System

Abstract

An object of a system according to an embodiment is to easily tag an image and construct an efficient image database.SOLUTION: A system includes a reception part, a proposal part, a storage part, and a retrieval part. The reception unit inputs a description of the image. The suggestion unit suggests a tag based on the description input by the reception unit. The storage unit stores the image to which the tag proposed by the proposal unit is assigned. The retrieval unit retrieves the image stored by the storage unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that tagging images is complicated and it is difficult to build an efficient image database.

[0005] The system according to the embodiment aims to easily tag images and build an efficient image database. [Means for solving the problem]

[0006] A system according to an embodiment includes a receiving unit, a suggestion unit, a storage unit, and a search unit. The receiving unit inputs a description of an image. The suggestion unit suggests tags based on the description input by the receiving unit. The storage unit stores images to which the tags suggested by the suggestion unit have been added. The search unit searches for images stored by the storage unit. [Effects of the Invention]

[0007] The system according to the embodiment can easily tag images and build an efficient image database. [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 image management system according to an embodiment of the present invention is a system that inputs image descriptions, proposes tags, stores them, and searches them. The image management system uses a generation AI to input image descriptions and request tag suggestions. An image database with the suggested tags is constructed, and a search system is realized using IT technology. For example, a user inputs an image description to the generation AI. For example, a description such as "a landscape with blue sky and white clouds" is input. This description is input to the generation AI. The generation AI then analyzes the input description and proposes appropriate tags. For example, tags such as "blue sky," "white clouds," and "landscape" are suggested. This allows users to easily tag images. An image database with the suggested tags is constructed. For example, tagged images are stored in a database, and a search system is constructed. This search system allows users to quickly search for the images they need. This makes it easier for teams and departments to reuse image materials, improving productivity. This allows the image management system to efficiently perform the series of processes of inputting image descriptions, proposing tags, storing them, and searching them. For example, when creating project materials, images used in the past can be easily searched and reused. In addition, tagging is easy, making image management more efficient. In the future, the company aims to provide a service that uses generative AI to generate image tags and build an image database using cloud technology, which will enable the provision of an even more advanced image management system.

[0029] An image management system according to an embodiment includes a reception unit, a suggestion unit, a storage unit, and a search unit. The reception unit inputs a description of an image. The image description may be in text format, audio format, or other formats, but is not limited to these examples. For example, a user may input a description in text format to the reception unit, such as "a landscape with blue sky and white clouds." The reception unit may also convert what the user dictates into text using voice input. For example, speech recognition technology may be used to convert speech to text. The suggestion unit uses a generation AI to suggest tags based on the description input by the reception unit. The generation AI may analyze the description using, for example, a text generation AI (e.g., a Transformer-based LLM) and suggest appropriate tags. For example, the generation AI may suggest tags such as "blue sky," "white clouds," and "landscape." The suggestion unit may also use the generation AI to improve the accuracy of tags based on the content of the description. For example, the generation AI may understand the context of the description and suggest more appropriate tags. The storage unit stores the images tagged with the tags suggested by the suggestion unit in a database. The database may include, for example, a relational database, a NoSQL database, or the like, but is not limited to these examples. The storage unit, for example, stores tagged images in a relational database. The storage unit can also store images in a NoSQL database. For example, the storage unit stores images including tag information in the NoSQL database. The search unit searches for images stored by the storage unit. The search unit, for example, searches for images using a search algorithm. For example, the search unit searches for images based on keywords entered by a user. The search unit can also display search results based on tag information of stored images. For example, the search unit searches for images based on tags such as "blue sky," "white clouds," and "landscape." This allows the image management system according to the embodiment to efficiently perform a series of processes: inputting a description of an image, proposing tags, saving, and searching. This allows the image management system to easily reuse image material across teams or departments, improving productivity.

[0030] The suggestion unit can analyze the input description using a generation AI and suggest tags. The generation AI can analyze the description using, for example, a text generation AI (e.g., a transformer-based LLM) and suggest appropriate tags. For example, the generation AI can suggest tags such as "blue sky," "white clouds," and "landscape." The generation AI can also improve the accuracy of tags based on the content of the description. For example, the generation AI can understand the context of the description and suggest more appropriate tags. In this way, the use of the generation AI improves the accuracy of tag suggestions. Some or all of the above-mentioned processing in the generation AI can be performed using, for example, AI, or can be performed without using AI. For example, the generation AI can suggest tags using an AI model that takes a description entered by a user as input and outputs tags.

[0031] The storage unit can store the tagged images in a database. Examples of databases include, but are not limited to, relational databases and NoSQL databases. For example, the storage unit stores the tagged images in a relational database. The storage unit can also store the images in a NoSQL database. For example, the storage unit stores images including tag information in a NoSQL database. This allows the tagged images to be stored efficiently. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can store the images using an AI model that takes the tagged images as input and stores them in a database.

[0032] The search unit can search for stored images. The search unit can search for images using, for example, a search algorithm. For example, the search unit can search for images based on keywords entered by a user. The search unit can also display search results based on tag information of stored images. For example, the search unit can search for images based on tags such as "blue sky," "white clouds," and "landscape." This allows for quick search of stored images. Some or all of the above-described processing in the search unit can be performed using, for example, AI, or can be performed without using AI. For example, the search unit can search for images using an AI model that inputs tag information and outputs search results.

[0033] The suggestion unit may include an accuracy improvement unit for improving the accuracy of the tag. The accuracy improvement unit may improve the accuracy of the tag using, for example, a feedback loop. For example, the accuracy improvement unit may collect feedback from users and improve the accuracy of the tag based on the feedback. The accuracy improvement unit may also optimize the algorithm. For example, the accuracy improvement unit may adjust parameters of a tag suggestion algorithm to improve the accuracy. This may improve the accuracy of the tag. Some or all of the above-described processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit may perform the accuracy improvement using an AI model that uses user feedback as input and improves the accuracy of the tag.

[0034] The search unit may include an efficiency improvement unit for improving the efficiency of the search system. The efficiency improvement unit improves the efficiency of the search system, for example, by using a cache function. For example, the efficiency improvement unit stores search results in a cache and retrieves the results from the cache the next time a search is performed. The efficiency improvement unit may also optimize an index. For example, the efficiency improvement unit optimizes a search index to improve search speed. This can improve the efficiency of the search system. Some or all of the above-described processing in the efficiency improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency improvement unit may improve search efficiency by using an AI model that inputs search results and outputs efficient search results.

[0035] The reception unit can provide an auto-completion function by referring to the user's past input history when entering an image description. For example, the reception unit automatically completes similar descriptions based on descriptions previously entered by the user. For example, the reception unit completes a similar description, such as "A beautiful landscape with blue skies and white clouds," based on the description previously entered by the user, such as "A landscape with blue skies and white clouds." The reception unit can also prioritize displaying keywords frequently used by the user to simplify input. For example, the reception unit prioritizes displaying keywords frequently used by the user, such as "blue skies" and "white clouds." The reception unit can also learn specific patterns from the user's past input history and suggest optimal completion candidates. For example, the reception unit analyzes the user's past input history and suggests optimal completion candidates. By referring to the past input history, input efficiency can be improved. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's past input history into a generation AI and cause the generation AI to suggest optimal completion candidates.

[0036] The reception unit can support multiple input methods, such as voice input and handwriting input, when inputting an image description. For example, when a user inputs an image description by voice, the reception unit converts it into text using voice recognition technology. For example, the reception unit automatically analyzes the voice using voice recognition software and saves it as text. The reception unit can also convert a user inputting an image description by handwriting into text using handwriting recognition technology. For example, the reception unit analyzes the handwritten characters using handwriting recognition software and saves them as text. The reception unit can also combine voice input and handwriting input to input image descriptions more intuitively. For example, the reception unit supports the user inputting a description by voice and inputting supplementary information by handwriting. This supports a variety of input methods, thereby improving user convenience. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input voice data or handwritten data into a generation AI and have the generation AI convert it into text data.

[0037] When inputting an image description, the reception unit can filter the input content based on the user's current project or task. For example, the reception unit can prioritize displaying keywords related to the user's current project. For example, the reception unit can work with a project management tool to automatically extract and display related keywords. The reception unit can also work with the user's task management tool to suggest input content based on related tasks. For example, the reception unit can acquire task information from the task management tool and suggest related keywords. The reception unit can also refer to the user's project history and suggest keywords related to past projects. For example, the reception unit can analyze past project history and suggest related keywords. By filtering the input content based on the current project or task, more relevant input can be made. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input data acquired from a project management tool or task management tool into a generation AI and cause the generation AI to suggest related keywords.

[0038] When an image description is input, the reception unit can prioritize displaying highly relevant descriptions based on the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes displaying keywords related to that area. For example, if the user is in a tourist spot, the reception unit prioritizes displaying keywords such as "sightseeing," "famous places," and "scenery." The reception unit can also suggest related image descriptions based on the user's current location. For example, the reception unit acquires GPS data and suggests keywords related to the current location. The reception unit can also refer to the user's past location information and prioritize displaying related keywords. For example, the reception unit analyzes past location information and suggests related keywords. This allows for providing more relevant descriptions by taking geographical location information into consideration. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input GPS data to a generation AI and cause the generation AI to suggest related keywords.

[0039] The reception unit can analyze the user's social media activity and suggest related descriptions when inputting an image description. For example, the reception unit can analyze the content posted by the user on social media and suggest related keywords. For example, if the user posts "travel" on social media, the reception unit can suggest keywords such as "sightseeing," "famous places," and "scenery." The reception unit can also refer to the user's social media activity history to suggest related image descriptions. For example, the reception unit can analyze the user's past posts and suggest related keywords. The reception unit can also analyze the activities of the user's friends and followers and suggest related keywords. For example, if the user's friend posts "travel," the reception unit can suggest keywords such as "sightseeing," "famous places," and "scenery." By analyzing social media activity, more relevant descriptions can be provided. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input social media posting data to a generation AI and cause the generation AI to suggest related keywords.

[0040] The reception unit can customize the input interface by reflecting the user's past feedback when inputting an image description. For example, the reception unit adjusts the interface design based on feedback provided by the user in the past. For example, if the user provides feedback that "a simple interface is preferable," the reception unit provides an interface with a simple design. The reception unit can also reflect the user's feedback and optimize the input procedure. For example, if the user provides feedback that "there are too many input steps," the reception unit simplifies the input procedure. The reception unit can also analyze the user's past feedback and suggest an optimal input method. For example, the reception unit can suggest an optimal input method based on the user's past feedback. This makes it possible to provide an input interface that is easier to use by reflecting the past feedback. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's feedback data to a generation AI and have the generation AI customize the interface.

[0041] When proposing tags, the suggestion unit can adjust the level of detail of the tags based on the content of the image. For example, if the image is complex, the suggestion unit can suggest detailed tags. For example, the suggestion unit can suggest detailed tags such as "mountain," "river," and "tree" for a landscape image. The suggestion unit can also suggest concise tags for a simple image. For example, the suggestion unit can suggest tags such as "background" and "simple" for a simple background image. The suggestion unit can also suggest tags with an appropriate level of detail depending on the content of the image. For example, the suggestion unit can analyze the content of the image and suggest tags with an appropriate level of detail. This makes it possible to suggest more appropriate tags by adjusting the level of detail of the tags based on the content of the image. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input image data to a generation AI and cause the generation AI to adjust the level of detail of the tags.

[0042] When proposing tags, the suggestion unit can apply different suggestion algorithms depending on the image category. For example, in the case of a landscape image, the suggestion unit applies an algorithm that suggests tags related to nature. For example, the suggestion unit proposes tags such as "mountain," "river," and "tree" for the landscape image. Furthermore, in the case of a portrait image, the suggestion unit can also apply an algorithm that suggests tags using facial recognition technology. For example, the suggestion unit proposes tags such as "face," "smile," and "portrait" for the portrait image. Furthermore, in the case of a product image, the suggestion unit can also apply an algorithm that suggests tags based on the product category. For example, the suggestion unit proposes tags such as "electronic device," "furniture," and "clothing" for the product image. Thus, by applying different suggestion algorithms depending on the image category, more appropriate tags can be proposed. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input image data to a generation AI and cause the generation AI to suggest tags according to the category.

[0043] When proposing tags, the suggestion unit can improve the accuracy of the suggestions by referring to the user's past tagging history. For example, the suggestion unit suggests similar tags based on tags previously added by the user. For example, the suggestion unit suggests tags such as "landscape" and "nature" for similar images to images previously tagged by the user with "landscape" and "nature." The suggestion unit can also analyze the user's tagging history and suggest optimal tags. For example, the suggestion unit can learn the user's past tagging patterns and suggest optimal tags. The suggestion unit can also improve the accuracy of the suggestions by referring to the user's past tagging history. For example, the suggestion unit analyzes the user's past tagging history and optimizes the suggestion algorithm. In this way, the accuracy of the suggestions can be improved by referring to the past tagging history. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the user's tagging history data into a generation AI and cause the generation AI to improve the accuracy of the suggestions.

[0044] When proposing tags, the suggestion unit can determine the priority of tags based on the time the image was taken. For example, if the image was taken recently, the suggestion unit prioritizes proposing the most recent tags. For example, the suggestion unit can suggest tags such as "latest," "fresh green," and "spring" for a recently taken landscape image. The suggestion unit can also prioritize proposing older tags for an older image. For example, the suggestion unit can suggest tags such as "historical," "old-fashioned," and "autumn" for an older landscape image. The suggestion unit can also prioritize proposing appropriate tags depending on the time the image was taken. For example, the suggestion unit can analyze the time the image was taken and suggest appropriate tags. Thus, by determining the priority of tags based on the time the image was taken, more appropriate tags can be suggested. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input image metadata into a generation AI and cause the generation AI to suggest tags based on the time the image was taken.

[0045] When suggesting tags, the suggestion unit can adjust the order of tags based on the relevance of the image. For example, if an image is related to a specific theme, the suggestion unit prioritizes suggesting tags related to that theme. For example, the suggestion unit prioritizes suggesting tags such as "nature," "scenery," and "outdoors" for a landscape image. Furthermore, if an image is related to multiple themes, the suggestion unit can also prioritize suggesting the most relevant tag. For example, the suggestion unit prioritizes suggesting the most relevant tag from among tags such as "nature," "scenery," and "outdoors" and "travel" and "tourism" for a landscape image. Furthermore, the suggestion unit can also adjust the order of appropriate tags based on the relevance of the image. For example, the suggestion unit analyzes the content of the image and prioritizes suggesting highly relevant tags. This allows more appropriate tags to be suggested by adjusting the order of tags based on the relevance of the image. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit may input image data to a generation AI and cause the generation AI to adjust the order of tags based on relevance.

[0046] When proposing tags, the suggestion unit can adjust the use of technical terms in the tags according to the user's level of expertise. For example, if the user is an expert, the suggestion unit can suggest tags containing technical terms. For example, the suggestion unit can suggest tags containing technical terms such as "geography," "ecosystem," and "vegetation" for a landscape image. Furthermore, if the user is a beginner, the suggestion unit can also suggest tags containing simple terms. For example, the suggestion unit can suggest tags containing simple terms such as "mountain," "river," and "tree" for a landscape image. Furthermore, the suggestion unit can also suggest appropriate tags according to the user's level of expertise. For example, the suggestion unit can analyze the user's level of expertise and suggest appropriate tags. This allows for the suggestion of more appropriate tags by adjusting the use of technical terms in the tags according to the user's level of expertise. Some or all of the above-described processing in the suggestion unit can be performed, for example, using AI or without AI. For example, the suggestion unit can input the user's level of expertise data into the generation AI and cause the generation AI to suggest tags that adjust the use of technical terms.

[0047] The storage unit can automatically generate and store image metadata when saving an image. The storage unit automatically generates and stores basic metadata, such as the date and time the image was taken and the location. For example, the storage unit generates information such as "October 1, 2023" and "Tokyo" as image metadata. The storage unit can also automatically generate and store detailed metadata based on the content of the image. For example, the storage unit analyzes the content of the image and generates metadata such as "blue sky," "white clouds," and "landscape." The storage unit can also automatically generate and store related metadata based on the tag information of the image. For example, the storage unit analyzes the tag information and generates metadata such as "nature" and "outdoors." This automatically generating image metadata can improve storage efficiency. Some or all of the above-described processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input image data to a generation AI and have the generation AI generate metadata.

[0048] The storage unit performs image version management when saving an image and can also store past versions. For example, when an image is updated, the storage unit automatically saves past versions. For example, the storage unit saves the "October 1, 2023" version of the image as version 1 and the "October 2, 2023" version as version 2. The storage unit can also manage the version history of the image and enable past versions to be restored as needed. For example, the storage unit displays the version history and allows a user to select and restore a past version. The storage unit can also perform image version management and enable tracking of change history. For example, the storage unit displays the change history of the image and allows a user to check which parts have been changed. In this way, by performing image version management, past versions can also be saved and restored as needed. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without AI. For example, the storage unit can input image data to a generation AI and have the generation AI perform version management.

[0049] The storage unit can automatically convert the image format when saving the image. For example, if an image is saved in a specific format, the storage unit automatically converts the image into another format as needed and saves it. For example, the storage unit converts a JPEG format image into a PNG format and saves it. The storage unit can also automatically convert the image format according to a user's requirements and save it. For example, the storage unit converts the image into a format specified by the user and saves it. The storage unit can also automatically convert and save the image format to optimize it and save storage space. For example, the storage unit adjusts the image resolution and saves the image by reducing the file size. This automatically converts the image format, thereby improving storage efficiency. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input image data to a generation AI and have the generation AI perform format conversion.

[0050] When saving an image, the storage unit can select a storage location based on the user's geographical location information. For example, if the user is in a specific area, the storage unit selects a storage location related to that area. For example, if the user is in Tokyo, the storage unit selects cloud storage related to Tokyo. The storage unit can also suggest an optimal storage location based on the user's current location. For example, the storage unit acquires GPS data and suggests a storage location related to the current location. The storage unit can also select a related storage location by referring to the user's past location information. For example, the storage unit analyzes past location information and suggests a related storage location. This allows for the selection of a more appropriate storage location by taking the geographical location information into consideration. Some or all of the above-described processing in the storage unit can be performed using, for example, AI, or can be performed without using AI. For example, the storage unit can input GPS data to a generation AI and have the generation AI select a storage location.

[0051] When saving an image, the storage unit can analyze the user's social media activity and suggest a storage method. For example, the storage unit analyzes the content posted by the user on social media and suggests an optimal storage method. For example, if the user posts "travel" on social media, the storage unit suggests a storage method related to "travel." The storage unit can also refer to the user's social media activity history and suggest a related storage method. For example, the storage unit analyzes the user's past postings and suggests a related storage method. The storage unit can also analyze the activities of the user's friends and followers and suggest an optimal storage method. For example, if the user's friend posts "travel," the storage unit suggests a storage method related to "travel." In this way, by analyzing social media activity, a more appropriate storage method can be suggested. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input social media posting data to a generation AI and have the generation AI suggest a storage method.

[0052] The storage unit can customize the storage method by reflecting the user's past feedback when saving an image. The storage unit, for example, adjusts the storage method based on feedback provided by the user in the past. For example, if the user provides feedback such as "I want to save in high resolution," the storage unit saves in high resolution. The storage unit can also optimize the storage procedure by reflecting the user's feedback. For example, if the user provides feedback such as "The saving procedure is too complicated," the storage unit simplifies the saving procedure. The storage unit can also analyze the user's past feedback and suggest an optimal saving method. For example, the storage unit can suggest an optimal saving method based on the user's past feedback. In this way, by reflecting the past feedback, a more appropriate saving method can be provided. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the user's feedback data into a generation AI and have the generation AI customize the saving method.

[0053] When performing an image search, the search unit can optimize search results by referring to past search history. For example, the search unit may prioritize displaying related search results based on keywords previously searched by the user. For example, if the user previously searched for "landscape," the search unit may prioritize displaying related landscape images. The search unit may also analyze the user's search history and suggest optimal search results. For example, the search unit may learn the user's past search patterns and suggest optimal search results. The search unit may also optimize search results by referring to the user's past search history. For example, the search unit may analyze the user's past search history and optimize the search algorithm. This allows more appropriate search results to be provided by referring to the past search history. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may input the user's search history data into a generation AI and cause the generation AI to optimize the search results.

[0054] During an image search, the search unit can prioritize search results based on the relevance of the images. For example, if an image relates to a specific theme, the search unit prioritizes displaying search results related to that theme. For example, the search unit prioritizes displaying search results such as "nature," "scenery," and "outdoors" for a landscape image. Furthermore, if an image relates to multiple themes, the search unit can prioritize displaying the most relevant search results. For example, for a landscape image, the search unit prioritizes displaying the most relevant search results from among search results such as "nature," "scenery," and "outdoors" and "travel" and "tourism." Furthermore, the search unit can prioritize appropriate search results based on the relevance of the images. For example, the search unit analyzes the content of the image and prioritizes displaying highly relevant search results. Thus, by prioritizing search results based on the relevance of the image, more appropriate search results can be provided. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or without AI. For example, the search unit may input image data to a generation AI and cause the generation AI to prioritize search results based on relevance.

[0055] When performing an image search, the search unit can filter search results based on the user's current project or task. For example, the search unit may prioritize displaying search results related to the user's current project. For example, the search unit may work with a project management tool to automatically extract and display related search results. The search unit may also work with the user's task management tool to filter related search results. For example, the search unit may acquire task information from the task management tool and filter related search results. The search unit may also reference the user's project history and prioritize displaying search results related to past projects. For example, the search unit may analyze past project history and filter related search results. This allows for filtering search results based on the current project or task, thereby providing more relevant search results. Some or all of the above-described processing in the search unit may be performed using, or without, AI. For example, the search unit may input data acquired from the project management tool or task management tool into a generation AI and have the generation AI filter the search results.

[0056] When performing an image search, the search unit can prioritize displaying highly relevant images by taking into account the user's geographical location information. For example, if the user is in a specific area, the search unit prioritizes displaying images related to that area. For example, if the user is in Tokyo, the search unit prioritizes displaying images related to Tokyo. The search unit can also prioritize displaying related images based on the user's current location. For example, the search unit acquires GPS data and prioritizes displaying images related to the current location. The search unit can also refer to the user's past location information and prioritize displaying related images. For example, the search unit analyzes past location information and prioritizes displaying related images. This makes it possible to provide more relevant images by taking geographical location information into consideration. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can input GPS data to a generation AI and cause the generation AI to display highly relevant images.

[0057] When performing an image search, the search unit can analyze the user's social media activity and display related images. For example, the search unit analyzes the content posted by the user on social media and displays related images. For example, if the user posts "travel" on social media, the search unit displays related travel images. The search unit can also refer to the user's social media activity history and display related images. For example, the search unit analyzes the user's past posts and displays related images. The search unit can also analyze the activities of the user's friends and followers and display related images. For example, if the user's friend posts "travel," the search unit displays related travel images. This allows for analysis of social media activity to provide more relevant images. Some or all of the above-described processing in the search unit may be performed using, or without, AI. For example, the search unit may input social media post data into a generation AI and cause the generation AI to display related images.

[0058] The search unit can customize the search method by reflecting the user's past feedback during an image search. For example, the search unit adjusts the search method based on feedback provided by the user in the past. For example, if the user provides feedback indicating that they want more detailed search results, the search unit provides more detailed search results. The search unit can also optimize the search procedure by reflecting the user's feedback. For example, if the user provides feedback indicating that the search procedure is too complicated, the search unit simplifies the search procedure. The search unit can also analyze the user's past feedback and suggest an optimal search method. For example, the search unit can suggest an optimal search method based on the user's past feedback. This allows for a more appropriate search method to be provided by reflecting the past feedback. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can input user feedback data into a generation AI and have the generation AI customize the search method.

[0059] When improving the accuracy of tags, the accuracy improvement unit can optimize the algorithm by referring to past tagging data. The accuracy improvement unit, for example, optimizes the algorithm based on the past tagging data. For example, the accuracy improvement unit analyzes the past tagging data and adjusts the parameters of the algorithm. The accuracy improvement unit can also learn past tagging patterns and optimize the algorithm. For example, the accuracy improvement unit learns the past tagging data and improves the accuracy of the algorithm. The accuracy improvement unit can also improve the accuracy of the algorithm by referring to the past tagging data. For example, the accuracy improvement unit analyzes the past tagging data and optimizes the algorithm. In this way, the accuracy of the algorithm can be improved by referring to the past tagging data. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using, or without, AI. For example, the accuracy improvement unit can input the past tagging data to the generation AI and cause the generation AI to optimize the algorithm.

[0060] The accuracy improvement unit can adjust the algorithm by reflecting user feedback when improving the accuracy of the tag. The accuracy improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the tag accuracy is low, the accuracy improvement unit adjusts the parameters of the algorithm. The accuracy improvement unit can also improve the accuracy of the algorithm by reflecting user feedback. For example, the accuracy improvement unit optimizes the algorithm based on user feedback. The accuracy improvement unit can also analyze past user feedback and optimize the algorithm. For example, the accuracy improvement unit improves the accuracy of the algorithm based on past user feedback. In this way, the accuracy of the algorithm can be improved by reflecting user feedback. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the accuracy improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm.

[0061] The accuracy improvement unit can improve tag accuracy by integrating information from different data sources when improving tag accuracy. For example, the accuracy improvement unit integrates information from different data sources to improve tag accuracy. For example, the accuracy improvement unit integrates data obtained from an external API with data from an internal database to improve tag accuracy. The accuracy improvement unit can also analyze data from different data sources to optimize an algorithm. For example, the accuracy improvement unit analyzes data obtained from an external API and adjusts algorithm parameters. The accuracy improvement unit can also learn information from different data sources to improve tag accuracy. For example, the accuracy improvement unit learns data obtained from an external API and improves algorithm accuracy. In this way, tag accuracy can be improved by integrating information from different data sources. Some or all of the above-described processing in the accuracy improvement unit may be performed using AI, for example, or without AI. For example, the accuracy improvement unit can input data from different data sources into a generation AI and cause the generation AI to perform accuracy improvement.

[0062] The accuracy improvement unit can adjust the algorithm by reflecting the user's past feedback when improving the accuracy of the tag. The accuracy improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the tag accuracy is low, the accuracy improvement unit adjusts the parameters of the algorithm. The accuracy improvement unit can also improve the accuracy of the algorithm by reflecting the user's feedback. For example, the accuracy improvement unit optimizes the algorithm based on the user's feedback. The accuracy improvement unit can also optimize the algorithm by analyzing the user's past feedback. For example, the accuracy improvement unit improves the accuracy of the algorithm based on the user's past feedback. In this way, the accuracy of the algorithm can be improved by reflecting the user's past feedback. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the accuracy improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm.

[0063] When improving search efficiency, the efficiency unit can optimize the algorithm by referring to past search data. The efficiency unit, for example, optimizes the algorithm based on past search data. For example, the efficiency unit analyzes past search data and adjusts algorithm parameters. The efficiency unit can also learn past search patterns and optimize the algorithm. For example, the efficiency unit learns past search data and improves the accuracy of the algorithm. The efficiency unit can also improve the accuracy of the algorithm by referring to past search data. For example, the efficiency unit analyzes past search data and optimizes the algorithm. In this way, the accuracy of the algorithm can be improved by referring to the past search data. Some or all of the above-mentioned processing in the efficiency unit may be performed using AI, or may be performed without using AI. For example, the efficiency unit can input past search data to a generation AI and cause the generation AI to optimize the algorithm.

[0064] The efficiency improvement unit can adjust the algorithm by reflecting user feedback when improving search efficiency. The efficiency improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the search results are inappropriate, the efficiency improvement unit adjusts the parameters of the algorithm. The efficiency improvement unit can also improve the accuracy of the algorithm by reflecting user feedback. For example, the efficiency improvement unit optimizes the algorithm based on user feedback. The efficiency improvement unit can also optimize the algorithm by analyzing the user's past feedback. For example, the efficiency improvement unit improves the accuracy of the algorithm based on the user's past feedback. In this way, the accuracy of the algorithm can be improved by reflecting the user's feedback. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the efficiency improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm.

[0065] The efficiency improvement unit can improve search efficiency by integrating information from different data sources when improving search efficiency. For example, the efficiency improvement unit integrates information from different data sources to improve search efficiency. For example, the efficiency improvement unit integrates data obtained from an external API with data from an internal database to improve search efficiency. The efficiency improvement unit can also analyze data from different data sources to optimize algorithms. For example, the efficiency improvement unit analyzes data obtained from an external API and adjusts algorithm parameters. The efficiency improvement unit can also learn information from different data sources to improve search efficiency. For example, the efficiency improvement unit learns data obtained from an external API to improve the accuracy of the algorithm. In this way, search efficiency can be improved by integrating information from different data sources. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency improvement unit can input data from different data sources into a generation AI and cause the generation AI to perform efficiency improvements.

[0066] The efficiency improvement unit can adjust the algorithm by reflecting the user's past feedback when improving search efficiency. The efficiency improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the search results are inappropriate, the efficiency improvement unit adjusts the parameters of the algorithm. The efficiency improvement unit can also improve the accuracy of the algorithm by reflecting the user's feedback. For example, the efficiency improvement unit optimizes the algorithm based on the user's feedback. The efficiency improvement unit can also optimize the algorithm by analyzing the user's past feedback. For example, the efficiency improvement unit improves the accuracy of the algorithm based on the user's past feedback. In this way, the accuracy of the algorithm can be improved by reflecting the user's past feedback. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the efficiency improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm.

[0067] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0068] The reception unit can refer to the user's past search history and automatically suggest similar descriptions. For example, if the user previously input "a landscape with blue skies and white clouds," the reception unit can suggest a similar description such as "a beautiful landscape with blue skies and white clouds." The reception unit can also prioritize displaying keywords frequently used by the user to simplify input. For example, keywords such as "blue skies" and "white clouds" are displayed with priority. Furthermore, the reception unit can learn specific patterns from the user's past input history and suggest optimal completion candidates. This makes it possible to improve input efficiency by referring to the past input history.

[0069] The storage unit can automatically generate and store image metadata when saving an image. For example, basic metadata such as the date and time the image was taken and the location of the image can be automatically generated and stored. Detailed metadata can also be automatically generated and stored based on the content of the image. For example, metadata such as "blue sky," "white clouds," and "scenery" can be generated. Furthermore, related metadata can also be automatically generated and stored based on tag information of the image. In this way, automatic generation of image metadata can improve storage efficiency.

[0070] When proposing tags, the suggestion unit can adjust the level of detail of the tags based on the content of the image. For example, if the image is complex, detailed tags are proposed. For example, detailed tags such as "mountain," "river," and "tree" are proposed. Also, if the image is simple, concise tags can be proposed. For example, tags such as "background" and "simple" are proposed. Furthermore, tags with an appropriate level of detail can be proposed depending on the content of the image. In this way, more appropriate tags can be proposed by adjusting the level of detail of tags based on the content of the image.

[0071] The storage unit can manage image versions when saving images and can also save past versions. For example, if an image is updated, past versions are automatically saved. It can also manage image version history so that past versions can be restored as needed. It can also manage image versioning so that change history can be tracked. In this way, by managing image versions, past versions can be saved and restored as needed.

[0072] When performing an image search, the search unit can optimize search results by referring to past search history. For example, it can prioritize displaying related search results based on keywords that the user has previously searched for. It can also analyze the user's search history and suggest optimal search results. Furthermore, it can also optimize search results by referring to the user's past search history. This makes it possible to provide more appropriate search results by referring to past search history.

[0073] When proposing tags, the suggestion unit can adjust the use of technical terms in the tags according to the user's level of expertise. For example, if the user is an expert, the suggestion unit can suggest tags containing technical terms. Also, if the user is a beginner, the suggestion unit can suggest tags containing simple terms. Furthermore, the suggestion unit can suggest appropriate tags according to the user's level of expertise. In this way, by adjusting the use of technical terms in the tags according to the user's level of expertise, more appropriate tags can be suggested.

[0074] The processing flow of the first embodiment will be briefly explained below.

[0075] Step 1: The reception unit inputs a description of the image. The image description can be in text or voice format. For example, the user can input a description in text format such as "A landscape with blue skies and white clouds." Alternatively, the user can use voice input to convert dictated content into text using voice recognition technology. Step 2: The suggestion unit uses the generation AI to suggest tags based on the description entered by the reception unit. The generation AI analyzes the description using, for example, a text generation AI (e.g., GPT-3) and suggests appropriate tags such as "blue sky," "white clouds," and "landscape." The generation AI can also understand the context of the description to improve the accuracy of the tags. Step 3: The storage unit stores the images with the tags suggested by the suggestion unit in a database. The database may be a relational database or a NoSQL database. For example, the images with the tags are stored in a relational database or a NoSQL database. Step 4: The search unit searches for images stored by the storage unit. The search unit uses a search algorithm to search for images based on keywords entered by the user and tag information of the stored images, and displays the search results. For example, images are searched for based on tags such as "blue sky," "white clouds," and "landscape."

[0076] (Example 2) An image management system according to an embodiment of the present invention is a system that inputs image descriptions, proposes tags, stores them, and searches them. The image management system uses a generation AI to input image descriptions and request tag suggestions. An image database with the suggested tags is constructed, and a search system is realized using IT technology. For example, a user inputs an image description to the generation AI. For example, a description such as "a landscape with blue sky and white clouds" is input. This description is input to the generation AI. The generation AI then analyzes the input description and proposes appropriate tags. For example, tags such as "blue sky," "white clouds," and "landscape" are suggested. This allows users to easily tag images. An image database with the suggested tags is constructed. For example, tagged images are stored in a database, and a search system is constructed. This search system allows users to quickly search for the images they need. This makes it easier for teams and departments to reuse image materials, improving productivity. This allows the image management system to efficiently perform the series of processes of inputting image descriptions, proposing tags, storing them, and searching them. For example, when creating project materials, images used in the past can be easily searched and reused. In addition, tagging is easy, making image management more efficient. In the future, the company aims to provide a service that uses generative AI to generate image tags and build an image database using cloud technology, which will enable the provision of an even more advanced image management system.

[0077] An image management system according to an embodiment includes a reception unit, a suggestion unit, a storage unit, and a search unit. The reception unit inputs a description of an image. The image description may be in text format, audio format, or other formats, but is not limited to these examples. For example, a user may input a description in text format to the reception unit, such as "a landscape with blue sky and white clouds." The reception unit may also convert what the user dictates into text using voice input. For example, speech recognition technology may be used to convert speech to text. The suggestion unit uses a generation AI to suggest tags based on the description input by the reception unit. The generation AI may analyze the description using, for example, a text generation AI (e.g., a Transformer-based LLM) and suggest appropriate tags. For example, the generation AI may suggest tags such as "blue sky," "white clouds," and "landscape." The suggestion unit may also use the generation AI to improve the accuracy of tags based on the content of the description. For example, the generation AI may understand the context of the description and suggest more appropriate tags. The storage unit stores the images tagged with the tags suggested by the suggestion unit in a database. The database may include, for example, a relational database, a NoSQL database, or the like, but is not limited to these examples. The storage unit, for example, stores tagged images in a relational database. The storage unit can also store images in a NoSQL database. For example, the storage unit stores images including tag information in the NoSQL database. The search unit searches for images stored by the storage unit. The search unit, for example, searches for images using a search algorithm. For example, the search unit searches for images based on keywords entered by a user. The search unit can also display search results based on tag information of stored images. For example, the search unit searches for images based on tags such as "blue sky," "white clouds," and "landscape." This allows the image management system according to the embodiment to efficiently perform a series of processes: inputting a description of an image, proposing tags, saving, and searching. This allows the image management system to easily reuse image material across teams or departments, improving productivity.

[0078] The suggestion unit can analyze the input description using a generation AI and suggest tags. The generation AI can analyze the description using, for example, a text generation AI (e.g., a transformer-based LLM) and suggest appropriate tags. For example, the generation AI can suggest tags such as "blue sky," "white clouds," and "landscape." The generation AI can also improve the accuracy of tags based on the content of the description. For example, the generation AI can understand the context of the description and suggest more appropriate tags. In this way, the use of the generation AI improves the accuracy of tag suggestions. Some or all of the above-mentioned processing in the generation AI can be performed using, for example, AI, or can be performed without using AI. For example, the generation AI can suggest tags using an AI model that takes a description entered by a user as input and outputs tags.

[0079] The storage unit can store the tagged images in a database. Examples of databases include, but are not limited to, relational databases and NoSQL databases. For example, the storage unit stores the tagged images in a relational database. The storage unit can also store the images in a NoSQL database. For example, the storage unit stores images including tag information in a NoSQL database. This allows the tagged images to be stored efficiently. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can store the images using an AI model that takes the tagged images as input and stores them in a database.

[0080] The search unit can search for stored images. The search unit can search for images using, for example, a search algorithm. For example, the search unit can search for images based on keywords entered by a user. The search unit can also display search results based on tag information of stored images. For example, the search unit can search for images based on tags such as "blue sky," "white clouds," and "landscape." This allows for quick search of stored images. Some or all of the above-described processing in the search unit can be performed using, for example, AI, or can be performed without using AI. For example, the search unit can search for images using an AI model that inputs tag information and outputs search results.

[0081] The suggestion unit may include an accuracy improvement unit for improving the accuracy of the tag. The accuracy improvement unit may improve the accuracy of the tag using, for example, a feedback loop. For example, the accuracy improvement unit may collect feedback from users and improve the accuracy of the tag based on the feedback. The accuracy improvement unit may also optimize the algorithm. For example, the accuracy improvement unit may adjust parameters of a tag suggestion algorithm to improve the accuracy. This may improve the accuracy of the tag. Some or all of the above-described processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit may perform the accuracy improvement using an AI model that uses user feedback as input and improves the accuracy of the tag.

[0082] The search unit may include an efficiency improvement unit for improving the efficiency of the search system. The efficiency improvement unit improves the efficiency of the search system, for example, by using a cache function. For example, the efficiency improvement unit stores search results in a cache and retrieves the results from the cache the next time a search is performed. The efficiency improvement unit may also optimize an index. For example, the efficiency improvement unit optimizes a search index to improve search speed. This can improve the efficiency of the search system. Some or all of the above-described processing in the efficiency improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency improvement unit may improve search efficiency by using an AI model that inputs search results and outputs efficient search results.

[0083] The reception unit can estimate the user's emotion and customize the image description input interface based on the estimated user's emotion. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice and calculates an emotion score. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations. This allows the input interface to be customized according to the user's emotion, thereby providing a more user-friendly system. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be 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 reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0084] The reception unit can provide an auto-completion function by referring to the user's past input history when entering an image description. For example, the reception unit automatically completes similar descriptions based on descriptions previously entered by the user. For example, the reception unit completes a similar description, such as "A beautiful landscape with blue skies and white clouds," based on the description previously entered by the user, such as "A landscape with blue skies and white clouds." The reception unit can also prioritize displaying keywords frequently used by the user to simplify input. For example, the reception unit prioritizes displaying keywords frequently used by the user, such as "blue skies" and "white clouds." The reception unit can also learn specific patterns from the user's past input history and suggest optimal completion candidates. For example, the reception unit analyzes the user's past input history and suggests optimal completion candidates. By referring to the past input history, input efficiency can be improved. Some or all of the above-described processing in the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's past input history into a generation AI and cause the generation AI to suggest optimal completion candidates.

[0085] The reception unit can support multiple input methods, such as voice input and handwriting input, when inputting an image description. For example, when a user inputs an image description by voice, the reception unit converts it into text using voice recognition technology. For example, the reception unit automatically analyzes the voice using voice recognition software and saves it as text. The reception unit can also convert a user inputting an image description by handwriting into text using handwriting recognition technology. For example, the reception unit analyzes the handwritten characters using handwriting recognition software and saves them as text. The reception unit can also combine voice input and handwriting input to input image descriptions more intuitively. For example, the reception unit supports the user inputting a description by voice and inputting supplementary information by handwriting. This supports a variety of input methods, thereby improving user convenience. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input voice data or handwritten data into a generation AI and have the generation AI convert it into text data.

[0086] When inputting an image description, the reception unit can filter the input content based on the user's current project or task. For example, the reception unit can prioritize displaying keywords related to the user's current project. For example, the reception unit can work with a project management tool to automatically extract and display related keywords. The reception unit can also work with the user's task management tool to suggest input content based on related tasks. For example, the reception unit can acquire task information from the task management tool and suggest related keywords. The reception unit can also refer to the user's project history and suggest keywords related to past projects. For example, the reception unit can analyze past project history and suggest related keywords. By filtering the input content based on the current project or task, more relevant input can be made. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input data acquired from a project management tool or task management tool into a generation AI and cause the generation AI to suggest related keywords.

[0087] The reception unit can estimate the user's emotions and prioritize input content based on the estimated user emotions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice and calculates the emotion score. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates the emotion score based on heart rate fluctuations. This allows for more efficient input by prioritizing input content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0088] When an image description is input, the reception unit can prioritize displaying highly relevant descriptions based on the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes displaying keywords related to that area. For example, if the user is in a tourist spot, the reception unit prioritizes displaying keywords such as "sightseeing," "famous places," and "scenery." The reception unit can also suggest related image descriptions based on the user's current location. For example, the reception unit acquires GPS data and suggests keywords related to the current location. The reception unit can also refer to the user's past location information and prioritize displaying related keywords. For example, the reception unit analyzes past location information and suggests related keywords. This allows for providing more relevant descriptions by taking geographical location information into consideration. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input GPS data to a generation AI and cause the generation AI to suggest related keywords.

[0089] The reception unit can analyze the user's social media activity and suggest related descriptions when inputting an image description. For example, the reception unit can analyze the content posted by the user on social media and suggest related keywords. For example, if the user posts "travel" on social media, the reception unit can suggest keywords such as "sightseeing," "famous places," and "scenery." The reception unit can also refer to the user's social media activity history to suggest related image descriptions. For example, the reception unit can analyze the user's past posts and suggest related keywords. The reception unit can also analyze the activities of the user's friends and followers and suggest related keywords. For example, if the user's friend posts "travel," the reception unit can suggest keywords such as "sightseeing," "famous places," and "scenery." By analyzing social media activity, more relevant descriptions can be provided. Some or all of the above-described processing by the reception unit can be performed using, for example, AI, or without AI. For example, the reception unit can input social media posting data to a generation AI and cause the generation AI to suggest related keywords.

[0090] The reception unit can customize the input interface by reflecting the user's past feedback when inputting an image description. For example, the reception unit adjusts the interface design based on feedback provided by the user in the past. For example, if the user provides feedback that "a simple interface is preferable," the reception unit provides an interface with a simple design. The reception unit can also reflect the user's feedback and optimize the input procedure. For example, if the user provides feedback that "there are too many input steps," the reception unit simplifies the input procedure. The reception unit can also analyze the user's past feedback and suggest an optimal input method. For example, the reception unit can suggest an optimal input method based on the user's past feedback. This makes it possible to provide an input interface that is easier to use by reflecting the past feedback. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's feedback data to a generation AI and have the generation AI customize the interface.

[0091] The suggestion unit can estimate the user's emotions and adjust the tag suggestion method based on the estimated user's emotions. For example, the suggestion unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on changes in facial expressions. The suggestion unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the voice and calculates an emotion score. The suggestion unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on heart rate fluctuations. This allows the tag suggestion method to be adjusted based on the user's emotions, thereby suggesting more appropriate tags. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0092] When proposing tags, the suggestion unit can adjust the level of detail of the tags based on the content of the image. For example, if the image is complex, the suggestion unit can suggest detailed tags. For example, the suggestion unit can suggest detailed tags such as "mountain," "river," and "tree" for a landscape image. The suggestion unit can also suggest concise tags for a simple image. For example, the suggestion unit can suggest tags such as "background" and "simple" for a simple background image. The suggestion unit can also suggest tags with an appropriate level of detail depending on the content of the image. For example, the suggestion unit can analyze the content of the image and suggest tags with an appropriate level of detail. This makes it possible to suggest more appropriate tags by adjusting the level of detail of the tags based on the content of the image. Some or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit can input image data to a generation AI and cause the generation AI to adjust the level of detail of the tags.

[0093] When proposing tags, the suggestion unit can apply different suggestion algorithms depending on the image category. For example, in the case of a landscape image, the suggestion unit applies an algorithm that suggests tags related to nature. For example, the suggestion unit proposes tags such as "mountain," "river," and "tree" for the landscape image. Furthermore, in the case of a portrait image, the suggestion unit can also apply an algorithm that suggests tags using facial recognition technology. For example, the suggestion unit proposes tags such as "face," "smile," and "portrait" for the portrait image. Furthermore, in the case of a product image, the suggestion unit can also apply an algorithm that suggests tags based on the product category. For example, the suggestion unit proposes tags such as "electronic device," "furniture," and "clothing" for the product image. Thus, by applying different suggestion algorithms depending on the image category, more appropriate tags can be proposed. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input image data to a generation AI and cause the generation AI to suggest tags according to the category.

[0094] When proposing tags, the suggestion unit can improve the accuracy of the suggestions by referring to the user's past tagging history. For example, the suggestion unit suggests similar tags based on tags previously added by the user. For example, the suggestion unit suggests tags such as "landscape" and "nature" for similar images to images previously tagged by the user with "landscape" and "nature." The suggestion unit can also analyze the user's tagging history and suggest optimal tags. For example, the suggestion unit can learn the user's past tagging patterns and suggest optimal tags. The suggestion unit can also improve the accuracy of the suggestions by referring to the user's past tagging history. For example, the suggestion unit analyzes the user's past tagging history and optimizes the suggestion algorithm. In this way, the accuracy of the suggestions can be improved by referring to the past tagging history. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input the user's tagging history data into a generation AI and cause the generation AI to improve the accuracy of the suggestions.

[0095] The suggestion unit can estimate the user's emotions and determine the priority of tags to be suggested based on the estimated user emotions. For example, the suggestion unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on changes in facial expression. The suggestion unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the suggestion unit analyzes the tone and speed of the voice and calculates the emotion score. The suggestion unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the suggestion unit calculates the emotion score based on heart rate fluctuations. This allows the priority of tags to be suggested based on the user's emotions, thereby suggesting more appropriate tags. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0096] When proposing tags, the suggestion unit can determine the priority of tags based on the time the image was taken. For example, if the image was taken recently, the suggestion unit prioritizes proposing the most recent tags. For example, the suggestion unit can suggest tags such as "latest," "fresh green," and "spring" for a recently taken landscape image. The suggestion unit can also prioritize proposing older tags for an older image. For example, the suggestion unit can suggest tags such as "historical," "old-fashioned," and "autumn" for an older landscape image. The suggestion unit can also prioritize proposing appropriate tags depending on the time the image was taken. For example, the suggestion unit can analyze the time the image was taken and suggest appropriate tags. Thus, by determining the priority of tags based on the time the image was taken, more appropriate tags can be suggested. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit can input image metadata into a generation AI and cause the generation AI to suggest tags based on the time the image was taken.

[0097] When suggesting tags, the suggestion unit can adjust the order of tags based on the relevance of the image. For example, if an image is related to a specific theme, the suggestion unit prioritizes suggesting tags related to that theme. For example, the suggestion unit prioritizes suggesting tags such as "nature," "scenery," and "outdoors" for a landscape image. Furthermore, if an image is related to multiple themes, the suggestion unit can also prioritize suggesting the most relevant tag. For example, the suggestion unit prioritizes suggesting the most relevant tag from among tags such as "nature," "scenery," and "outdoors" and "travel" and "tourism" for a landscape image. Furthermore, the suggestion unit can also adjust the order of appropriate tags based on the relevance of the image. For example, the suggestion unit analyzes the content of the image and prioritizes suggesting highly relevant tags. This allows more appropriate tags to be suggested by adjusting the order of tags based on the relevance of the image. Some or all of the above-described processing by the suggestion unit may be performed using, or without, AI. For example, the suggestion unit may input image data to a generation AI and cause the generation AI to adjust the order of tags based on relevance.

[0098] When proposing tags, the suggestion unit can adjust the use of technical terms in the tags according to the user's level of expertise. For example, if the user is an expert, the suggestion unit can suggest tags containing technical terms. For example, the suggestion unit can suggest tags containing technical terms such as "geography," "ecosystem," and "vegetation" for a landscape image. Furthermore, if the user is a beginner, the suggestion unit can also suggest tags containing simple terms. For example, the suggestion unit can suggest tags containing simple terms such as "mountain," "river," and "tree" for a landscape image. Furthermore, the suggestion unit can also suggest appropriate tags according to the user's level of expertise. For example, the suggestion unit can analyze the user's level of expertise and suggest appropriate tags. This allows for the suggestion of more appropriate tags by adjusting the use of technical terms in the tags according to the user's level of expertise. Some or all of the above-described processing in the suggestion unit can be performed, for example, using AI or without AI. For example, the suggestion unit can input the user's level of expertise data into the generation AI and cause the generation AI to suggest tags that adjust the use of technical terms.

[0099] The storage unit can estimate the user's emotions and determine the priority of images to be saved based on the estimated user emotions. For example, the storage unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the storage unit calculates an emotion score based on changes in facial expression. The storage unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the storage unit analyzes the tone and speed of the voice and calculates the emotion score. The storage unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the storage unit calculates the emotion score based on heart rate fluctuations. This allows more appropriate images to be saved by determining the priority of images to be saved based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0100] The storage unit can automatically generate and store image metadata when saving an image. The storage unit automatically generates and stores basic metadata, such as the date and time the image was taken and the location. For example, the storage unit generates information such as "October 1, 2023" and "Tokyo" as image metadata. The storage unit can also automatically generate and store detailed metadata based on the content of the image. For example, the storage unit analyzes the content of the image and generates metadata such as "blue sky," "white clouds," and "landscape." The storage unit can also automatically generate and store related metadata based on the tag information of the image. For example, the storage unit analyzes the tag information and generates metadata such as "nature" and "outdoors." This automatically generating image metadata can improve storage efficiency. Some or all of the above-described processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input image data to a generation AI and have the generation AI generate metadata.

[0101] The storage unit performs image version management when saving an image and can also store past versions. For example, when an image is updated, the storage unit automatically saves past versions. For example, the storage unit saves the "October 1, 2023" version of the image as version 1 and the "October 2, 2023" version as version 2. The storage unit can also manage the version history of the image and enable past versions to be restored as needed. For example, the storage unit displays the version history and allows a user to select and restore a past version. The storage unit can also perform image version management and enable tracking of change history. For example, the storage unit displays the change history of the image and allows a user to check which parts have been changed. In this way, by performing image version management, past versions can also be saved and restored as needed. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without AI. For example, the storage unit can input image data to a generation AI and have the generation AI perform version management.

[0102] The storage unit can automatically convert the image format when saving the image. For example, if an image is saved in a specific format, the storage unit automatically converts the image into another format as needed and saves it. For example, the storage unit converts a JPEG format image into a PNG format and saves it. The storage unit can also automatically convert the image format according to a user's requirements and save it. For example, the storage unit converts the image into a format specified by the user and saves it. The storage unit can also automatically convert and save the image format to optimize it and save storage space. For example, the storage unit adjusts the image resolution and saves the image by reducing the file size. This automatically converts the image format, thereby improving storage efficiency. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input image data to a generation AI and have the generation AI perform format conversion.

[0103] The storage unit can estimate the user's emotion and adjust the display method of the stored image based on the estimated user emotion. For example, the storage unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the storage unit calculates an emotion score based on changes in facial expression. The storage unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the storage unit analyzes the tone and speed of the voice and calculates the emotion score. The storage unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the storage unit calculates the emotion score based on heart rate fluctuations. This allows the display method of the stored image to be adjusted based on the user's emotion, thereby providing a more appropriate display method. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0104] When saving an image, the storage unit can select a storage location based on the user's geographical location information. For example, if the user is in a specific area, the storage unit selects a storage location related to that area. For example, if the user is in Tokyo, the storage unit selects cloud storage related to Tokyo. The storage unit can also suggest an optimal storage location based on the user's current location. For example, the storage unit acquires GPS data and suggests a storage location related to the current location. The storage unit can also select a related storage location by referring to the user's past location information. For example, the storage unit analyzes past location information and suggests a related storage location. This allows for the selection of a more appropriate storage location by taking the geographical location information into consideration. Some or all of the above-described processing in the storage unit can be performed using, for example, AI, or can be performed without using AI. For example, the storage unit can input GPS data to a generation AI and have the generation AI select a storage location.

[0105] When saving an image, the storage unit can analyze the user's social media activity and suggest a storage method. For example, the storage unit analyzes the content posted by the user on social media and suggests an optimal storage method. For example, if the user posts "travel" on social media, the storage unit suggests a storage method related to "travel." The storage unit can also refer to the user's social media activity history and suggest a related storage method. For example, the storage unit analyzes the user's past postings and suggests a related storage method. The storage unit can also analyze the activities of the user's friends and followers and suggest an optimal storage method. For example, if the user's friend posts "travel," the storage unit suggests a storage method related to "travel." In this way, by analyzing social media activity, a more appropriate storage method can be suggested. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input social media posting data to a generation AI and have the generation AI suggest a storage method.

[0106] The storage unit can customize the storage method by reflecting the user's past feedback when saving an image. The storage unit, for example, adjusts the storage method based on feedback provided by the user in the past. For example, if the user provides feedback such as "I want to save in high resolution," the storage unit saves in high resolution. The storage unit can also optimize the storage procedure by reflecting the user's feedback. For example, if the user provides feedback such as "The saving procedure is too complicated," the storage unit simplifies the saving procedure. The storage unit can also analyze the user's past feedback and suggest an optimal saving method. For example, the storage unit can suggest an optimal saving method based on the user's past feedback. In this way, by reflecting the past feedback, a more appropriate saving method can be provided. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the user's feedback data into a generation AI and have the generation AI customize the saving method.

[0107] The search unit can estimate a user's emotion and adjust the display method of search results based on the estimated user's emotion. For example, the search unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on changes in facial expression. The search unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the search unit analyzes the tone and speed of the voice and calculates an emotion score. The search unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on heart rate fluctuations. This allows the display method of search results to be adjusted based on the user's emotion, thereby providing more appropriate search results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be 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 search unit may be performed using, for example, AI, or without AI. For example, the search unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0108] When performing an image search, the search unit can optimize search results by referring to past search history. For example, the search unit may prioritize displaying related search results based on keywords previously searched by the user. For example, if the user previously searched for "landscape," the search unit may prioritize displaying related landscape images. The search unit may also analyze the user's search history and suggest optimal search results. For example, the search unit may learn the user's past search patterns and suggest optimal search results. The search unit may also optimize search results by referring to the user's past search history. For example, the search unit may analyze the user's past search history and optimize the search algorithm. This allows more appropriate search results to be provided by referring to the past search history. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit may input the user's search history data into a generation AI and cause the generation AI to optimize the search results.

[0109] During an image search, the search unit can prioritize search results based on the relevance of the images. For example, if an image relates to a specific theme, the search unit prioritizes displaying search results related to that theme. For example, the search unit prioritizes displaying search results such as "nature," "scenery," and "outdoors" for a landscape image. Furthermore, if an image relates to multiple themes, the search unit can prioritize displaying the most relevant search results. For example, for a landscape image, the search unit prioritizes displaying the most relevant search results from among search results such as "nature," "scenery," and "outdoors" and "travel" and "tourism." Furthermore, the search unit can prioritize appropriate search results based on the relevance of the images. For example, the search unit analyzes the content of the image and prioritizes displaying highly relevant search results. Thus, by prioritizing search results based on the relevance of the image, more appropriate search results can be provided. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or without AI. For example, the search unit may input image data to a generation AI and cause the generation AI to prioritize search results based on relevance.

[0110] When performing an image search, the search unit can filter search results based on the user's current project or task. For example, the search unit may prioritize displaying search results related to the user's current project. For example, the search unit may work with a project management tool to automatically extract and display related search results. The search unit may also work with the user's task management tool to filter related search results. For example, the search unit may acquire task information from the task management tool and filter related search results. The search unit may also reference the user's project history and prioritize displaying search results related to past projects. For example, the search unit may analyze past project history and filter related search results. This allows for filtering search results based on the current project or task, thereby providing more relevant search results. Some or all of the above-described processing in the search unit may be performed using, or without, AI. For example, the search unit may input data acquired from the project management tool or task management tool into a generation AI and have the generation AI filter the search results.

[0111] The search unit can estimate a user's emotion and adjust the display order of search results based on the estimated user's emotion. For example, the search unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on changes in facial expression. The search unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the search unit analyzes the tone and speed of the voice and calculates an emotion score. The search unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the search unit calculates an emotion score based on heart rate fluctuations. This allows the display order of search results to be adjusted based on the user's emotion, thereby providing more appropriate search results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be 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 search unit may be performed using, for example, AI, or without AI. For example, the search unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0112] When performing an image search, the search unit can prioritize displaying highly relevant images by taking into account the user's geographical location information. For example, if the user is in a specific area, the search unit prioritizes displaying images related to that area. For example, if the user is in Tokyo, the search unit prioritizes displaying images related to Tokyo. The search unit can also prioritize displaying related images based on the user's current location. For example, the search unit acquires GPS data and prioritizes displaying images related to the current location. The search unit can also refer to the user's past location information and prioritize displaying related images. For example, the search unit analyzes past location information and prioritizes displaying related images. This makes it possible to provide more relevant images by taking geographical location information into consideration. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can input GPS data to a generation AI and cause the generation AI to display highly relevant images.

[0113] When performing an image search, the search unit can analyze the user's social media activity and display related images. For example, the search unit analyzes the content posted by the user on social media and displays related images. For example, if the user posts "travel" on social media, the search unit displays related travel images. The search unit can also refer to the user's social media activity history and display related images. For example, the search unit analyzes the user's past posts and displays related images. The search unit can also analyze the activities of the user's friends and followers and display related images. For example, if the user's friend posts "travel," the search unit displays related travel images. This allows for analysis of social media activity to provide more relevant images. Some or all of the above-described processing in the search unit may be performed using, or without, AI. For example, the search unit may input social media post data into a generation AI and cause the generation AI to display related images.

[0114] The search unit can customize the search method by reflecting the user's past feedback during an image search. For example, the search unit adjusts the search method based on feedback provided by the user in the past. For example, if the user provides feedback indicating that they want more detailed search results, the search unit provides more detailed search results. The search unit can also optimize the search procedure by reflecting the user's feedback. For example, if the user provides feedback indicating that the search procedure is too complicated, the search unit simplifies the search procedure. The search unit can also analyze the user's past feedback and suggest an optimal search method. For example, the search unit can suggest an optimal search method based on the user's past feedback. This allows for a more appropriate search method to be provided by reflecting the past feedback. Some or all of the above-described processing in the search unit may be performed using, for example, AI, or may be performed without using AI. For example, the search unit can input user feedback data into a generation AI and have the generation AI customize the search method.

[0115] The accuracy improvement unit can estimate the user's emotion and adjust the tag accuracy improvement method based on the estimated user emotion. For example, the accuracy improvement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the accuracy improvement unit calculates an emotion score based on changes in facial expression. The accuracy improvement unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the accuracy improvement unit analyzes the tone and speed of the voice and calculates the emotion score. The accuracy improvement unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the accuracy improvement unit calculates the emotion score based on heart rate fluctuations. This allows the tag accuracy improvement method to be adjusted based on the user's emotion, thereby providing more appropriate tags. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0116] When improving the accuracy of tags, the accuracy improvement unit can optimize the algorithm by referring to past tagging data. The accuracy improvement unit, for example, optimizes the algorithm based on the past tagging data. For example, the accuracy improvement unit analyzes the past tagging data and adjusts the parameters of the algorithm. The accuracy improvement unit can also learn past tagging patterns and optimize the algorithm. For example, the accuracy improvement unit learns the past tagging data and improves the accuracy of the algorithm. The accuracy improvement unit can also improve the accuracy of the algorithm by referring to the past tagging data. For example, the accuracy improvement unit analyzes the past tagging data and optimizes the algorithm. In this way, the accuracy of the algorithm can be improved by referring to the past tagging data. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using, or without, AI. For example, the accuracy improvement unit can input the past tagging data to the generation AI and cause the generation AI to optimize the algorithm.

[0117] The accuracy improvement unit can adjust the algorithm by reflecting user feedback when improving the accuracy of the tag. The accuracy improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the tag accuracy is low, the accuracy improvement unit adjusts the parameters of the algorithm. The accuracy improvement unit can also improve the accuracy of the algorithm by reflecting user feedback. For example, the accuracy improvement unit optimizes the algorithm based on user feedback. The accuracy improvement unit can also analyze past user feedback and optimize the algorithm. For example, the accuracy improvement unit improves the accuracy of the algorithm based on past user feedback. In this way, the accuracy of the algorithm can be improved by reflecting user feedback. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the accuracy improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm.

[0118] The accuracy improvement unit can estimate the user's emotion and adjust the frequency of accuracy improvement based on the estimated user's emotion. For example, the accuracy improvement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the accuracy improvement unit calculates an emotion score based on changes in facial expression. The accuracy improvement unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the accuracy improvement unit analyzes the tone and speed of the voice and calculates the emotion score. The accuracy improvement unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the accuracy improvement unit calculates the emotion score based on heart rate fluctuations. This allows for more appropriate accuracy improvement by adjusting the frequency of accuracy improvement based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the accuracy improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the accuracy improvement unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0119] The accuracy improvement unit can improve tag accuracy by integrating information from different data sources when improving tag accuracy. For example, the accuracy improvement unit integrates information from different data sources to improve tag accuracy. For example, the accuracy improvement unit integrates data obtained from an external API with data from an internal database to improve tag accuracy. The accuracy improvement unit can also analyze data from different data sources to optimize an algorithm. For example, the accuracy improvement unit analyzes data obtained from an external API and adjusts algorithm parameters. The accuracy improvement unit can also learn information from different data sources to improve tag accuracy. For example, the accuracy improvement unit learns data obtained from an external API and improves algorithm accuracy. In this way, tag accuracy can be improved by integrating information from different data sources. Some or all of the above-described processing in the accuracy improvement unit may be performed using AI, for example, or without AI. For example, the accuracy improvement unit can input data from different data sources into a generation AI and cause the generation AI to perform accuracy improvement.

[0120] The accuracy improvement unit can adjust the algorithm by reflecting the user's past feedback when improving the accuracy of the tag. The accuracy improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the tag accuracy is low, the accuracy improvement unit adjusts the parameters of the algorithm. The accuracy improvement unit can also improve the accuracy of the algorithm by reflecting the user's feedback. For example, the accuracy improvement unit optimizes the algorithm based on the user's feedback. The accuracy improvement unit can also optimize the algorithm by analyzing the user's past feedback. For example, the accuracy improvement unit improves the accuracy of the algorithm based on the user's past feedback. In this way, the accuracy of the algorithm can be improved by reflecting the user's past feedback. Some or all of the above-mentioned processing in the accuracy improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the accuracy improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm.

[0121] The efficiency improvement unit can estimate the user's emotions and adjust the search efficiency improvement method based on the estimated user's emotions. For example, the efficiency improvement unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on changes in facial expression. The efficiency improvement unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the efficiency improvement unit analyzes the tone and speed of the voice and calculates an emotion score. The efficiency improvement unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on heart rate fluctuations. This allows the search efficiency improvement method to be adjusted based on the user's emotions, thereby providing more appropriate search results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the efficiency improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency improvement unit may input image data of a user taken with a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0122] When improving search efficiency, the efficiency unit can optimize the algorithm by referring to past search data. The efficiency unit, for example, optimizes the algorithm based on past search data. For example, the efficiency unit analyzes past search data and adjusts algorithm parameters. The efficiency unit can also learn past search patterns and optimize the algorithm. For example, the efficiency unit learns past search data and improves the accuracy of the algorithm. The efficiency unit can also improve the accuracy of the algorithm by referring to past search data. For example, the efficiency unit analyzes past search data and optimizes the algorithm. In this way, the accuracy of the algorithm can be improved by referring to the past search data. Some or all of the above-mentioned processing in the efficiency unit may be performed using AI, or may be performed without using AI. For example, the efficiency unit can input past search data to a generation AI and cause the generation AI to optimize the algorithm.

[0123] The efficiency improvement unit can adjust the algorithm by reflecting user feedback when improving search efficiency. The efficiency improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the search results are inappropriate, the efficiency improvement unit adjusts the parameters of the algorithm. The efficiency improvement unit can also improve the accuracy of the algorithm by reflecting user feedback. For example, the efficiency improvement unit optimizes the algorithm based on user feedback. The efficiency improvement unit can also optimize the algorithm by analyzing the user's past feedback. For example, the efficiency improvement unit improves the accuracy of the algorithm based on the user's past feedback. In this way, the accuracy of the algorithm can be improved by reflecting the user's feedback. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the efficiency improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm.

[0124] The efficiency improvement unit can estimate the user's emotions and adjust the frequency of efficiency improvements based on the estimated user emotions. For example, the efficiency improvement unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on changes in facial expressions. The efficiency improvement unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the efficiency improvement unit analyzes the tone and speed of the voice and calculates an emotion score. The efficiency improvement unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the efficiency improvement unit calculates an emotion score based on heart rate fluctuations. This allows for more appropriate efficiency improvement by adjusting the frequency of efficiency improvements based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be 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 efficiency improvement unit can be performed using, for example, AI, or without AI. For example, the efficiency improvement unit can input image data of a user taken with a camera into the generation AI and have the generation AI estimate the user's emotions.

[0125] The efficiency improvement unit can improve search efficiency by integrating information from different data sources when improving search efficiency. For example, the efficiency improvement unit integrates information from different data sources to improve search efficiency. For example, the efficiency improvement unit integrates data obtained from an external API with data from an internal database to improve search efficiency. The efficiency improvement unit can also analyze data from different data sources to optimize algorithms. For example, the efficiency improvement unit analyzes data obtained from an external API and adjusts algorithm parameters. The efficiency improvement unit can also learn information from different data sources to improve search efficiency. For example, the efficiency improvement unit learns data obtained from an external API to improve the accuracy of the algorithm. In this way, search efficiency can be improved by integrating information from different data sources. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed using, for example, AI, or may be performed without using AI. For example, the efficiency improvement unit can input data from different data sources into a generation AI and cause the generation AI to perform efficiency improvements.

[0126] The efficiency improvement unit can adjust the algorithm by reflecting the user's past feedback when improving search efficiency. The efficiency improvement unit, for example, adjusts the algorithm based on feedback provided by the user. For example, if the user provides feedback that the search results are inappropriate, the efficiency improvement unit adjusts the parameters of the algorithm. The efficiency improvement unit can also improve the accuracy of the algorithm by reflecting the user's feedback. For example, the efficiency improvement unit optimizes the algorithm based on the user's feedback. The efficiency improvement unit can also optimize the algorithm by analyzing the user's past feedback. For example, the efficiency improvement unit improves the accuracy of the algorithm based on the user's past feedback. In this way, the accuracy of the algorithm can be improved by reflecting the user's past feedback. Some or all of the above-mentioned processing in the efficiency improvement unit may be performed using AI, for example, or may be performed without using AI. For example, the efficiency improvement unit can input user feedback data to the generation AI and cause the generation AI to adjust the algorithm. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, suggestion unit, storage unit, and search unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the reception device 38 of the smart device 14, and allows a user to input a description of an image in text or voice format. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests tags based on the input description using a generation AI. For example, the storage unit stores images with the suggested tags in the database 24 of the data processing device 12. For example, the search unit is realized by the specific processing unit 290 of the data processing device 12, and searches for stored images. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, suggestion unit, storage unit, and search unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the microphone 238 or camera 42 of the smart glasses 214, allowing the user to input voice or images. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests tags based on the input description using a generation AI. For example, the storage unit stores images with the suggested tags in the database 24 of the data processing device 12. For example, the search unit is realized by the specific processing unit 290 of the data processing device 12, and searches for stored images. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, suggestion unit, storage unit, and search unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit is realized by the microphone 238 or camera 42 of the headset-type terminal 314, allowing the user to input voice or images. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests tags based on the input description using a generation AI. For example, the storage unit stores images with the suggested tags in the database 24 of the data processing device 12. For example, the search unit is realized by the specific processing unit 290 of the data processing device 12, and searches for stored images. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, suggestion unit, storage unit, and search unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the microphone 238 or camera 42 of the robot 414, allowing the user to input voice or images. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests tags based on the input description using a generation AI. For example, the storage unit stores images with the suggested tags in the database 24 of the data processing device 12. For example, the search unit is realized by the specific processing unit 290 of the data processing device 12, and searches for stored images.

[0127] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0128] The reception unit can refer to the user's past search history and automatically suggest similar descriptions. For example, if the user previously input "a landscape with blue skies and white clouds," the reception unit can suggest a similar description such as "a beautiful landscape with blue skies and white clouds." The reception unit can also prioritize displaying keywords frequently used by the user to simplify input. For example, keywords such as "blue skies" and "white clouds" are displayed with priority. Furthermore, the reception unit can learn specific patterns from the user's past input history and suggest optimal completion candidates. This makes it possible to improve input efficiency by referring to the past input history.

[0129] The suggestion unit can estimate the user's emotions and adjust the tag suggestion method based on the estimated emotions. For example, if the user is feeling stressed, the suggestion unit can prioritize suggesting simple and intuitive tags. On the other hand, if the user is relaxed, the suggestion unit can suggest more detailed and complex tags. Furthermore, the suggestion unit can adjust the tag suggestion speed according to the user's emotions. In this way, by adjusting the tag suggestion method based on the user's emotions, more appropriate tags can be suggested.

[0130] The storage unit can automatically generate and store image metadata when saving an image. For example, basic metadata such as the date and time the image was taken and the location of the image can be automatically generated and stored. Detailed metadata can also be automatically generated and stored based on the content of the image. For example, metadata such as "blue sky," "white clouds," and "scenery" can be generated. Furthermore, related metadata can also be automatically generated and stored based on tag information of the image. In this way, automatic generation of image metadata can improve storage efficiency.

[0131] The search unit can estimate the user's emotions and adjust the way search results are displayed based on the estimated emotions. For example, if the user is feeling stressed, the search unit can prioritize displaying simple and intuitive search results. On the other hand, if the user is relaxed, the search unit can display more detailed and complex search results. Furthermore, the search unit can adjust the speed at which search results are displayed according to the user's emotions. In this way, by adjusting the way search results are displayed based on the user's emotions, more appropriate search results can be provided.

[0132] When proposing tags, the suggestion unit can adjust the level of detail of the tags based on the content of the image. For example, if the image is complex, detailed tags are proposed. For example, detailed tags such as "mountain," "river," and "tree" are proposed. Also, if the image is simple, concise tags can be proposed. For example, tags such as "background" and "simple" are proposed. Furthermore, tags with an appropriate level of detail can be proposed depending on the content of the image. In this way, more appropriate tags can be proposed by adjusting the level of detail of tags based on the content of the image.

[0133] The reception unit can estimate the user's emotions and customize the image description input interface based on the estimated emotions. For example, if the user is feeling stressed, a simple and intuitive interface can be provided. Alternatively, if the user is relaxed, a more detailed and complex interface can be provided. Furthermore, the color and layout of the input interface can be adjusted according to the user's emotions. This makes it possible to provide a more user-friendly system by customizing the input interface according to the user's emotions.

[0134] The storage unit can manage image versions when saving images and can also save past versions. For example, if an image is updated, past versions are automatically saved. It can also manage image version history so that past versions can be restored as needed. It can also manage image versioning so that change history can be tracked. In this way, by managing image versions, past versions can be saved and restored as needed.

[0135] The suggestion unit can estimate the user's emotions and determine the priority of tags to be suggested based on the estimated emotions. For example, if the user is feeling stressed, simple and intuitive tags can be suggested with priority. On the other hand, if the user is relaxed, more detailed and complex tags can be suggested with priority. Furthermore, the tag suggestion speed can be adjusted according to the user's emotions. In this way, by determining the priority of tags to be suggested based on the user's emotions, more appropriate tags can be suggested.

[0136] When performing an image search, the search unit can optimize search results by referring to past search history. For example, it can prioritize displaying related search results based on keywords that the user has previously searched for. It can also analyze the user's search history and suggest optimal search results. Furthermore, it can also optimize search results by referring to the user's past search history. This makes it possible to provide more appropriate search results by referring to past search history.

[0137] When proposing tags, the suggestion unit can adjust the use of technical terms in the tags according to the user's level of expertise. For example, if the user is an expert, the suggestion unit can suggest tags containing technical terms. Also, if the user is a beginner, the suggestion unit can suggest tags containing simple terms. Furthermore, the suggestion unit can suggest appropriate tags according to the user's level of expertise. In this way, by adjusting the use of technical terms in the tags according to the user's level of expertise, more appropriate tags can be suggested.

[0138] The processing flow of the second embodiment will be briefly explained below.

[0139] Step 1: The reception unit inputs a description of the image. The image description can be in text or voice format. For example, the user can input a description in text format such as "A landscape with blue skies and white clouds." Alternatively, the user can use voice input to convert dictated content into text using voice recognition technology. Step 2: The suggestion unit uses the generation AI to suggest tags based on the description entered by the reception unit. The generation AI analyzes the description using, for example, a text generation AI (e.g., GPT-3) and suggests appropriate tags such as "blue sky," "white clouds," and "landscape." The generation AI can also understand the context of the description to improve the accuracy of the tags. Step 3: The storage unit stores the images with the tags suggested by the suggestion unit in a database. The database may be a relational database or a NoSQL database. For example, the images with the tags are stored in a relational database or a NoSQL database. Step 4: The search unit searches for images stored by the storage unit. The search unit uses a search algorithm to search for images based on keywords entered by the user and tag information of the stored images, and displays the search results. For example, images are searched for based on tags such as "blue sky," "white clouds," and "landscape."

[0140] 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.

[0141] 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.

[0142] 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.

[0143] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0144] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0158] 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.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0174] 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.

[0175] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0176] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0177] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0191] 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.

[0192] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0198] 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."

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] [Explanation of symbols]

[0212] 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. a reception section for inputting a description of an image; a suggestion unit that suggests tags based on the description input by the reception unit; a storage unit that stores images to which the tags proposed by the suggestion unit have been added; a search unit that searches for images stored by the storage unit; Equipped with A system characterized by:

2. The proposal unit Uses generative AI to analyze input descriptions and suggest tags 2. The system of claim 1.

3. The storage unit Save the tagged images in the database 2. The system of claim 1.

4. The search unit Search for saved images 2. The system of claim 1.

5. The proposal unit Equipped with an accuracy improvement unit to improve tag accuracy 2. The system of claim 1.

6. The search unit Equipped with an efficiency improvement department to improve the efficiency of the search system 2. The system of claim 1.

7. The reception unit Estimating user emotions and customizing the image description input interface based on the estimated user emotions 2. The system of claim 1.

8. The reception unit When entering image descriptions, provide an auto-complete function by referring to the user's past input history.

2. The system of claim 1.

Images