation unit can also generate a summary such as "Ingredient preparation, cooking steps, and finished dish" for a cooking video. This allows the content of the entire video to be summarized in text.

[0064] The caption generation unit can analyze the style or artistic quality of an image and generate captions from an artistic perspective. For example, the caption generation unit uses a generative AI to analyze the style or artistic quality of an image and generate captions from an artistic perspective. For example, a caption such as "Landscape painting influenced by Impressionism" can be generated for an image of a painting. The caption generation unit can also generate a caption such as "A work characterized by abstract shapes and vivid colors" for an image of modern art. The caption generation unit can also generate a caption such as "A beautiful monochrome portrait" for an image of a photograph. This allows captions to be generated from an artistic perspective.

[0065] The caption generation unit can use the emotion estimation function to estimate the emotion a user is feeling when viewing an image in real time and generate a caption based on that emotion. For example, the caption generation unit can use the emotion estimation function to estimate the emotion a user is feeling when viewing an image in real time and generate a caption based on that emotion. For example, when a user sees a photo of a smiling face, the caption generation unit can generate a caption such as "A fun moment." Furthermore, when a user sees a photo of an inspiring landscape, the caption generation unit can also generate a caption such as "A beautiful, moving landscape." Furthermore, when a user sees a photo of a surprised expression, the caption generation unit can generate a caption such as "A moment of surprise." In this way, captions can be generated according to the user's emotions.

[0066] The reading unit can read the captions generated by the generation AI in a natural voice using speech synthesis technology. For example, the reading unit can read the captions generated by the generation AI in a natural voice using speech synthesis technology. For example, the reading unit can read the caption "Beautiful mountain scenery" in a natural voice. The reading unit can also read the caption "Photo taken with friends" in a natural voice. The reading unit can also read the caption "Mountains and lake dyed in a sunset" in a natural voice. This makes it possible to read captions in a natural voice.

[0067] The reading unit can provide a function that allows the reading speed or tone of voice of the captions to be customized to suit the user's preferences. The reading unit can provide a function that allows the reading speed or tone of voice of the captions to be customized to suit the user's preferences. For example, the reading speed can be increased or the tone of voice can be raised. The reading unit can also slow down the reading speed or lower the tone of voice. The reading unit can also make the tone of voice more emotional or adjust the reading speed. This allows the reading speed and tone of voice to be customized.

[0068] The reading unit can use the emotion estimation function to reflect emotional expressions in the voice according to the content of the caption. The reading unit can use the emotion estimation function to reflect emotional expressions in the voice according to the content of the caption. For example, the reading unit can read a caption such as "Friends laughing happily" in an emotional voice. The reading unit can also read a caption such as "A sad girl" in an emotional voice. The reading unit can also read a caption such as "A man with a surprised expression" in an emotional voice. In this way, emotional expressions in the voice according to the content of the caption can be reflected.

[0069] The reading unit can display captions on a Braille display, allowing visually impaired people to understand the content through their sense of touch. The reading unit can, for example, display captions on a Braille display, allowing visually impaired people to understand the content through their sense of touch. For example, the reading unit can display the caption "Beautiful mountain scenery" in Braille. The reading unit can also display the caption "Photos taken with friends" in Braille. The reading unit can also display the caption "Mountains and lakes bathed in a sunset" in Braille. This allows visually impaired people to understand the content through their sense of touch.

[0070] The reading unit converts captions into sign language in real time, making it possible to provide information to people with hearing impairments. The reading unit, for example, converts captions into sign language in real time, making it possible to provide information to people with hearing impairments. For example, the caption "Beautiful mountain scenery" can be expressed in sign language. The reading unit can also express the caption "Photo taken with friends" in sign language. The reading unit can also express the caption "Mountains and lake bathed in a sunset" in sign language. This makes it possible to provide information to people with hearing impairments.

[0071] The image analysis unit can scan an entire webpage and detect images without alt text in bulk. For example, the image analysis unit uses a generative AI to scan an entire webpage and detect images without alt text in bulk. For example, it can scan all pages of a news site and list images without alt text. The image analysis unit can also scan all product pages of an online shop and identify images without alt text. The image analysis unit can also scan all articles on a blog site and extract images without alt text. This makes it possible to detect images without alt text in bulk.

[0072] The image analysis unit can evaluate the importance of images and prioritize generating captions for important images. For example, the image analysis unit uses a generation AI to evaluate the importance of images and prioritize generating captions for important images. For example, it prioritizes generating captions for the main image of a news article. The image analysis unit can also prioritize generating captions for the main product image on a product page. The image analysis unit can also prioritize generating captions for the top image of a blog article. This allows captions to be generated with priority for important images.

[0073] The image analysis unit can use the emotion estimation function to analyze a user's emotional response to an image without alternative text and generate a caption based on the result. For example, the image analysis unit can use the emotion estimation function to analyze a user's emotional response to an image without alternative text and generate a caption based on the result. For example, the image analysis unit can generate a caption such as "happy scene" for an image in which the user expressed positive emotion. The image analysis unit can also generate a caption such as "surprising moment" for an image in which the user expressed surprised emotion. The image analysis unit can also generate a caption such as "sad scene" for an image in which the user expressed sad emotion. In this way, captions can be generated based on the user's emotional response.

[0074] The image analysis unit can also detect images within documents such as PDFs and e-books and generate captions. For example, the image analysis unit uses a generative AI to detect images within documents such as PDFs and e-books and generate captions. For example, it can generate a caption such as "An illustration depicting a scene from a story" for an illustration in an e-book. The image analysis unit can also generate a caption such as "A graph showing data trends" for a diagram in a technical document. The image analysis unit can also generate a caption such as "A diagram showing experimental results" for a figure in an academic paper. This makes it possible to generate captions for images within documents.

[0075] The image analysis unit can also generate captions in real time for images on social media stories or during live streaming. For example, the image analysis unit uses a generation AI to generate captions in real time for images on social media stories or during live streaming. For example, it generates a caption such as "Current Scenery" for a scene during a live streaming. The image analysis unit can also generate a caption such as "Delicious Dinner" for an image of a meal posted to a story. The image analysis unit can also generate a caption such as "Event Scene" for an image of an event being live streamed. This makes it possible to generate captions in real time for images on social media stories or during live streaming.

[0076] The image analysis unit can use the emotion estimation function to monitor in real time the user's emotions toward an image without alt text and generate a caption based on the emotions. For example, the image analysis unit can use the emotion estimation function to monitor in real time the user's emotions toward an image without alt text and generate a caption based on the emotions. For example, when a user sees an image of a smiling face, the image analysis unit can generate a caption such as "A joyful moment." Furthermore, when a user sees an image of a moving landscape, the image analysis unit can also generate a caption such as "A beautiful, moving landscape." Furthermore, when a user sees an image of a surprised expression, the image analysis unit can generate a caption such as "A moment of surprise." In this way, captions can be generated based on the user's emotions.

[0077] The caption generation unit allows users to provide feedback on captions generated by the generation AI, and the generation AI learns based on that feedback to improve the accuracy of the captions. For example, the caption generation unit allows users to provide feedback on captions generated by the generation AI, and the generation AI learns based on that feedback to improve the accuracy of the captions. For example, the caption generation unit can correct "photo of a dog" to "photo of my beloved dog." The caption generation unit can also correct "sunset scenery" to "mountains with a beautiful sunset." The caption generation unit can also correct "photo of friends" to "photo taken with friends from college." This allows the accuracy of captions to be improved based on user feedback.

[0078] The caption generation unit can provide a function that saves the caption customization history and allows the user to refer to past customizations. The caption generation unit, for example, saves the caption customization history and allows the user to refer to past customizations. For example, it displays a list of captions that have been modified in the past. The caption generation unit can also display the customization history made to a specific image. The caption generation unit can also display the customization history in chronological order and check past changes. This allows the user to refer to past customizations.

[0079] The caption generation unit can use the emotion estimation function to analyze the emotion a user has when customizing a caption and make customization suggestions based on that emotion. The caption generation unit can, for example, use the emotion estimation function to analyze the emotion a user has when customizing a caption and make customization suggestions based on that emotion. For example, if the user expresses positive emotion, the caption generation unit can make a suggestion such as "add more detailed information." In addition, if the user expresses negative emotion, the caption generation unit can also make a suggestion such as "change the caption to a concise one." In addition, if the user expresses surprise, the caption generation unit can also make a suggestion such as "emphasize the element of surprise." In this way, customization suggestions can be made based on the user's emotion.

[0080] The caption generator may provide a function that allows a user to share captions generated by the generation AI with other users and collaboratively customize them. For example, the caption generator may provide a function that allows a user to share captions generated by the generation AI with other users and collaboratively customize them. For example, revising captions together with family and friends. The caption generator may also allow a user to revise image captions for a project together with colleagues. The caption generator may also allow a user to share captions in an online community and exchange opinions. This allows a user to collaboratively customize captions with other users.

[0081] The caption generation unit may enable caption customization through voice input, making it easier for visually impaired people to customize captions. The caption generation unit may enable caption customization through voice input, making it easier for visually impaired people to customize captions. For example, the caption generation unit may voice input "Edit caption." The caption generation unit may also voice input "Add details to caption." The caption generation unit may also voice input "Delete caption." This allows visually impaired people to customize captions through voice input.

[0082] The caption generation unit can use the emotion estimation function to monitor the emotion of the user when customizing captions in real time and suggest customizations according to the emotion. The caption generation unit can, for example, use the emotion estimation function to monitor the emotion of the user when customizing captions in real time and suggest customizations according to the emotion. For example, when the user expresses positive emotion, the caption generation unit can suggest, for example, "add more detailed information." In addition, when the user expresses negative emotion, the caption generation unit can also suggest, for example, "change the caption to a concise one." In addition, when the user expresses surprise, the caption generation unit can also suggest, for example, "emphasize the element of surprise." In this way, customizations can be suggested according to the user's emotion.

[0083] The caption generation unit can generate captions taking into account the nuances and cultural backgrounds of different languages. For example, the generation AI generates captions taking into account the nuances and cultural backgrounds of different languages. For example, cultural nuances can be reflected when translating Japanese image captions into English. The caption generation unit can also take cultural backgrounds into account when translating Spanish image captions into French. The caption generation unit can also reflect cultural nuances when translating Chinese image captions into German. This allows captions to be generated taking into account the nuances and cultural backgrounds of different languages.

[0084] The caption generation unit can use the emotion estimation function to analyze a user's emotional response to captions in different languages ​​and adjust the captions based on the results. For example, the caption generation unit can use the emotion estimation function to analyze a user's emotional response to captions in different languages ​​and adjust the captions based on the results. For example, the caption generation unit can adjust Japanese captions based on a positive response to English captions. The caption generation unit can also adjust French captions based on a negative response to Spanish captions. The caption generation unit can also adjust German captions based on a surprised response to Chinese captions. This allows captions to be adjusted based on a user's emotional response to captions in different languages.

[0085] The caption generation unit can also handle non-verbal expressions such as sign language and Braille, and provide information to the visually impaired and the hearing impaired. For example, the generation AI can handle non-verbal expressions such as sign language and Braille, and provide information to the visually impaired and the hearing impaired. For example, captions can be expressed in sign language. The caption generation unit can also display captions on a Braille display. The caption generation unit can also generate sign language video to express captions. This allows for support of non-verbal expressions such as sign language and Braille.

[0086] The caption generation unit can provide a function to read captions in different languages ​​in a natural voice using speech synthesis technology. The caption generation unit, for example, provides a function in which a generation AI reads captions in different languages ​​in a natural voice using speech synthesis technology. For example, English captions are read in a natural voice. The caption generation unit can also read Japanese captions in a natural voice. The caption generation unit can also read Spanish captions in a natural voice. This makes it possible to read captions in different languages ​​in a natural voice.

[0087] The caption generation unit can use the emotion estimation function to monitor users' emotions toward captions in different languages ​​in real time and adjust the captions based on the emotions. For example, the caption generation unit can use the emotion estimation function to monitor users' emotions toward captions in different languages ​​in real time and adjust the captions based on the emotions. For example, the caption generation unit can adjust Japanese captions based on a positive reaction to English captions. The caption generation unit can also adjust French captions based on a negative reaction to Spanish captions. The caption generation unit can also adjust German captions based on a surprised reaction to Chinese captions. This allows users' emotions toward captions in different languages ​​to be monitored in real time and the captions to be adjusted based on the emotions.

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

[0089] The caption generation unit can customize the style of captions based on the user's preferences. For example, if a user prefers a formal style, the unit can generate a caption such as "This image shows mountains and a lake bathed in a sunset glow." For a user who prefers a casual style, the unit can generate a caption such as "The mountains and lake at sunset are so beautiful!" For a user who prefers a humorous style, the unit can generate a caption such as "The mountains and lake look stylish in the sunset!" This allows the unit to provide captions that suit the user's preferences.

[0090] The caption generator can provide relevant information based on the content of an image. For example, for a landscape image, it can generate a caption such as "This mountain is Mount Fuji, and it is 3,776 meters high." For an image of a historical building, it can generate a caption such as "This building is the Eiffel Tower, completed in 1889." For an image of an animal, it can generate a caption such as "This animal is an African elephant, and it can weigh up to 6,000 kilograms." This allows it to provide detailed information related to the image.

[0091] The caption generator can personalize captions based on a user's past search history and interests. For example, if a user has performed many travel-related searches in the past, a caption such as "This place is the next place you want to visit" can be generated for a travel photo. If a user is interested in cooking, a caption such as "This is your favorite Italian dish" can be generated for an image of food. Furthermore, if a user is interested in sports, a caption such as "This game is for the team you support" can be generated for an image of a sporting event. This allows captions to be provided based on the user's interests.

[0092] The caption generation unit can use the emotion estimation function to estimate the emotion a user is feeling when viewing an image in real time and generate a caption based on that emotion. For example, when a user sees a photo of a smiling face, the caption generation unit can generate a caption such as "A joyful moment." When a user sees a photo of an inspiring landscape, the caption generation unit can also generate a caption such as "A beautiful, moving landscape." When a user sees a photo of a surprised face, the caption generation unit can also generate a caption such as "A moment of surprise." This allows captions to be generated according to the user's emotions.

[0093] The caption generation unit uses the emotion estimation function to monitor the user's emotions in real time when customizing captions and can make customization suggestions based on those emotions. For example, if the user expresses positive emotions, the caption generation unit can make a suggestion such as "add more detailed information." The caption generation unit can also make a suggestion such as "change the caption to a concise one" if the user expresses negative emotions. The caption generation unit can also make a suggestion such as "emphasize the element of surprise" if the user expresses surprise. This makes it possible to make customization suggestions based on the user's emotions.

[0094] The caption generator can use the emotion estimation function to analyze users' emotional responses to captions in different languages ​​and adjust the captions based on the results. For example, Japanese captions can be adjusted based on positive responses to English captions. The caption generator can also adjust French captions based on negative responses to Spanish captions. The caption generator can also adjust German captions based on surprised responses to Chinese captions. This allows captions to be adjusted based on users' emotional responses to captions in different languages.

[0095] The caption generation unit uses the emotion estimation function to allow users to provide feedback on the captions generated by the generation AI, and the generation AI can learn from that feedback to improve the accuracy of the captions. For example, a caption could be corrected from "a photo of a dog" to "a photo of my beloved dog." The caption generation unit could also correct a "sunset landscape" to "mountains with a beautiful sunset." The caption generation unit could also correct a "photo of friends" to "a photo taken with friends from college." This allows the accuracy of captions to be improved based on user feedback.

[0096] The caption generator may provide a feature that allows users to share captions generated by the generation AI with other users and collaboratively customize them. For example, users can revise captions together with family and friends. The caption generator may also allow users to revise image captions for a project together with colleagues. The caption generator may also allow users to share captions in an online community and exchange opinions. This allows users to collaboratively customize captions with other users.

[0097] The caption generation unit can generate captions taking into account the nuances and cultural backgrounds of different languages. For example, cultural nuances can be reflected when translating Japanese image captions into English. The caption generation unit can also take into account cultural backgrounds when translating Spanish image captions into French. The caption generation unit can also take into account cultural nuances when translating Chinese image captions into German. This allows captions to be generated taking into account the nuances and cultural backgrounds of different languages.

[0098] The caption generator may allow for customization of captions through voice input, making it easier for visually impaired people to customize captions. For example, the caption generator may allow for voice input of "Edit caption." The caption generator may also allow for voice input of "Add details to caption." The caption generator may also allow for voice input of "Delete caption." This allows visually impaired people to customize captions through voice input.

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

[0100] Step 1: The image analysis unit analyzes the image. For example, the image analysis unit may analyze the content of the image using an image recognition algorithm to identify the type of image being analyzed. Step 2: The caption generator generates a caption based on the image analyzed by the image analyzer. For example, the caption generator may generate a caption using natural language generation technology and may specify the format of the generated caption. Step 3: The text storage unit stores the captions generated by the caption generation unit. For example, the text storage unit may store the captions in a database and specify a file format for storing the captions. Step 4: The reading unit reads out the captions stored by the text storage unit. For example, the reading unit can use voice synthesis technology to read out the captions and can also specify the timing of reading out, which allows visually impaired people to understand the content of the images.

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

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (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.

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

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0118] 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.

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

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

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[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 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.

[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 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.

[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 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.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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 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.

[0146] 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.

[0147] 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.

[0148] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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."

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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]

[0168] 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 image analysis unit that analyzes an image; a caption generation unit that generates a caption based on the image analyzed by the image analysis unit; a text storage unit that stores the captions generated by the caption generation unit; a reading unit that reads out the captions stored by the text storage unit. A system characterized by:

2. The image analysis unit Analyzes the background information of an image and generates detailed captions based on the image context 2. The system of claim 1.

3. The image analysis unit Recognize multiple objects in an image and generate individual captions for each one 2. The system of claim 1.

4. The image analysis unit Estimate the emotion associated with an image and generate a caption based on that emotion 2. The system of claim 1.

5. The caption generation unit Generate captions for each frame of a video and provide a text summary of the entire video 2. The system of claim 1.

6. The caption generation unit Analyzes the style or artistic value of an image and generates artistic captions 2. The system of claim 1.

7. The caption generation unit Estimates the user's emotions in real time as they view an image and generates captions based on those emotions.

2. The system of claim 1.

8. The reading unit Captions generated by the AI ​​are read out in a natural voice using speech synthesis technology.

2. The system of claim 1.

Images