system

Abstract

The system according to the embodiment aims to enable visually impaired people to distinguish between images on the Internet and on social networking sites. [Solution] A system according to an embodiment includes an acquisition unit, an analysis unit, a generation unit, and a provision unit. The acquisition unit acquires image data. The analysis unit analyzes the image data acquired by the acquisition unit. The generation unit generates captions based on the data analyzed by the analysis unit. The provision unit provides the captions generated by the generation unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technology makes it difficult for visually impaired people to distinguish images on the internet or social networking sites, and there is room for improvement.

[0005] The system according to the embodiment aims to enable visually impaired people to distinguish between images on the Internet and on social networking sites. [Means for solving the problem]

[0006] A system according to an embodiment includes an acquisition unit, an analysis unit, a generation unit, and a provision unit. The acquisition unit acquires image data. The analysis unit analyzes the image data acquired by the acquisition unit. The generation unit generates a caption based on the data analyzed by the analysis unit. The provision unit provides the caption generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can enable visually impaired people to distinguish between images on the Internet and on social networking sites. [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) An automatic captioning system according to an embodiment of the present invention enables visually impaired people to identify the nature of images posted on the Internet or social networking sites using their PCs or smartphones. When a user browses images on the Internet or social networking sites, the automatic captioning system sends the image data to a generation AI, which analyzes the image data, understands its content, and generates a caption. The generated caption is then sent to the user's screen reader and read aloud. For example, for a landscape image, the automatic captioning system generates a caption such as "blue sky and green field." The generation AI continuously learns and can improve the accuracy of the captions. For example, it can generate captions tailored to specific user preferences. Furthermore, the automatic captioning system is usable not only by visually impaired people but also by general users who want to quickly understand the content of images. For example, when a large number of images are posted on a news site, the generation AI can automatically add captions, allowing users to quickly understand the content of the images. This makes the automatic captioning system a useful tool for supporting visually impaired people's use of the Internet and social networking sites and quickly understanding the content of images. For example, visually impaired people will be able to understand the content of images, making it easier to use the internet and social networking sites. General users will also be able to quickly understand the content of images, making it more efficient to gather information from news sites and other sources.

[0029] An automatic captioning system according to an embodiment includes an acquisition unit, an analysis unit, a generation unit, and a provision unit. The acquisition unit acquires image data. The image data may be in formats such as, but not limited to, JPEG, PNG, and GIF. The acquisition unit may automatically acquire images from the Internet or from a user uploading an image. The analysis unit analyzes the image data acquired by the acquisition unit. The analysis may be performed based on, but not limited to, an image recognition algorithm or a feature extraction method. For example, the analysis unit extracts features such as the color, shape, and texture of the image. The generation unit generates captions based on the data analyzed by the analysis unit. The captions may be generated based on, but not limited to, the length of the sentence and the level of detail of the information. For example, the generation unit uses a generation AI to generate captions that describe the content of the image. The provision unit provides the captions generated by the generation unit. The provision may be performed by, but not limited to, reading the captions aloud using a screen reader or displaying them in text format. For example, the providing unit transmits the generated caption to a user's device and reads it aloud. This allows the automatic captioning system according to the embodiment to enable visually impaired people to understand the content of an image. Some or all of the above-described processing in the generating unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generating unit may input data analyzed by the analyzing unit into the generating AI and cause the generating AI to generate a caption.

[0030] The automatic captioning system includes a collection unit that collects user feedback. The collection unit collects user feedback. Examples of the feedback include, but are not limited to, questionnaires and user reviews. For example, the collection unit provides an interface for users to rate captions. The collection unit can also build a system that automatically collects user feedback. For example, the collection unit collects user opinions regarding the quality of captions and uses the collected opinions to improve the system. This allows the collected user feedback to be used to improve the system. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit may input user feedback data into the generation AI and cause the generation AI to analyze the feedback.

[0031] The automatic captioning system includes a learning unit that causes the generation AI to learn based on collected feedback. The learning unit causes the generation AI to learn based on the collected feedback. The generation AI may perform learning using, for example, but not limited to, technologies such as neural networks and deep learning. For example, the learning unit may analyze user feedback data and use it as learning data for the generation AI. The learning unit may also construct a system for the generation AI to continuously learn. For example, the learning unit may periodically collect feedback data and update the learning data for the generation AI. This allows the generation AI to continuously learn and improve the accuracy of captions. Some or all of the above-described processing in the learning unit is performed using the generation AI. For example, the learning unit inputs collected feedback data into the generation AI, and the generation AI learns.

[0032] The automatic captioning system includes a customization unit that customizes captions to suit the user's preferences. The customization unit customizes captions to suit the user's preferences. Examples of customization include, but are not limited to, a user profile and past usage history. For example, the customization unit adjusts the content and format of captions based on the user's preferences. The customization unit can also build a system that customizes captions based on user feedback. For example, the customization unit generates similar captions based on the characteristics of captions that the user has previously rated highly. This makes it possible to provide captions that match the user's preferences. Some or all of the above-described processing in the customization unit is performed using a generation AI. For example, the customization unit inputs user profile data into the generation AI, which then customizes the captions.

[0033] The acquisition unit can automatically acquire images when a user uploads an image or on the Internet. For example, when a user uploads an image, the acquisition unit acquires image data. The acquisition unit can also automatically acquire images on the Internet. For example, the acquisition unit acquires image data using a specific website or API. This makes it possible to automatically acquire images uploaded by a user or images on the Internet. Some or all of the above-mentioned processing in the acquisition unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the acquisition unit can input image data on the Internet into the generation AI and cause the generation AI to acquire the image data.

[0034] The generation unit can extract image features and generate a caption based on the extracted features. The generation unit, for example, extracts image features and generates a caption based on the extracted features. Features include, but are not limited to, color, shape, and texture. For example, the generation unit can analyze the color and shape of an image and generate a caption based on the extracted features. The generation unit can also analyze the texture of an image and generate a caption based on the extracted features. This allows for more accurate captions to be provided by extracting image features and generating captions. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image feature data into the generation AI and cause the generation AI to generate a caption.

[0035] The acquisition unit can analyze the user's past image viewing history and select an appropriate acquisition method. The acquisition unit, for example, analyzes the user's past image viewing history and selects an appropriate acquisition method. Past image viewing history includes, but is not limited to, log data and click history. For example, the acquisition unit prioritizes acquiring similar images based on the types of images the user frequently viewed in the past. The acquisition unit can also analyze the user's past viewing history to determine the tendency of images viewed during a specific time period and select an optimal acquisition method. The acquisition unit can also prioritize acquiring similar images based on the characteristics of images that the user has previously rated highly. By selecting an optimal acquisition method based on the user's past viewing history, images that are useful to the user can be prioritized. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's past image viewing history data into the generation AI and cause the generation AI to select an optimal acquisition method.

[0036] The acquisition unit may perform filtering based on the user's current areas of interest when acquiring image data. For example, the acquisition unit may perform filtering based on the user's current areas of interest when acquiring image data. Areas of interest include, but are not limited to, survey results and past search history. For example, the acquisition unit may preferentially acquire images related to topics in which the user is currently interested. The acquisition unit may also filter and acquire related images based on keywords recently searched by the user. The acquisition unit may also preferentially acquire images posted on social media accounts that the user follows. By doing so, highly relevant images can be acquired by filtering images based on the user's areas of interest. Some or all of the above-described processing in the acquisition unit may be performed using a generation AI. For example, the acquisition unit may input the user's area of ​​interest data into the generation AI and cause the generation AI to perform filtering.

[0037] The acquisition unit can select an appropriate acquisition means according to the user's input method when acquiring image data. For example, the acquisition unit selects an appropriate acquisition means according to the user's input method when acquiring image data. Input methods include, but are not limited to, keyboard input, voice input, and touch input. For example, if the user uses voice input, the acquisition unit can acquire images based on a voice command. Also, if the user uses text input, the acquisition unit can acquire images based on an entered keyword. Also, if the user uploads an image, the acquisition unit can acquire images related to the uploaded image. This allows images to be acquired efficiently by selecting the optimal acquisition means according to the user's input method. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's input data to the generation AI and cause the generation AI to select the optimal acquisition means.

[0038] The acquisition unit can prioritize acquisition of highly relevant images based on the user's geographical location information when acquiring image data. For example, when acquiring image data, the acquisition unit prioritizes acquisition of highly relevant images based on the user's geographical location information. Geographical location information includes, but is not limited to, GPS data and IP address. For example, when the user is in a specific area, the acquisition unit prioritizes acquisition of images related to that area. Furthermore, when the user is traveling, the acquisition unit can prioritize acquisition of images of tourist spots related to the travel destination. Furthermore, when the user is at home, the acquisition unit can prioritize acquisition of images related to events and news around the user's home. This allows for acquisition of highly relevant images taking into account the user's geographical location information, thereby providing useful information to the user. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's geographical location information data into the generation AI and cause the generation AI to acquire highly relevant images.

[0039] The acquisition unit can analyze the user's social media activity and acquire related images when acquiring image data. For example, the acquisition unit can analyze the user's social media activity and acquire related images when acquiring image data. Social media activity includes, but is not limited to, the content of posts and the number of likes. For example, the acquisition unit can prioritize acquiring images posted by accounts the user follows on social media. The acquisition unit can also analyze the content of the user's social media posts and acquire related images. The acquisition unit can also acquire related images by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity and acquiring related images, it is possible to provide useful information to the user. Some or all of the above-mentioned processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's social media activity data into the generation AI and cause the generation AI to acquire related images.

[0040] The acquisition unit can customize the acquisition method by reflecting the user's past feedback when acquiring image data. For example, the acquisition unit customizes the acquisition method by reflecting the user's past feedback when acquiring image data. Past feedback includes, but is not limited to, survey results and user reviews. For example, the acquisition unit preferentially acquires similar images based on the characteristics of images that the user has previously rated highly. The acquisition unit can also select images to acquire while avoiding the characteristics of images that the user has previously rated poorly. The acquisition unit can also analyze the user's past feedback and customize the optimal acquisition method. By customizing the acquisition method by reflecting the user's past feedback, more appropriate images can be acquired. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the acquisition method.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance of the image during image analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the image during image analysis. The importance of an image includes, but is not limited to, the user's level of interest and the content of the image. For example, the analysis unit may perform a detailed analysis of an image containing important information, analyzing all elements. Alternatively, the analysis unit may perform a concise analysis of a general image, analyzing only key elements. Alternatively, the analysis unit may perform a particularly detailed analysis of an image in which the user is particularly interested, providing related information. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the image. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit may input image importance data into the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0042] The analysis unit can apply different analysis algorithms depending on the image category during image analysis. For example, the analysis unit applies different analysis algorithms depending on the image category during image analysis. Image categories include, but are not limited to, landscapes, people, and animals. For example, the analysis unit applies an algorithm that analyzes natural elements in the case of landscape images. The analysis unit can also apply a face recognition algorithm in the case of portrait images. The analysis unit can also apply an algorithm that analyzes product information in the case of product images. This improves the accuracy of analysis by applying an appropriate analysis algorithm depending on the image category. Some or all of the above-mentioned processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input image category data into the generation AI and cause the generation AI to apply the analysis algorithm.

[0043] The analysis unit can improve the accuracy of the image analysis by referring to the user's past analysis results. For example, the analysis unit can improve the accuracy of the image analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, log data and analysis reports. For example, the analysis unit performs a similar analysis based on analysis results that the user previously rated highly. The analysis unit can also adjust the analysis method by avoiding analysis results that the user previously rated poorly. The analysis unit can also analyze the user's past analysis results and select the optimal analysis method. By referring to the user's past analysis results, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0044] The analysis unit can determine the analysis priority based on the time of image submission during image analysis. For example, the analysis unit determines the analysis priority based on the time of image submission during image analysis. The submission time includes, but is not limited to, a timestamp or a submission date and time. For example, the analysis unit prioritizes analyzing the most recent image. The analysis unit can also prioritize analyzing images submitted by a user during a specific time period. The analysis unit can also determine the analysis priority by referring to images submitted by the user in the past. This allows for efficient analysis by determining the analysis priority based on the time of image submission. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input image submission time data into the generation AI and have the generation AI determine the priority.

[0045] The analysis unit can adjust the analysis order based on the relevance of the images during image analysis. For example, the analysis unit adjusts the analysis order based on the relevance of the images during image analysis. Image relevance includes, but is not limited to, common tags and similarity scores. For example, the analysis unit prioritizes analyzing images related to topics in which the user is interested. The analysis unit can also prioritize analyzing images related to images that the user has previously rated highly. The analysis unit can also prioritize analyzing highly relevant images based on the user's current search history. This allows for efficient analysis by adjusting the analysis order based on the relevance of the images. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input image relevance data into the generation AI and cause the generation AI to adjust the analysis order.

[0046] The analysis unit can adjust the use of technical terms during image analysis according to the user's level of expertise. For example, the analysis unit can adjust the use of technical terms during image analysis according to the user's level of expertise. Examples of technical terms include, but are not limited to, survey results and past usage history. For example, if the user is an expert, the analysis unit can display the analysis results using detailed technical terms. If the user is a general user, the analysis unit can also display the analysis results using concise and easy-to-understand terms. The analysis unit can also select optimal terms based on feedback from the user's past analysis results. This allows for more appropriate analysis results by adjusting the use of technical terms during analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI adjust the use of technical terms.

[0047] The generation unit can adjust the level of detail of the caption based on the importance of the image when generating the caption. For example, the generation unit adjusts the level of detail of the caption based on the importance of the image when generating the caption. The level of detail of the caption includes, but is not limited to, the comprehensiveness of the information and the length of the sentence. For example, the generation unit generates a detailed caption for an image containing important information. The generation unit can also generate a concise caption for a general image. The generation unit can also generate a particularly detailed caption for an image in which the user is particularly interested. This allows for efficient caption generation by adjusting the level of detail of the caption based on the importance of the image. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image importance data to the generation AI and cause the generation AI to adjust the level of detail of the caption.

[0048] The generation unit can apply different generation algorithms depending on the image category when generating captions. For example, the generation unit applies different generation algorithms depending on the image category when generating captions. Image categories include, but are not limited to, landscapes, people, and animals. For example, the generation unit generates a caption that emphasizes natural elements for a landscape image. For a portrait image, the generation unit can also generate a caption based on facial recognition. For a product image, the generation unit can also generate a caption that describes product information in detail. This improves the accuracy of the caption by applying an appropriate generation algorithm depending on the image category. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image category data into the generation AI and cause the generation AI to apply the generation algorithm.

[0049] The generation unit can improve the accuracy of caption generation by referring to the user's past caption results. For example, the generation unit can improve the accuracy of caption generation by referring to the user's past caption results. Past caption results include, but are not limited to, log data and user reviews. For example, the generation unit generates similar captions based on captions that the user has previously rated highly. The generation unit can also adjust the generation method to avoid captions that the user has previously rated poorly. The generation unit can also analyze the user's past caption results and select the optimal generation method. This improves the accuracy of captions by referring to the user's past caption results. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input the user's past caption result data into the generation AI and cause the generation AI to improve the accuracy of caption generation.

[0050] The generation unit can determine the priority of captions based on the time of image submission when generating captions. For example, the generation unit determines the priority of captions based on the time of image submission when generating captions. The submission time includes, but is not limited to, a timestamp or a submission date and time. For example, the generation unit generates captions with priority for the most recent image. The generation unit can also generate captions with priority for images submitted by a user within a specific time period. The generation unit can also determine the priority of captions by referring to images previously submitted by the user. This allows for efficient caption generation by determining the priority of captions based on the time of image submission. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image submission date data into the generation AI and have the generation AI determine the priority.

[0051] The generation unit can adjust the order of captions based on the relevance of the images when generating captions. For example, the generation unit adjusts the order of captions based on the relevance of the images when generating captions. Image relevance includes, but is not limited to, common tags and similarity scores. For example, the generation unit may prioritize generating captions for images related to topics in which the user is interested. The generation unit may also prioritize generating captions for images related to images that the user has previously rated highly. The generation unit may also prioritize generating captions for highly relevant images based on the user's current search history. This allows for efficient caption generation by adjusting the order of captions based on the relevance of the images. Some or all of the above-described processing in the generation unit may be performed using a generation AI. For example, the generation unit may input image relevance data to the generation AI and cause the generation AI to adjust the order of captions.

[0052] The generation unit can adjust the use of technical terms in captions according to the user's level of expertise when generating captions. For example, the generation unit can adjust the use of technical terms in captions according to the user's level of expertise when generating captions. Expertise levels include, but are not limited to, survey results and past usage history. For example, if the user is an expert, the generation unit can generate captions using detailed technical terms. If the user is a general user, the generation unit can also generate captions using concise and easy-to-understand terms. The generation unit can also select optimal terms based on feedback from the user's past caption results. This allows for more appropriate captions to be provided by adjusting the use of technical terms in captions according to the user's level of expertise. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0053] The providing unit can select the optimal caption delivery method by referring to the user's past usage history when providing captions. For example, the providing unit can select the optimal caption delivery method by referring to the user's past usage history when providing captions. Examples of past usage history include, but are not limited to, log data and user reviews. For example, if the user previously received captions in audio format, the providing unit can provide them in the same manner. Furthermore, if the user previously received captions in text format, the providing unit can also provide them in the same manner. Furthermore, the providing unit can analyze the user's past usage history and select the optimal caption delivery method. By selecting the optimal caption delivery method by referring to the user's past usage history, more appropriate captions can be provided. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input the user's past usage history data into the generation AI and have the generation AI select the delivery method.

[0054] The providing unit can customize the provided content according to the user's current task when providing captions. For example, the providing unit customizes the provided content according to the user's current task when providing captions. The current task includes, but is not limited to, an activity log or user input. For example, the providing unit can provide concise and to-the-point captions when the user is working. The providing unit can also provide detailed and emotive captions when the user is relaxed. The providing unit can also provide captions that are quickly understandable when the user is in a hurry. This allows for more appropriate captions to be provided by customizing the provided content according to the user's current task. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input the user's current task data into the generation AI and cause the generation AI to customize the provided content.

[0055] The providing unit can improve the caption providing method by reflecting user feedback when providing captions. For example, the providing unit improves the caption providing method by reflecting user feedback when providing captions. Feedback includes, but is not limited to, survey results and user reviews. For example, the providing unit provides captions in a similar manner based on a caption providing method that a user has previously rated highly. The providing unit can also improve the caption providing method by avoiding a caption providing method that a user has previously rated poorly. The providing unit can also analyze users' past feedback and select an optimal caption providing method. By improving the caption providing method by reflecting user feedback, more appropriate captions can be provided. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input user feedback data into the generation AI and cause the generation AI to improve the caption providing method.

[0056] The providing unit can select the optimal caption providing method by taking into consideration the user's device information when providing captions. For example, the providing unit selects the optimal caption providing method by taking into consideration the user's device information when providing captions. Device information includes, but is not limited to, the device type and OS version. For example, if the user is using a smartphone, the providing unit can provide captions tailored to the screen size. Furthermore, if the user is using a tablet, the providing unit can provide captions optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can provide concise, highly visible captions. This allows for more appropriate captions to be provided by selecting the optimal caption providing method by taking into consideration the user's device information. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input the user's device information data into the generation AI and have the generation AI select the caption providing method.

[0057] The providing unit can provide multilingual content in accordance with the user's language setting when providing captions. For example, the providing unit can provide multilingual content in accordance with the user's language setting when providing captions. Language settings include, but are not limited to, user configuration information and browser language settings. For example, the providing unit can automatically set the caption language based on the language setting of the user's device. The providing unit can also provide a language switching function when the user uses multiple languages. The providing unit can also provide captions in a specific language when the user selects that language. This allows for more appropriate captions to be provided by providing multilingual content in accordance with the user's language setting. Some or all of the above-described processing by the providing unit can be performed using a generation AI. For example, the providing unit can input the user's language setting data into the generation AI and cause the generation AI to execute multilingual content.

[0058] The providing unit can customize the caption providing method according to the degree of the user's visual impairment when providing captions. For example, the providing unit customizes the caption providing method according to the degree of the user's visual impairment when providing captions. The degree of visual impairment includes, but is not limited to, medical diagnosis results and self-reporting. For example, if the user is completely blind, the providing unit can provide captions by audio. Also, if the user has low vision, the providing unit can provide captions in a large font. The providing unit can also select the optimal caption providing method according to the user's degree of visual impairment. This allows for more appropriate captions to be provided by customizing the caption providing method according to the user's degree of visual impairment. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input data on the user's degree of visual impairment into the generation AI and cause the generation AI to customize the caption providing method.

[0059] The collection unit can select the optimal collection method by referring to the user's past feedback history when collecting feedback. For example, the collection unit selects the optimal collection method by referring to the user's past feedback history when collecting feedback. Past feedback history includes, but is not limited to, survey results and user reviews. For example, if the user has provided detailed feedback in the past, the collection unit collects it in a similar manner. Furthermore, if the user has provided brief feedback in the past, the collection unit can collect it in a similar manner. Furthermore, the collection unit can analyze the user's past feedback history and select the optimal collection method. In this way, by selecting the optimal collection method by referring to the user's past feedback history, more appropriate feedback can be collected. Some or all of the above-described processing in the collection unit can be performed using a generation AI. For example, the collection unit can input the user's past feedback history data into the generation AI and cause the generation AI to select the collection method.

[0060] The collection unit can customize the collected content based on the user's current usage status when collecting feedback. For example, the collection unit customizes the collected content based on the user's current usage status when collecting feedback. The current usage status includes, but is not limited to, an activity log and user input. For example, the collection unit may request brief and to-the-point feedback when the user is working. The collection unit may also request detailed feedback when the user is relaxed. The collection unit may also collect quick feedback when the user is in a hurry. This allows for more appropriate feedback to be collected by customizing the collected content based on the user's current usage status. Some or all of the above-described processing in the collection unit is performed using a generation AI. For example, the collection unit may input the user's current usage status data into the generation AI and cause the generation AI to customize the collected content.

[0061] The collection unit can select the optimal collection method by taking into account the user's device information when collecting feedback. For example, the collection unit selects the optimal collection method by taking into account the user's device information when collecting feedback. Device information includes, but is not limited to, the device type and OS version. For example, if the user is using a smartphone, the collection unit can provide a feedback collection method tailored to the screen size. Furthermore, if the user is using a tablet, the collection unit can provide a feedback collection method optimized for a large screen. Furthermore, if the user is using a smartwatch, the collection unit can provide a feedback collection method that is concise and highly visible. This allows for more appropriate feedback to be collected by selecting the optimal collection method by taking into account the user's device information. Some or all of the above-described processing in the collection unit is performed using a generation AI. For example, the collection unit can input the user's device information data into the generation AI and cause the generation AI to select a collection method.

[0062] The collection unit can make the collected content multilingual in accordance with the user's language setting when collecting feedback. For example, the collection unit can make the collected content multilingual in accordance with the user's language setting when collecting feedback. Language settings include, but are not limited to, user settings information and browser language settings. For example, the collection unit can automatically set the language for collecting feedback based on the language setting of the user's device. The collection unit can also provide a language switching function when the user uses multiple languages. If the user selects a specific language, the collection unit can also collect feedback in that language. This allows for more appropriate feedback to be collected by making the collected content multilingual in accordance with the user's language setting. Some or all of the above-described processing by the collection unit can be performed using a generation AI. For example, the collection unit can input the user's language setting data into the generation AI and cause the generation AI to execute the multilingual collected content.

[0063] The learning unit can optimize the learning algorithm by referring to past learning data during learning. For example, the learning unit optimizes the learning algorithm by referring to past learning data during learning. Past learning data includes, but is not limited to, log data and learning reports. For example, the learning unit selects an optimal learning algorithm based on the past learning data. The learning unit can also analyze the past learning data and adjust parameters of the learning algorithm. The learning unit can also improve the accuracy of the learning algorithm by referring to the past learning data. In this way, optimizing the learning algorithm by referring to the past learning data improves the accuracy of learning. Some or all of the above-mentioned processing in the learning unit can be performed using a generation AI. For example, the learning unit can input past learning data into the generation AI and cause the generation AI to optimize the learning algorithm.

[0064] The learning unit can update the learning data to reflect user feedback during learning. For example, the learning unit updates the learning data to reflect user feedback during learning. Feedback includes, but is not limited to, survey results and user reviews. For example, the learning unit updates the learning data based on feedback provided by the user. The learning unit can also analyze user feedback to improve the accuracy of the learning data. The learning unit can also optimize the learning algorithm by reflecting user feedback. In this way, updating the learning data to reflect user feedback improves the accuracy of learning. Some or all of the above-mentioned processing in the learning unit can be performed using a generation AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to update the learning data.

[0065] The learning unit can weight the learning data based on the time of submission of the image data during learning. For example, the learning unit weights the learning data based on the time of submission of the image data during learning. The submission time includes, but is not limited to, a timestamp or a submission date and time. For example, the learning unit weights the most recent image data to improve the accuracy of learning. The learning unit can also weight image data submitted by the user during a specific time period. The learning unit can also weight the learning data by referring to image data submitted by the user in the past. In this way, weighting the learning data based on the time of submission of the image data improves the accuracy of learning. Some or all of the above-described processing in the learning unit can be performed using a generation AI. For example, the learning unit can input data on the time of submission of the image data to the generation AI and cause the generation AI to perform weighting.

[0066] The learning unit can integrate information from different data sources to enrich the training data during learning. For example, the learning unit integrates information from different data sources to enrich the training data during learning. Data sources include, but are not limited to, web data and sensor data. For example, the learning unit integrates image data from different social media platforms to learn. The learning unit can also integrate image data from news sites and blogs to learn. The learning unit can also integrate image data uploaded by users to learn. In this way, the accuracy of learning is improved by integrating information from different data sources to enrich the training data. Some or all of the above-described processing in the learning unit is performed using a generative AI. For example, the learning unit can input information from different data sources into the generative AI and have the generative AI perform the integration.

[0067] The customization unit can select the optimal customization method by referring to the user's past customization history when customizing captions. For example, the customization unit can select the optimal customization method by referring to the user's past customization history when customizing captions. Past customization history includes, but is not limited to, log data and user reviews. For example, if the user previously preferred detailed captions, the customization unit can customize them in a similar manner. Furthermore, if the user previously preferred concise captions, the customization unit can also customize them in a similar manner. The customization unit can also analyze the user's past customization history and select the optimal customization method. By selecting the optimal customization method by referring to the user's past customization history, more appropriate captions can be provided. Some or all of the above-described processing in the customization unit can be performed using a generation AI. For example, the customization unit can input the user's past customization history data into the generation AI and have the generation AI select a customization method.

[0068] The customization unit can adjust the customization content based on the user's current usage status when customizing captions. For example, the customization unit adjusts the customization content based on the user's current usage status when customizing captions. Current usage status includes, but is not limited to, activity logs and user input. For example, the customization unit can provide concise and to-the-point captions when the user is working. The customization unit can also provide detailed and emotive captions when the user is relaxed. The customization unit can also provide captions that are easy to understand when the user is in a hurry. This allows for more appropriate captions to be provided by adjusting the customization content based on the user's current usage status. Some or all of the above-described processing in the customization unit can be performed using a generation AI. For example, the customization unit can input the user's current usage status data into the generation AI and cause the generation AI to adjust the customization content.

[0069] The customization unit can select the optimal customization method by taking into account the user's device information when customizing captions. For example, the customization unit selects the optimal customization method by taking into account the user's device information when customizing captions. Device information includes, but is not limited to, the device type and OS version. For example, if the user is using a smartphone, the customization unit can provide captions tailored to the screen size. Furthermore, if the user is using a tablet, the customization unit can provide captions optimized for a large screen. Furthermore, if the user is using a smartwatch, the customization unit can provide concise, highly visible captions. This allows for more appropriate captions to be provided by selecting the optimal customization method by taking into account the user's device information. Some or all of the above-described processing in the customization unit is performed using a generation AI. For example, the customization unit can input the user's device information data into the generation AI and cause the generation AI to select a customization method.

[0070] The customization unit can make the customized content multilingual in accordance with the user's language setting when customizing captions. For example, the customization unit can make the customized content multilingual in accordance with the user's language setting when customizing captions. Language settings include, but are not limited to, user configuration information and browser language settings. For example, the customization unit can automatically set the caption language based on the language setting of the user's device. The customization unit can also provide a language switching function when the user uses multiple languages. The customization unit can also provide captions in a specific language when the user selects that language. This allows for more appropriate captions to be provided by making the customized content multilingual in accordance with the user's language setting. Some or all of the above-described processing in the customization unit can be performed using a generation AI. For example, the customization unit can input the user's language setting data into the generation AI and cause the generation AI to execute the multilingual customized content.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The acquisition unit monitors the remaining battery level of the user's device and can temporarily stop acquiring image data if the battery is low. For example, the acquisition unit can stop acquiring image data if the smartphone battery drops below 20% and resume acquiring image data after the battery recovers. The acquisition unit can also prioritize acquiring low-resolution image data if the battery level is low. This allows image data to be acquired efficiently, taking into account the remaining battery level of the user's device.

[0073] When analyzing image data, the analysis unit can adjust the level of detail of the analysis taking into account the user's internet connection speed. For example, the analysis unit performs a simple analysis when the internet connection speed is slow, and a detailed analysis when the connection speed is fast. The analysis unit can also temporarily save the analysis results when the connection speed is unstable and resume the detailed analysis after the connection stabilizes. This allows image data to be analyzed efficiently according to the user's internet connection speed.

[0074] When generating captions, the generator can adjust the content of the captions by referring to the user's past search history. For example, the generator can include relevant information in the caption based on keywords the user has searched for in the past. The generator can also generate similar captions based on the characteristics of captions that the user has previously rated highly. This allows the generator to generate more relevant captions by referring to the user's past search history.

[0075] The providing unit can adjust the providing method when providing captions, taking into account the user's current activity status. For example, the providing unit can provide captions by voice when the user is driving, and by text when the user is in a quiet environment. The providing unit can also provide concise captions when the user is in a meeting, and detailed captions when the user is relaxed. This makes it possible to provide captions in an optimal manner depending on the user's current activity status.

[0076] When collecting user feedback, the collection unit can select the optimal collection method depending on the type of device used by the user. For example, the collection unit may provide a user using a smartphone with an interface that allows the user to easily provide feedback using touch operations, and a user using a desktop PC with an interface that allows the user to provide detailed feedback using keyboard input. The collection unit may also provide a user using a smartwatch with an interface that allows the user to provide concise feedback. This makes it possible to collect feedback in the optimal way depending on the type of device used by the user.

[0077] The processing flow of the first embodiment will be briefly explained below.

[0078] Step 1: The acquisition unit acquires image data. The image data may be in formats such as, but not limited to, JPEG, PNG, and GIF. The acquisition unit may acquire images automatically, for example, when a user uploads an image or when an image is available on the Internet. Step 2: The analysis unit analyzes the image data acquired by the acquisition unit. The analysis is performed based on, for example, an image recognition algorithm or a feature extraction method, but is not limited to these examples. For example, the analysis unit extracts features such as color, shape, and texture of the image. Step 3: The generator generates a caption based on the data analyzed by the analyzer. The caption is generated based on, for example, but not limited to, the length of the sentence and the level of detail of the information. For example, the generator uses a generation AI to generate a caption that describes the content of the image. Step 4: The providing unit provides the captions generated by the generating unit. Examples of providing include, but are not limited to, reading the captions aloud through a screen reader or displaying them in text format. For example, the providing unit transmits the generated captions to a user's device and reads them aloud.

[0079] (Example 2) An automatic captioning system according to an embodiment of the present invention enables visually impaired people to identify the nature of images posted on the Internet or social networking sites using their PCs or smartphones. When a user browses images on the Internet or social networking sites, the automatic captioning system sends the image data to a generation AI, which analyzes the image data, understands its content, and generates a caption. The generated caption is then sent to the user's screen reader and read aloud. For example, for a landscape image, the automatic captioning system generates a caption such as "blue sky and green field." The generation AI continuously learns and can improve the accuracy of the captions. For example, it can generate captions tailored to specific user preferences. Furthermore, the automatic captioning system is usable not only by visually impaired people but also by general users who want to quickly understand the content of images. For example, when a large number of images are posted on a news site, the generation AI can automatically add captions, allowing users to quickly understand the content of the images. This makes the automatic captioning system a useful tool for supporting visually impaired people's use of the Internet and social networking sites and quickly understanding the content of images. For example, visually impaired people will be able to understand the content of images, making it easier to use the internet and social networking sites. General users will also be able to quickly understand the content of images, making it more efficient to gather information from news sites and other sources.

[0080] An automatic captioning system according to an embodiment includes an acquisition unit, an analysis unit, a generation unit, and a provision unit. The acquisition unit acquires image data. The image data may be in formats such as, but not limited to, JPEG, PNG, and GIF. The acquisition unit may automatically acquire images from the Internet or from a user uploading an image. The analysis unit analyzes the image data acquired by the acquisition unit. The analysis may be performed based on, but not limited to, an image recognition algorithm or a feature extraction method. For example, the analysis unit extracts features such as the color, shape, and texture of the image. The generation unit generates captions based on the data analyzed by the analysis unit. The captions may be generated based on, but not limited to, the length of the sentence and the level of detail of the information. For example, the generation unit uses a generation AI to generate captions that describe the content of the image. The provision unit provides the captions generated by the generation unit. The provision may be performed by, but not limited to, reading the captions aloud using a screen reader or displaying them in text format. For example, the providing unit transmits the generated caption to a user's device and reads it aloud. This allows the automatic captioning system according to the embodiment to enable visually impaired people to understand the content of an image. Some or all of the above-described processing in the generating unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generating unit may input data analyzed by the analyzing unit into the generating AI and cause the generating AI to generate a caption.

[0081] The automatic captioning system includes a collection unit that collects user feedback. The collection unit collects user feedback. Examples of the feedback include, but are not limited to, questionnaires and user reviews. For example, the collection unit provides an interface for users to rate captions. The collection unit can also build a system that automatically collects user feedback. For example, the collection unit collects user opinions regarding the quality of captions and uses the collected opinions to improve the system. This allows the collected user feedback to be used to improve the system. Some or all of the above-described processing in the collection unit may be performed using, or without, a generation AI. For example, the collection unit may input user feedback data into the generation AI and cause the generation AI to analyze the feedback.

[0082] The automatic captioning system includes a learning unit that causes the generation AI to learn based on collected feedback. The learning unit causes the generation AI to learn based on the collected feedback. The generation AI may perform learning using, for example, but not limited to, technologies such as neural networks and deep learning. For example, the learning unit may analyze user feedback data and use it as learning data for the generation AI. The learning unit may also construct a system for the generation AI to continuously learn. For example, the learning unit may periodically collect feedback data and update the learning data for the generation AI. This allows the generation AI to continuously learn and improve the accuracy of captions. Some or all of the above-described processing in the learning unit is performed using the generation AI. For example, the learning unit inputs collected feedback data into the generation AI, and the generation AI learns.

[0083] The automatic captioning system includes a customization unit that customizes captions to suit the user's preferences. The customization unit customizes captions to suit the user's preferences. Examples of customization include, but are not limited to, a user profile and past usage history. For example, the customization unit adjusts the content and format of captions based on the user's preferences. The customization unit can also build a system that customizes captions based on user feedback. For example, the customization unit generates similar captions based on the characteristics of captions that the user has previously rated highly. This makes it possible to provide captions that match the user's preferences. Some or all of the above-described processing in the customization unit is performed using a generation AI. For example, the customization unit inputs user profile data into the generation AI, which then customizes the captions.

[0084] The acquisition unit can automatically acquire images when a user uploads an image or on the Internet. For example, when a user uploads an image, the acquisition unit acquires image data. The acquisition unit can also automatically acquire images on the Internet. For example, the acquisition unit acquires image data using a specific website or API. This makes it possible to automatically acquire images uploaded by a user or images on the Internet. Some or all of the above-mentioned processing in the acquisition unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the acquisition unit can input image data on the Internet into the generation AI and cause the generation AI to acquire the image data.

[0085] The generation unit can extract image features and generate a caption based on the extracted features. The generation unit, for example, extracts image features and generates a caption based on the extracted features. Features include, but are not limited to, color, shape, and texture. For example, the generation unit can analyze the color and shape of an image and generate a caption based on the extracted features. The generation unit can also analyze the texture of an image and generate a caption based on the extracted features. This allows for more accurate captions to be provided by extracting image features and generating captions. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image feature data into the generation AI and cause the generation AI to generate a caption.

[0086] The acquisition unit can estimate the user's emotion and adjust the timing of image data acquisition based on the estimated user's emotion. The acquisition unit, for example, estimates the user's emotion and adjusts the timing of image data acquisition based on the estimated user's emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, if the user is relaxed, the acquisition unit can instantly acquire image data to provide a smooth experience. Furthermore, if the user is feeling stressed, the acquisition unit can slightly delay image data acquisition to reduce the user's burden. Furthermore, if the user is in a hurry, the acquisition unit can quickly acquire image data and provide captions immediately. This allows the image to be acquired at a more appropriate time by adjusting the timing of image data acquisition according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the acquisition unit is performed using the generation AI. For example, the acquisition unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0087] The acquisition unit can analyze the user's past image viewing history and select an appropriate acquisition method. The acquisition unit, for example, analyzes the user's past image viewing history and selects an appropriate acquisition method. Past image viewing history includes, but is not limited to, log data and click history. For example, the acquisition unit prioritizes acquiring similar images based on the types of images the user frequently viewed in the past. The acquisition unit can also analyze the user's past viewing history to determine the tendency of images viewed during a specific time period and select an optimal acquisition method. The acquisition unit can also prioritize acquiring similar images based on the characteristics of images that the user has previously rated highly. By selecting an optimal acquisition method based on the user's past viewing history, images that are useful to the user can be prioritized. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's past image viewing history data into the generation AI and cause the generation AI to select an optimal acquisition method.

[0088] The acquisition unit may perform filtering based on the user's current areas of interest when acquiring image data. For example, the acquisition unit may perform filtering based on the user's current areas of interest when acquiring image data. Areas of interest include, but are not limited to, survey results and past search history. For example, the acquisition unit may preferentially acquire images related to topics in which the user is currently interested. The acquisition unit may also filter and acquire related images based on keywords recently searched by the user. The acquisition unit may also preferentially acquire images posted on social media accounts that the user follows. By doing so, highly relevant images can be acquired by filtering images based on the user's areas of interest. Some or all of the above-described processing in the acquisition unit may be performed using a generation AI. For example, the acquisition unit may input the user's area of ​​interest data into the generation AI and cause the generation AI to perform filtering.

[0089] The acquisition unit can select an appropriate acquisition means according to the user's input method when acquiring image data. For example, the acquisition unit selects an appropriate acquisition means according to the user's input method when acquiring image data. Input methods include, but are not limited to, keyboard input, voice input, and touch input. For example, if the user uses voice input, the acquisition unit can acquire images based on a voice command. Also, if the user uses text input, the acquisition unit can acquire images based on an entered keyword. Also, if the user uploads an image, the acquisition unit can acquire images related to the uploaded image. This allows images to be acquired efficiently by selecting the optimal acquisition means according to the user's input method. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's input data to the generation AI and cause the generation AI to select the optimal acquisition means.

[0090] The acquisition unit can estimate the user's emotions and determine the priority of image data to be acquired based on the estimated user emotions. The acquisition unit, for example, estimates the user's emotions and determines the priority of image data to be acquired based on the estimated user emotions. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, when the user is relaxed, the acquisition unit prioritizes acquiring interesting images. Furthermore, when the user is stressed, the acquisition unit can prioritize acquiring relaxing images. Furthermore, when the user is in a hurry, the acquisition unit can prioritize acquiring images containing important information. In this way, by determining the priority of image data according to the user's emotions, more appropriate images can be acquired preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the acquisition unit is performed using the generation AI. For example, the acquisition unit can input the user's emotion data into the generation AI and cause the generation AI to determine the priority based on emotions.

[0091] The acquisition unit can prioritize acquisition of highly relevant images based on the user's geographical location information when acquiring image data. For example, when acquiring image data, the acquisition unit prioritizes acquisition of highly relevant images based on the user's geographical location information. Geographical location information includes, but is not limited to, GPS data and IP address. For example, when the user is in a specific area, the acquisition unit prioritizes acquisition of images related to that area. Furthermore, when the user is traveling, the acquisition unit can prioritize acquisition of images of tourist spots related to the travel destination. Furthermore, when the user is at home, the acquisition unit can prioritize acquisition of images related to events and news around the user's home. This allows for acquisition of highly relevant images taking into account the user's geographical location information, thereby providing useful information to the user. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's geographical location information data into the generation AI and cause the generation AI to acquire highly relevant images.

[0092] The acquisition unit can analyze the user's social media activity and acquire related images when acquiring image data. For example, the acquisition unit can analyze the user's social media activity and acquire related images when acquiring image data. Social media activity includes, but is not limited to, the content of posts and the number of likes. For example, the acquisition unit can prioritize acquiring images posted by accounts the user follows on social media. The acquisition unit can also analyze the content of the user's social media posts and acquire related images. The acquisition unit can also acquire related images by referring to the activities of the user's friends on social media. In this way, by analyzing the user's social media activity and acquiring related images, it is possible to provide useful information to the user. Some or all of the above-mentioned processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's social media activity data into the generation AI and cause the generation AI to acquire related images.

[0093] The acquisition unit can customize the acquisition method by reflecting the user's past feedback when acquiring image data. For example, the acquisition unit customizes the acquisition method by reflecting the user's past feedback when acquiring image data. Past feedback includes, but is not limited to, survey results and user reviews. For example, the acquisition unit preferentially acquires similar images based on the characteristics of images that the user has previously rated highly. The acquisition unit can also select images to acquire while avoiding the characteristics of images that the user has previously rated poorly. The acquisition unit can also analyze the user's past feedback and customize the optimal acquisition method. By customizing the acquisition method by reflecting the user's past feedback, more appropriate images can be acquired. Some or all of the above-described processing in the acquisition unit can be performed using a generation AI. For example, the acquisition unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the acquisition method.

[0094] The analysis unit can estimate the user's emotion and adjust the image analysis method based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts the image analysis method based on the estimated user emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, if the user is relaxed, the analysis unit can perform a detailed analysis to provide more information. Furthermore, if the user is stressed, the analysis unit can perform a concise analysis to provide the minimum necessary information. Furthermore, if the user is in a hurry, the analysis unit can perform a quick analysis to provide immediate results. This allows for more appropriate analysis results to be provided by adjusting the image analysis method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit is performed using the generation AI. For example, the analysis unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the analysis method based on the emotion.

[0095] The analysis unit can adjust the level of detail of the analysis based on the importance of the image during image analysis. For example, the analysis unit adjusts the level of detail of the analysis based on the importance of the image during image analysis. The importance of an image includes, but is not limited to, the user's level of interest and the content of the image. For example, the analysis unit may perform a detailed analysis of an image containing important information, analyzing all elements. Alternatively, the analysis unit may perform a concise analysis of a general image, analyzing only key elements. Alternatively, the analysis unit may perform a particularly detailed analysis of an image in which the user is particularly interested, providing related information. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the image. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit may input image importance data into the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0096] The analysis unit can apply different analysis algorithms depending on the image category during image analysis. For example, the analysis unit applies different analysis algorithms depending on the image category during image analysis. Image categories include, but are not limited to, landscapes, people, and animals. For example, the analysis unit applies an algorithm that analyzes natural elements in the case of landscape images. The analysis unit can also apply a face recognition algorithm in the case of portrait images. The analysis unit can also apply an algorithm that analyzes product information in the case of product images. This improves the accuracy of analysis by applying an appropriate analysis algorithm depending on the image category. Some or all of the above-mentioned processing in the analysis unit is performed using a generation AI. For example, the analysis unit can input image category data into the generation AI and cause the generation AI to apply the analysis algorithm.

[0097] The analysis unit can improve the accuracy of the image analysis by referring to the user's past analysis results. For example, the analysis unit can improve the accuracy of the image analysis by referring to the user's past analysis results. Past analysis results include, but are not limited to, log data and analysis reports. For example, the analysis unit performs a similar analysis based on analysis results that the user previously rated highly. The analysis unit can also adjust the analysis method by avoiding analysis results that the user previously rated poorly. The analysis unit can also analyze the user's past analysis results and select the optimal analysis method. By referring to the user's past analysis results, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input the user's past analysis result data into the generation AI and cause the generation AI to improve the accuracy of the analysis.

[0098] The analysis unit can estimate the user's emotion and adjust the display method of the analysis results based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts the display method of the analysis results based on the estimated user emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the analysis unit displays detailed analysis results when the user is relaxed. The analysis unit can also display concise analysis results when the user is stressed. The analysis unit can also quickly display analysis results when the user is in a hurry. This enables more appropriate display by adjusting the display method of the analysis results according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the analysis unit is performed using the generation AI. For example, the analysis unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the display method based on the emotion.

[0099] The analysis unit can determine the analysis priority based on the time of image submission during image analysis. For example, the analysis unit determines the analysis priority based on the time of image submission during image analysis. The submission time includes, but is not limited to, a timestamp or a submission date and time. For example, the analysis unit prioritizes analyzing the most recent image. The analysis unit can also prioritize analyzing images submitted by a user during a specific time period. The analysis unit can also determine the analysis priority by referring to images submitted by the user in the past. This allows for efficient analysis by determining the analysis priority based on the time of image submission. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input image submission time data into the generation AI and have the generation AI determine the priority.

[0100] The analysis unit can adjust the analysis order based on the relevance of the images during image analysis. For example, the analysis unit adjusts the analysis order based on the relevance of the images during image analysis. Image relevance includes, but is not limited to, common tags and similarity scores. For example, the analysis unit prioritizes analyzing images related to topics in which the user is interested. The analysis unit can also prioritize analyzing images related to images that the user has previously rated highly. The analysis unit can also prioritize analyzing highly relevant images based on the user's current search history. This allows for efficient analysis by adjusting the analysis order based on the relevance of the images. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input image relevance data into the generation AI and cause the generation AI to adjust the analysis order.

[0101] The analysis unit can adjust the use of technical terms during image analysis according to the user's level of expertise. For example, the analysis unit can adjust the use of technical terms during image analysis according to the user's level of expertise. Examples of technical terms include, but are not limited to, survey results and past usage history. For example, if the user is an expert, the analysis unit can display the analysis results using detailed technical terms. If the user is a general user, the analysis unit can also display the analysis results using concise and easy-to-understand terms. The analysis unit can also select optimal terms based on feedback from the user's past analysis results. This allows for more appropriate analysis results by adjusting the use of technical terms during analysis according to the user's level of expertise. Some or all of the above-described processing in the analysis unit can be performed using a generation AI. For example, the analysis unit can input the user's level of expertise data into the generation AI and have the generation AI adjust the use of technical terms.

[0102] The generation unit can estimate the user's emotion and adjust the caption expression method based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the caption expression method based on the estimated user's emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the generation unit can generate a detailed and emotive caption when the user is relaxed. The generation unit can also generate a concise and to-the-point caption when the user is stressed. The generation unit can also generate a caption that is quickly understandable when the user is in a hurry. This allows for more appropriate captions to be provided by adjusting the caption expression method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the generation unit is performed using the generation AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the way the caption is expressed.

[0103] The generation unit can adjust the level of detail of the caption based on the importance of the image when generating the caption. For example, the generation unit adjusts the level of detail of the caption based on the importance of the image when generating the caption. The level of detail of the caption includes, but is not limited to, the comprehensiveness of the information and the length of the sentence. For example, the generation unit generates a detailed caption for an image containing important information. The generation unit can also generate a concise caption for a general image. The generation unit can also generate a particularly detailed caption for an image in which the user is particularly interested. This allows for efficient caption generation by adjusting the level of detail of the caption based on the importance of the image. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image importance data to the generation AI and cause the generation AI to adjust the level of detail of the caption.

[0104] The generation unit can apply different generation algorithms depending on the image category when generating captions. For example, the generation unit applies different generation algorithms depending on the image category when generating captions. Image categories include, but are not limited to, landscapes, people, and animals. For example, the generation unit generates a caption that emphasizes natural elements for a landscape image. For a portrait image, the generation unit can also generate a caption based on facial recognition. For a product image, the generation unit can also generate a caption that describes product information in detail. This improves the accuracy of the caption by applying an appropriate generation algorithm depending on the image category. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image category data into the generation AI and cause the generation AI to apply the generation algorithm.

[0105] The generation unit can improve the accuracy of caption generation by referring to the user's past caption results. For example, the generation unit can improve the accuracy of caption generation by referring to the user's past caption results. Past caption results include, but are not limited to, log data and user reviews. For example, the generation unit generates similar captions based on captions that the user has previously rated highly. The generation unit can also adjust the generation method to avoid captions that the user has previously rated poorly. The generation unit can also analyze the user's past caption results and select the optimal generation method. This improves the accuracy of captions by referring to the user's past caption results. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input the user's past caption result data into the generation AI and cause the generation AI to improve the accuracy of caption generation.

[0106] The generation unit can estimate the user's emotion and adjust the length of the caption based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion and adjusts the length of the caption based on the estimated user's emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the generation unit generates a detailed and longer caption when the user is relaxed. The generation unit can also generate a concise and shorter caption when the user is stressed. The generation unit can also generate a short caption that focuses on the main points when the user is in a hurry. This allows for more appropriate captions to be provided by adjusting the length of the caption according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit is performed using the generation AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the length of the caption.

[0107] The generation unit can determine the priority of captions based on the time of image submission when generating captions. For example, the generation unit determines the priority of captions based on the time of image submission when generating captions. The submission time includes, but is not limited to, a timestamp or a submission date and time. For example, the generation unit generates captions with priority for the most recent image. The generation unit can also generate captions with priority for images submitted by a user within a specific time period. The generation unit can also determine the priority of captions by referring to images previously submitted by the user. This allows for efficient caption generation by determining the priority of captions based on the time of image submission. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input image submission date data into the generation AI and have the generation AI determine the priority.

[0108] The generation unit can adjust the order of captions based on the relevance of the images when generating captions. For example, the generation unit adjusts the order of captions based on the relevance of the images when generating captions. Image relevance includes, but is not limited to, common tags and similarity scores. For example, the generation unit may prioritize generating captions for images related to topics in which the user is interested. The generation unit may also prioritize generating captions for images related to images that the user has previously rated highly. The generation unit may also prioritize generating captions for highly relevant images based on the user's current search history. This allows for efficient caption generation by adjusting the order of captions based on the relevance of the images. Some or all of the above-described processing in the generation unit may be performed using a generation AI. For example, the generation unit may input image relevance data to the generation AI and cause the generation AI to adjust the order of captions.

[0109] The generation unit can adjust the use of technical terms in captions according to the user's level of expertise when generating captions. For example, the generation unit can adjust the use of technical terms in captions according to the user's level of expertise when generating captions. Expertise levels include, but are not limited to, survey results and past usage history. For example, if the user is an expert, the generation unit can generate captions using detailed technical terms. If the user is a general user, the generation unit can also generate captions using concise and easy-to-understand terms. The generation unit can also select optimal terms based on feedback from the user's past caption results. This allows for more appropriate captions to be provided by adjusting the use of technical terms in captions according to the user's level of expertise. Some or all of the above-described processing in the generation unit can be performed using a generation AI. For example, the generation unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0110] The providing unit can estimate the user's emotion and adjust the caption provision method based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the caption provision method based on the estimated user's emotion. Emotion estimation includes, for example, facial expression recognition and voice analysis, but is not limited to these examples. For example, the providing unit can provide detailed captions by voice when the user is relaxed. Furthermore, the providing unit can provide concise captions by voice when the user is stressed. Furthermore, the providing unit can provide captions that focus on the main points by voice when the user is in a hurry. This allows for adjusting the caption provision method according to the user's emotion, thereby providing more appropriate captions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit is performed using the generation AI. For example, the providing unit can input the user's emotional data into the generating AI and cause the generating AI to adjust the providing method.

[0111] The providing unit can select the optimal caption delivery method by referring to the user's past usage history when providing captions. For example, the providing unit can select the optimal caption delivery method by referring to the user's past usage history when providing captions. Examples of past usage history include, but are not limited to, log data and user reviews. For example, if the user previously received captions in audio format, the providing unit can provide them in the same manner. Furthermore, if the user previously received captions in text format, the providing unit can also provide them in the same manner. Furthermore, the providing unit can analyze the user's past usage history and select the optimal caption delivery method. By selecting the optimal caption delivery method by referring to the user's past usage history, more appropriate captions can be provided. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input the user's past usage history data into the generation AI and have the generation AI select the delivery method.

[0112] The providing unit can customize the provided content according to the user's current task when providing captions. For example, the providing unit customizes the provided content according to the user's current task when providing captions. The current task includes, but is not limited to, an activity log or user input. For example, the providing unit can provide concise and to-the-point captions when the user is working. The providing unit can also provide detailed and emotive captions when the user is relaxed. The providing unit can also provide captions that are quickly understandable when the user is in a hurry. This allows for more appropriate captions to be provided by customizing the provided content according to the user's current task. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input the user's current task data into the generation AI and cause the generation AI to customize the provided content.

[0113] The providing unit can improve the caption providing method by reflecting user feedback when providing captions. For example, the providing unit improves the caption providing method by reflecting user feedback when providing captions. Feedback includes, but is not limited to, survey results and user reviews. For example, the providing unit provides captions in a similar manner based on a caption providing method that a user has previously rated highly. The providing unit can also improve the caption providing method by avoiding a caption providing method that a user has previously rated poorly. The providing unit can also analyze users' past feedback and select an optimal caption providing method. By improving the caption providing method by reflecting user feedback, more appropriate captions can be provided. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input user feedback data into the generation AI and cause the generation AI to improve the caption providing method.

[0114] The providing unit can estimate the user's emotion and adjust the timing of providing captions based on the estimated user's emotion. The providing unit, for example, estimates the user's emotion and adjusts the timing of providing captions based on the estimated user's emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the providing unit can provide captions immediately if the user is relaxed. Furthermore, the providing unit can provide captions with a slight delay if the user is stressed. Furthermore, the providing unit can provide captions quickly if the user is in a hurry. This allows captions to be provided at a more appropriate time by adjusting the timing of providing captions according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit is performed using the generation AI. For example, the providing unit can input the user's emotional data into the generating AI and cause the generating AI to adjust the timing of providing the data.

[0115] The providing unit can select the optimal caption providing method by taking into consideration the user's device information when providing captions. For example, the providing unit selects the optimal caption providing method by taking into consideration the user's device information when providing captions. Device information includes, but is not limited to, the device type and OS version. For example, if the user is using a smartphone, the providing unit can provide captions tailored to the screen size. Furthermore, if the user is using a tablet, the providing unit can provide captions optimized for a large screen. Furthermore, if the user is using a smartwatch, the providing unit can provide concise, highly visible captions. This allows for more appropriate captions to be provided by selecting the optimal caption providing method by taking into consideration the user's device information. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input the user's device information data into the generation AI and have the generation AI select the caption providing method.

[0116] The providing unit can provide multilingual content in accordance with the user's language setting when providing captions. For example, the providing unit can provide multilingual content in accordance with the user's language setting when providing captions. Language settings include, but are not limited to, user configuration information and browser language settings. For example, the providing unit can automatically set the caption language based on the language setting of the user's device. The providing unit can also provide a language switching function when the user uses multiple languages. The providing unit can also provide captions in a specific language when the user selects that language. This allows for more appropriate captions to be provided by providing multilingual content in accordance with the user's language setting. Some or all of the above-described processing by the providing unit can be performed using a generation AI. For example, the providing unit can input the user's language setting data into the generation AI and cause the generation AI to execute multilingual content.

[0117] The providing unit can customize the caption providing method according to the degree of the user's visual impairment when providing captions. For example, the providing unit customizes the caption providing method according to the degree of the user's visual impairment when providing captions. The degree of visual impairment includes, but is not limited to, medical diagnosis results and self-reporting. For example, if the user is completely blind, the providing unit can provide captions by audio. Also, if the user has low vision, the providing unit can provide captions in a large font. The providing unit can also select the optimal caption providing method according to the user's degree of visual impairment. This allows for more appropriate captions to be provided by customizing the caption providing method according to the user's degree of visual impairment. Some or all of the above-described processing in the providing unit can be performed using a generation AI. For example, the providing unit can input data on the user's degree of visual impairment into the generation AI and cause the generation AI to customize the caption providing method.

[0118] The collection unit can estimate the user's emotions and adjust the feedback collection method based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and adjusts the feedback collection method based on the estimated user emotions. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the collection unit may request detailed feedback if the user is relaxed. The collection unit may also request brief feedback if the user is stressed. The collection unit may also collect feedback quickly if the user is in a hurry. This allows for more appropriate feedback to be collected by adjusting the feedback collection method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the collection unit is performed using the generation AI. For example, the collection unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the collection method.

[0119] The collection unit can select the optimal collection method by referring to the user's past feedback history when collecting feedback. For example, the collection unit selects the optimal collection method by referring to the user's past feedback history when collecting feedback. Past feedback history includes, but is not limited to, survey results and user reviews. For example, if the user has provided detailed feedback in the past, the collection unit collects it in a similar manner. Furthermore, if the user has provided brief feedback in the past, the collection unit can collect it in a similar manner. Furthermore, the collection unit can analyze the user's past feedback history and select the optimal collection method. In this way, by selecting the optimal collection method by referring to the user's past feedback history, more appropriate feedback can be collected. Some or all of the above-described processing in the collection unit can be performed using a generation AI. For example, the collection unit can input the user's past feedback history data into the generation AI and cause the generation AI to select the collection method.

[0120] The collection unit can customize the collected content based on the user's current usage status when collecting feedback. For example, the collection unit customizes the collected content based on the user's current usage status when collecting feedback. The current usage status includes, but is not limited to, an activity log and user input. For example, the collection unit may request brief and to-the-point feedback when the user is working. The collection unit may also request detailed feedback when the user is relaxed. The collection unit may also collect quick feedback when the user is in a hurry. This allows for more appropriate feedback to be collected by customizing the collected content based on the user's current usage status. Some or all of the above-described processing in the collection unit is performed using a generation AI. For example, the collection unit may input the user's current usage status data into the generation AI and cause the generation AI to customize the collected content.

[0121] The collection unit can estimate the user's emotions and adjust the timing of feedback collection based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and adjusts the timing of feedback collection based on the estimated user emotions. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the collection unit collects feedback immediately when the user is relaxed. The collection unit can also collect feedback with a slight delay when the user is stressed. The collection unit can also collect feedback quickly when the user is in a hurry. This allows feedback to be collected at a more appropriate time by adjusting the timing of feedback collection according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the collection unit is performed using the generation AI. For example, the collection unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the collection timing.

[0122] The collection unit can select the optimal collection method by taking into account the user's device information when collecting feedback. For example, the collection unit selects the optimal collection method by taking into account the user's device information when collecting feedback. Device information includes, but is not limited to, the device type and OS version. For example, if the user is using a smartphone, the collection unit can provide a feedback collection method tailored to the screen size. Furthermore, if the user is using a tablet, the collection unit can provide a feedback collection method optimized for a large screen. Furthermore, if the user is using a smartwatch, the collection unit can provide a feedback collection method that is concise and highly visible. This allows for more appropriate feedback to be collected by selecting the optimal collection method by taking into account the user's device information. Some or all of the above-described processing in the collection unit is performed using a generation AI. For example, the collection unit can input the user's device information data into the generation AI and cause the generation AI to select a collection method.

[0123] The collection unit can make the collected content multilingual in accordance with the user's language setting when collecting feedback. For example, the collection unit can make the collected content multilingual in accordance with the user's language setting when collecting feedback. Language settings include, but are not limited to, user settings information and browser language settings. For example, the collection unit can automatically set the language for collecting feedback based on the language setting of the user's device. The collection unit can also provide a language switching function when the user uses multiple languages. If the user selects a specific language, the collection unit can also collect feedback in that language. This allows for more appropriate feedback to be collected by making the collected content multilingual in accordance with the user's language setting. Some or all of the above-described processing by the collection unit can be performed using a generation AI. For example, the collection unit can input the user's language setting data into the generation AI and cause the generation AI to execute the multilingual collected content.

[0124] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. The learning unit, for example, estimates the user's emotions and selects training data based on the estimated user emotions. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the learning unit selects detailed training data when the user is relaxed. The learning unit can also select concise training data when the user is stressed. The learning unit can also select data that can be quickly learned when the user is in a hurry. This allows for the selection of training data based on the user's emotions, enabling learning to be performed using more appropriate data. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the learning unit is performed using the generation AI. For example, the learning unit can input the user's emotion data into the generation AI and cause the generation AI to select training data.

[0125] The learning unit can optimize the learning algorithm by referring to past learning data during learning. For example, the learning unit optimizes the learning algorithm by referring to past learning data during learning. Past learning data includes, but is not limited to, log data and learning reports. For example, the learning unit selects an optimal learning algorithm based on the past learning data. The learning unit can also analyze the past learning data and adjust parameters of the learning algorithm. The learning unit can also improve the accuracy of the learning algorithm by referring to the past learning data. In this way, optimizing the learning algorithm by referring to the past learning data improves the accuracy of learning. Some or all of the above-mentioned processing in the learning unit can be performed using a generation AI. For example, the learning unit can input past learning data into the generation AI and cause the generation AI to optimize the learning algorithm.

[0126] The learning unit can update the learning data to reflect user feedback during learning. For example, the learning unit updates the learning data to reflect user feedback during learning. Feedback includes, but is not limited to, survey results and user reviews. For example, the learning unit updates the learning data based on feedback provided by the user. The learning unit can also analyze user feedback to improve the accuracy of the learning data. The learning unit can also optimize the learning algorithm by reflecting user feedback. In this way, updating the learning data to reflect user feedback improves the accuracy of learning. Some or all of the above-mentioned processing in the learning unit can be performed using a generation AI. For example, the learning unit can input user feedback data into the generation AI and cause the generation AI to update the learning data.

[0127] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. The learning unit, for example, estimates the user's emotions and adjusts the frequency of learning based on the estimated user emotions. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the learning unit may perform learning more frequently when the user is relaxed. The learning unit may also reduce the frequency of learning when the user is stressed. The learning unit may also perform learning more quickly when the user is in a hurry. This allows learning to be performed at a more appropriate time by adjusting the frequency of learning according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the learning unit is performed using the generation AI. For example, the learning unit may input the user's emotion data into the generation AI and cause the generation AI to adjust the learning frequency.

[0128] The learning unit can weight the learning data based on the time of submission of the image data during learning. For example, the learning unit weights the learning data based on the time of submission of the image data during learning. The submission time includes, but is not limited to, a timestamp or a submission date and time. For example, the learning unit weights the most recent image data to improve the accuracy of learning. The learning unit can also weight image data submitted by the user during a specific time period. The learning unit can also weight the learning data by referring to image data submitted by the user in the past. In this way, weighting the learning data based on the time of submission of the image data improves the accuracy of learning. Some or all of the above-described processing in the learning unit can be performed using a generation AI. For example, the learning unit can input data on the time of submission of the image data to the generation AI and cause the generation AI to perform weighting.

[0129] The learning unit can integrate information from different data sources to enrich the training data during learning. For example, the learning unit integrates information from different data sources to enrich the training data during learning. Data sources include, but are not limited to, web data and sensor data. For example, the learning unit integrates image data from different social media platforms to learn. The learning unit can also integrate image data from news sites and blogs to learn. The learning unit can also integrate image data uploaded by users to learn. In this way, the accuracy of learning is improved by integrating information from different data sources to enrich the training data. Some or all of the above-described processing in the learning unit is performed using a generative AI. For example, the learning unit can input information from different data sources into the generative AI and have the generative AI perform the integration.

[0130] The customization unit can estimate the user's emotion and adjust the caption customization method based on the estimated user's emotion. The customization unit, for example, estimates the user's emotion and adjusts the caption customization method based on the estimated user's emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the customization unit can provide detailed and emotive captions when the user is relaxed. The customization unit can also provide concise and to-the-point captions when the user is stressed. The customization unit can also provide captions that are quickly understandable when the user is in a hurry. This allows for more appropriate captions to be provided by adjusting the caption customization method according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the customization unit is performed using the generation AI. For example, the customization unit can input user emotion data into the generation AI and cause the generation AI to adjust the customization method.

[0131] The customization unit can select the optimal customization method by referring to the user's past customization history when customizing captions. For example, the customization unit can select the optimal customization method by referring to the user's past customization history when customizing captions. Past customization history includes, but is not limited to, log data and user reviews. For example, if the user previously preferred detailed captions, the customization unit can customize them in a similar manner. Furthermore, if the user previously preferred concise captions, the customization unit can also customize them in a similar manner. The customization unit can also analyze the user's past customization history and select the optimal customization method. By selecting the optimal customization method by referring to the user's past customization history, more appropriate captions can be provided. Some or all of the above-described processing in the customization unit can be performed using a generation AI. For example, the customization unit can input the user's past customization history data into the generation AI and have the generation AI select a customization method.

[0132] The customization unit can adjust the customization content based on the user's current usage status when customizing captions. For example, the customization unit adjusts the customization content based on the user's current usage status when customizing captions. Current usage status includes, but is not limited to, activity logs and user input. For example, the customization unit can provide concise and to-the-point captions when the user is working. The customization unit can also provide detailed and emotive captions when the user is relaxed. The customization unit can also provide captions that are easy to understand when the user is in a hurry. This allows for more appropriate captions to be provided by adjusting the customization content based on the user's current usage status. Some or all of the above-described processing in the customization unit can be performed using a generation AI. For example, the customization unit can input the user's current usage status data into the generation AI and cause the generation AI to adjust the customization content.

[0133] The customization unit can estimate a user's emotion and determine a caption customization priority based on the estimated user's emotion. The customization unit, for example, estimates a user's emotion and determines a caption customization priority based on the estimated user's emotion. Emotion estimation includes, but is not limited to, facial expression recognition and voice analysis. For example, the customization unit can prioritize providing detailed captions when the user is relaxed. The customization unit can also prioritize providing concise captions when the user is stressed. The customization unit can also prioritize providing captions that are easy to understand when the user is in a hurry. This allows for more appropriate captions to be provided by determining the caption customization priority based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the customization unit is performed using the generation AI. For example, the customization unit can input user emotion data into the generation AI and have the generation AI determine the customization priority.

[0134] The customization unit can select the optimal customization method by taking into account the user's device information when customizing captions. For example, the customization unit selects the optimal customization method by taking into account the user's device information when customizing captions. Device information includes, but is not limited to, the device type and OS version. For example, if the user is using a smartphone, the customization unit can provide captions tailored to the screen size. Furthermore, if the user is using a tablet, the customization unit can provide captions optimized for a large screen. Furthermore, if the user is using a smartwatch, the customization unit can provide concise, highly visible captions. This allows for more appropriate captions to be provided by selecting the optimal customization method by taking into account the user's device information. Some or all of the above-described processing in the customization unit is performed using a generation AI. For example, the customization unit can input the user's device information data into the generation AI and cause the generation AI to select a customization method.

[0135] The customization unit can make the customized content multilingual in accordance with the user's language setting when customizing captions. For example, the customization unit can make the customized content multilingual in accordance with the user's language setting when customizing captions. Language settings include, but are not limited to, user configuration information and browser language settings. For example, the customization unit can automatically set the caption language based on the language setting of the user's device. The customization unit can also provide a language switching function when the user uses multiple languages. The customization unit can also provide captions in a specific language when the user selects that language. This allows for more appropriate captions to be provided by making the customized content multilingual in accordance with the user's language setting. Some or all of the above-described processing in the customization unit can be performed using a generation AI. For example, the customization unit can input the user's language setting data into the generation AI and cause the generation AI to execute the multilingual customized content. === Hard Collateral 1-1 === Each of the multiple elements, including the acquisition unit, analysis unit, generation unit, provision unit, collection unit, learning unit, and customization unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit acquires image data using the camera 42 or communication I / F 44 of the smart device 14, and the image data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates captions based on the analyzed data. The provision unit is realized by the control unit 46A of the smart device 14 and transmits the generated captions to the user's device and reads them aloud. The collection unit is realized by the control unit 46A of the smart device 14 and collects user feedback. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI learns based on the collected feedback. The customization unit is realized by the specific processing unit 290 of the data processing device 12, and customizes the captions to suit the user's preferences. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned acquisition unit, analysis unit, generation unit, provision unit, collection unit, learning unit, and customization unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit acquires image data using the camera 42 and communication I / F 44 of the smart glasses 214, and the image data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates captions based on the analyzed data. The provision unit is realized by the control unit 46A of the smart glasses 214 and transmits the generated captions to the user's device and reads them aloud. The collection unit is realized by the control unit 46A of the smart glasses 214 and collects user feedback. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI learns based on the collected feedback. The customization unit is realized by the specific processing unit 290 of the data processing device 12, and customizes the captions to suit the user's preferences. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned acquisition unit, analysis unit, generation unit, provision unit, collection unit, learning unit, and customization unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the acquisition unit acquires image data using the camera 42 and communication I / F 44 of the headset-type terminal 314, and the image data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates captions based on the analyzed data. The provision unit is realized by the control unit 46A of the headset-type terminal 314 and transmits the generated captions to the user's device and reads them aloud. The collection unit is realized by the control unit 46A of the headset-type terminal 314 and collects user feedback. The learning unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI learns based on the collected feedback. The customization unit is realized by the specific processing unit 290 of the data processing device 12, and customizes the captions to suit the user's preferences. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned acquisition unit, analysis unit, generation unit, provision unit, collection unit, learning unit, and customization unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the acquisition unit acquires image data using the camera 42 and communication I / F 44 of the robot 414, and the image data is analyzed by the specific processing unit 290 of the data processing device 12. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates captions based on the analyzed data. The provision unit is realized by the control unit 46A of the robot 414 and transmits the generated captions to the user's device and reads them aloud. The collection unit is realized by the control unit 46A of the robot 414 and collects user feedback. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and the generation AI learns based on the collected feedback. The customization unit is realized by the specific processing unit 290 of the data processing device 12, and customizes the captions to suit the user's preferences.

[0136] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0137] The acquisition unit monitors the remaining battery level of the user's device and can temporarily stop acquiring image data if the battery is low. For example, the acquisition unit can stop acquiring image data if the smartphone battery drops below 20% and resume acquiring image data after the battery recovers. The acquisition unit can also prioritize acquiring low-resolution image data if the battery level is low. This allows image data to be acquired efficiently, taking into account the remaining battery level of the user's device.

[0138] When analyzing image data, the analysis unit can adjust the level of detail of the analysis taking into account the user's internet connection speed. For example, the analysis unit performs a simple analysis when the internet connection speed is slow, and a detailed analysis when the connection speed is fast. The analysis unit can also temporarily save the analysis results when the connection speed is unstable and resume the detailed analysis after the connection stabilizes. This allows image data to be analyzed efficiently according to the user's internet connection speed.

[0139] When generating captions, the generator can adjust the content of the captions by referring to the user's past search history. For example, the generator can include relevant information in the caption based on keywords the user has searched for in the past. The generator can also generate similar captions based on the characteristics of captions that the user has previously rated highly. This allows the generator to generate more relevant captions by referring to the user's past search history.

[0140] The providing unit can adjust the providing method when providing captions, taking into account the user's current activity status. For example, the providing unit can provide captions by voice when the user is driving, and by text when the user is in a quiet environment. The providing unit can also provide concise captions when the user is in a meeting, and detailed captions when the user is relaxed. This makes it possible to provide captions in an optimal manner depending on the user's current activity status.

[0141] When collecting user feedback, the collection unit can select the optimal collection method depending on the type of device used by the user. For example, the collection unit may provide a user using a smartphone with an interface that allows the user to easily provide feedback using touch operations, and a user using a desktop PC with an interface that allows the user to provide detailed feedback using keyboard input. The collection unit may also provide a user using a smartwatch with an interface that allows the user to provide concise feedback. This makes it possible to collect feedback in the optimal way depending on the type of device used by the user.

[0142] The acquisition unit can estimate the user's emotions and adjust the image data acquisition method based on the estimated user's emotions. For example, the acquisition unit can prioritize acquiring images with vivid colors when the user is excited, and prioritize acquiring images with calm colors when the user is calm. Furthermore, the acquisition unit can prioritize acquiring images containing encouraging messages when the user is sad. This makes it possible to acquire optimal image data according to the user's emotions.

[0143] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. For example, the analysis unit can display detailed analysis results when the user is relaxed, and display concise analysis results when the user is stressed. The analysis unit can also display the analysis results in a format that can be quickly understood when the user is in a hurry. This makes it possible to display the analysis results in an optimal manner depending on the user's emotions.

[0144] The generation unit can estimate the user's emotion and adjust the tone of the caption based on the estimated user's emotion. For example, the generation unit can generate a caption with a bright and positive tone when the user is happy, and generate a caption with an encouraging tone when the user is sad. The generation unit can also generate a caption with a calm and neutral tone when the user is angry. This makes it possible to provide captions with an optimal tone depending on the user's emotion.

[0145] The providing unit can estimate the user's emotions and adjust the timing of providing captions based on the estimated user's emotions. For example, the providing unit can provide captions immediately when the user is relaxed, and provide captions with a slight delay when the user is feeling stressed. The providing unit can also provide captions quickly when the user is in a hurry. This makes it possible to provide captions at the optimal timing according to the user's emotions.

[0146] The collection unit can estimate the user's emotions and adjust the feedback collection method based on the estimated user's emotions. For example, the collection unit requests detailed feedback when the user is relaxed, and requests brief feedback when the user is stressed. The collection unit can also collect feedback quickly when the user is in a hurry. This makes it possible to collect feedback in an optimal manner depending on the user's emotions.

[0147] The processing flow of the second embodiment will be briefly explained below.

[0148] Step 1: The acquisition unit acquires image data. The image data may be in formats such as, but not limited to, JPEG, PNG, and GIF. The acquisition unit may acquire images automatically, for example, when a user uploads an image or when an image is available on the Internet. Step 2: The analysis unit analyzes the image data acquired by the acquisition unit. The analysis is performed based on, for example, an image recognition algorithm or a feature extraction method, but is not limited to these examples. For example, the analysis unit extracts features such as color, shape, and texture of the image. Step 3: The generator generates a caption based on the data analyzed by the analyzer. The caption is generated based on, for example, but not limited to, the length of the sentence and the level of detail of the information. For example, the generator uses a generation AI to generate a caption that describes the content of the image. Step 4: The providing unit provides the captions generated by the generating unit. Examples of providing include, but are not limited to, reading the captions aloud through a screen reader or displaying them in text format. For example, the providing unit transmits the generated captions to a user's device and reads them aloud.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0185] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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."

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] [Explanation of symbols]

[0221] 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 acquisition unit that acquires image data; an analysis unit that analyzes the image data acquired by the acquisition unit; a generation unit that generates a caption based on the data analyzed by the analysis unit; a providing unit that provides the captions generated by the generating unit; Equipped with A system characterized by:

2. A collection unit for collecting user feedback is provided.

2. The system of claim 1.

3. Equipped with a learning unit that trains the generative AI based on collected feedback 2. The system of claim 1.

4. It has a customization section that allows users to customize captions to their liking.

2. The system of claim 1.

5. The acquisition unit When a user uploads an image or automatically retrieves an image from the internet 2. The system of claim 1.

6. The generation unit Extract image features and generate captions based on them 2. The system of claim 1.

7. The acquisition unit A method for estimating a user's emotion and adjusting the timing of acquiring image data based on the estimated user's emotion 2. The system of claim 1.

8. The acquisition unit Analyze the user's past image browsing history and select the appropriate acquisition method 2. The system of claim 1.

9. The acquisition unit When image data is acquired, it is filtered based on the user's current areas of interest.

2. The system of claim 1.

Images