System

Abstract

An object of a system according to an embodiment is to analyze a post content of a user and to effectively recommend related content.SOLUTION: A system according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a recommendation unit. The reception unit receives a post of a user. The analysis unit analyzes the post content received by the reception unit. The generation unit generates a data set based on the content analyzed by the analysis unit. The recommendation unit recommends the related content based on the data set generated by the generation 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 technologies have not yet been able to effectively analyze user posts and recommend related content, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze the content posted by users and effectively recommend related content. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a generation unit, and a recommendation unit. The reception unit receives posts from users. The analysis unit analyzes the content of the posts received by the reception unit. The generation unit generates a dataset based on the content analyzed by the analysis unit. The recommendation unit recommends related content based on the dataset generated by the generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze the content posted by the user and effectively recommend related content. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A social networking service (SNS) service according to an embodiment of the present invention is a system that uses generative AI technology to analyze content posted by users and automatically generate an open dataset. This SNS service accepts content posted by users, such as text, images, and videos, and the generative AI analyzes the posted content and classifies it into specific themes or categories. For example, when a user posts travel photos, the generative AI analyzes the photos and adds them to a travel-related dataset. This dataset is made public as an open dataset that researchers and developers can freely use. Furthermore, the generative AI also analyzes user posts and automatically recommends related content. For example, when a user posts a recipe for a specific dish, the generative AI recommends other recipes and photos of dishes related to the recipe. This allows users to easily find content that matches their interests. By utilizing generative AI technology, SNS services can efficiently analyze user-posted content, automatically generate open datasets, and recommend content that matches users' interests, improving the user experience. This is expected to significantly contribute to the spread of AI services, including generative AI.

[0029] An SNS service according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a recommendation unit. The reception unit receives content such as text, images, and videos posted by users. For example, the reception unit can receive text posted by users. The reception unit can also receive images posted by users. The reception unit can also receive videos posted by users. The analysis unit uses a generation AI to analyze the content posted by the reception unit and classify it into specific themes or categories. For example, the analysis unit uses a generation AI to analyze text posted by users and classify it into specific themes. The analysis unit can also use a generation AI to analyze images posted by users and classify them into specific categories. The analysis unit can also use a generation AI to analyze videos posted by users and classify them into specific themes. The generation unit generates an open dataset based on the content analyzed by the analysis unit. For example, the generation unit generates an open dataset based on text data analyzed by the analysis unit. The generation unit can also generate an open dataset based on image data analyzed by the analysis unit. The generation unit can also generate an open dataset based on the video data analyzed by the analysis unit. The recommendation unit recommends related content based on the dataset generated by the generation unit. For example, the recommendation unit uses the generation AI to recommend content related to text posted by a user. The recommendation unit can also use the generation AI to recommend content related to an image posted by a user. The recommendation unit can also use the generation AI to recommend content related to a video posted by a user. This allows the SNS service according to the embodiment to efficiently analyze user posts, generate a dataset, and recommend related content.

[0030] The reception unit can receive text, image, and video content posted by users. The reception unit, for example, receives text posted by users. For example, the reception unit can receive text posted by users with a character limit. The reception unit can also receive images posted by users. For example, the reception unit can receive images posted by users in JPEG format. The reception unit can also receive videos posted by users. For example, the reception unit can receive videos posted by users in high resolution. This allows users to post content in various formats.

[0031] The analysis unit can use the generation AI to analyze the posted content and classify it into specific themes or categories. For example, the analysis unit can use the generation AI to analyze text posted by users and classify it into specific themes. For example, the analysis unit can use the generation AI to analyze text posted by users using natural language processing technology and classify it into themes such as news, entertainment, and technology. The analysis unit can also use the generation AI to analyze images posted by users and classify them into specific categories. For example, the analysis unit can use the generation AI to analyze images posted by users using image analysis technology and classify them into categories such as travel, cooking, and events. The analysis unit can also use the generation AI to analyze videos posted by users and classify them into specific themes. For example, the analysis unit can use the generation AI to analyze videos posted by users using video analysis technology and classify them into themes such as news, entertainment, and technology. This allows the posted content to be efficiently analyzed and classified.

[0032] The generation unit can generate an open dataset based on the analysis results. The generation unit generates the open dataset based on, for example, text data analyzed by the analysis unit. For example, the generation unit generates the text data analyzed by the analysis unit as an open dataset in CSV format. The generation unit can also generate the open dataset based on image data analyzed by the analysis unit. For example, the generation unit generates the image data analyzed by the analysis unit as an open dataset in JPEG format. The generation unit can also generate the open dataset based on video data analyzed by the analysis unit. For example, the generation unit generates the video data analyzed by the analysis unit as an open dataset in MP4 format. This makes it possible to generate a dataset based on the analysis results.

[0033] The recommendation unit can use the generation AI to recommend content related to the content posted by the user. For example, the recommendation unit uses the generation AI to recommend content related to text posted by the user. For example, the recommendation unit uses the generation AI to recommend other text content related to the text posted by the user. The recommendation unit can also use the generation AI to recommend content related to images posted by the user. For example, the recommendation unit uses the generation AI to recommend other image content related to images posted by the user. The recommendation unit can also use the generation AI to recommend content related to videos posted by the user. For example, the recommendation unit uses the generation AI to recommend other video content related to the video posted by the user. This makes it possible to automatically recommend content related to the content posted by the user.

[0034] The reception unit can analyze the user's past posting history and select an appropriate reception method. For example, the reception unit analyzes the time periods in which the user frequently posted in the past and sends a notification encouraging the user to post during those time periods. For example, the reception unit retrieves the user's past posting history from a database and identifies the time periods in which the user frequently posted. The reception unit can also preferentially suggest posting formats (text, image, video, etc.) that the user has used in the past. For example, the reception unit analyzes the user's past posting history and identifies the most frequently used posting format. The reception unit can also analyze the content of the user's past posts and automatically suggest related themes and categories. For example, the reception unit analyzes the content of the user's past posts using natural language processing technology and identifies related themes and categories. This makes it possible to select the optimal reception method based on the user's past posting history.

[0035] The reception unit can filter posts based on the user's current areas of interest when receiving the posts. For example, the reception unit preferentially receives only posts related to topics that the user has recently been interested in. For example, the reception unit can analyze the user's past browsing history and identify topics that the user has recently been interested in. The reception unit can also analyze the content of posts from accounts the user follows and preferentially receive related posts. For example, the reception unit can retrieve the content of posts from accounts the user follows from a database and identify related posts. The reception unit can also filter and receive related posts based on keywords recently searched by the user. For example, the reception unit can analyze the user's search history and identify related keywords. This makes it possible to filter posts based on the user's areas of interest.

[0036] When accepting a post, the acceptance unit can select the optimal acceptance means depending on the user's input method. For example, if the user selects voice input, the acceptance unit converts the voice into text using voice recognition technology and accepts the post. For example, the acceptance unit records the user's voice with a microphone and converts it into text using voice recognition software. Furthermore, when the user posts an image, the acceptance unit can analyze the content using image analysis technology and classify it into an appropriate category before accepting the post. For example, the acceptance unit analyzes the image posted by the user using image analysis software and classifies it into a category. Furthermore, when the user posts a video, the acceptance unit can analyze the content using video analysis technology and add it to an appropriate dataset before accepting the post. For example, the acceptance unit analyzes the video posted by the user using video analysis software and adds it to a dataset. This makes it possible to select the optimal acceptance means depending on the user's input method.

[0037] When accepting posts, the reception unit can prioritize accepting posts that are highly relevant by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes accepting posts related to that area. For example, the reception unit acquires the user's GPS data and identifies the user's current location. Furthermore, if the user is traveling, the reception unit can prioritize accepting posts related to the user's travel destination. For example, the reception unit analyzes the user's IP address and identifies the user's travel destination. Furthermore, if the user is at an event venue, the reception unit can prioritize accepting posts related to the event. For example, the reception unit acquires the user's location information in real time and identifies the event venue. This allows posts that are highly relevant to be accepted preferentially based on the user's geographical location information.

[0038] The reception unit can analyze the user's social media activity when receiving a post and receive related posts. The reception unit, for example, analyzes content shared by the user on social media and preferentially receives related posts. For example, the reception unit acquires and analyzes content shared from the user's social media account. The reception unit can also analyze content posted by accounts the user follows on social media and preferentially receive related posts. For example, the reception unit acquires and analyzes content posted by accounts the user follows from a database. The reception unit can also analyze activity content of groups the user participates in on social media and preferentially receive related posts. For example, the reception unit acquires and analyzes activity content of groups the user participates in from a database. This makes it possible to receive related posts based on the user's social media activity.

[0039] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a post. For example, the reception unit analyzes feedback on content previously posted by the user and preferentially receives posts with similar content. For example, the reception unit acquires and analyzes rating comments on the user's past posts from a database. The reception unit can also preferentially receive posts with high ratings based on the ratings on content previously posted by the user. For example, the reception unit acquires and analyzes star ratings on the user's past posts from a database. The reception unit can also analyze comments on content previously posted by the user and preferentially receive related posts. For example, the reception unit acquires and analyzes comments on the user's past posts from a database. This makes it possible to customize the reception method based on the user's past feedback.

[0040] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the posted content. For example, the analysis unit performs a detailed analysis on posted content with a high level of importance to provide deep insight. For example, the analysis unit evaluates the influence of the posted content and identifies its importance. The analysis unit can also perform a concise analysis on posted content with a low level of importance to provide basic information. For example, the analysis unit evaluates the urgency of the posted content and identifies its importance. The analysis unit can also appropriately allocate analysis resources according to the importance of the posted content to perform efficient analysis. For example, the analysis unit allocates more resources to posted content with a high level of importance. This makes it possible to adjust the level of detail of the analysis based on the importance of the posted content.

[0041] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the post content. For example, the analysis unit applies an image analysis algorithm to travel-related posts to extract features of travel destinations. For example, the analysis unit analyzes travel-related posts using image analysis technology to identify features of travel destinations. The analysis unit can also apply a text analysis algorithm to cooking-related posts to extract recipe details. For example, the analysis unit analyzes cooking-related posts using natural language processing technology to identify recipe details. The analysis unit can also apply a video analysis algorithm to event-related posts to extract event highlights. For example, the analysis unit analyzes event-related posts using video analysis technology to identify event highlights. This makes it possible to apply different analysis algorithms depending on the category of the post content.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the analysis accuracy of posts with similar content based on the analysis results of content posted by the user in the past. For example, the analysis unit obtains the user's past analysis results from a database and optimizes the analysis algorithm. The analysis unit can also analyze the user's past analysis results and optimize the analysis algorithm. For example, the analysis unit analyzes the user's past analysis results and adjusts the parameters of the algorithm. The analysis unit can also adjust the analysis parameters by referring to the user's past analysis results to improve accuracy. For example, the analysis unit adjusts the analysis parameters based on the user's past analysis results. In this way, the analysis accuracy can be improved by referring to the user's past analysis results.

[0043] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the posted content. The analysis unit, for example, prioritizes analysis of the most recent posted content and provides information in real time. For example, the analysis unit retrieves the submission date and time of the posted content from a database and identifies the most recent post. The analysis unit can also prioritize analysis of posted content during a specific event period and provide information related to the event. For example, the analysis unit retrieves and analyzes posted content during the event period from a database. The analysis unit can also prioritize analysis of posted content within a period specified by the user and provide necessary information quickly. For example, the analysis unit retrieves and analyzes posted content within a period specified by the user from a database. This makes it possible to determine the priority of analysis based on the submission time of the posted content.

[0044] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the posted content. For example, the analysis unit prioritizes analysis of highly relevant posted content and provides useful information to the user. For example, the analysis unit obtains the relevance of the posted content from a database and identifies highly relevant posts. The analysis unit can also postpone less relevant posted content and provide important information quickly. For example, the analysis unit evaluates the relevance of the posted content and postpones less relevant posts. The analysis unit can also appropriately allocate analysis resources according to the relevance of the posted content and perform efficient analysis. For example, the analysis unit allocates more resources to more relevant posted content. This makes it possible to adjust the order of analysis based on the relevance of the posted content.

[0045] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides the analysis results using detailed technical terminology. For example, the analysis unit evaluates the user's level of expertise from survey results and uses technical terminology. Furthermore, if the user does not have technical expertise, the analysis unit can provide the analysis results using simple and easy-to-understand language. For example, the analysis unit analyzes the user's past posts and evaluates the level of expertise. Furthermore, the analysis unit can adjust the way the analysis results are expressed according to the user's level of expertise and provide information that is easy to understand. For example, the analysis unit provides definitions of technical terms and uses simple expressions. This makes it possible to provide analysis results according to the user's level of expertise.

[0046] When generating a dataset, the generation unit can adjust the level of detail of the generation based on the importance of the analysis result. For example, the generation unit generates a detailed dataset for analysis results with high importance to provide deep insight. For example, the generation unit evaluates the impact of the analysis result and identifies its importance. The generation unit can also generate a concise dataset for analysis results with low importance to provide basic information. For example, the generation unit evaluates the urgency of the analysis result and identifies its importance. The generation unit can also appropriately allocate resources for dataset generation according to the importance of the analysis result to perform efficient generation. For example, the generation unit allocates more resources to analysis results with high importance. This makes it possible to adjust the level of detail of dataset generation based on the importance of the analysis result.

[0047] When generating a dataset, the generation unit can apply different generation algorithms depending on the category of the analysis results. For example, the generation unit applies an image analysis algorithm to analysis results related to travel to extract features of travel destinations. For example, the generation unit analyzes the analysis results related to travel using image analysis technology to identify features of travel destinations. The generation unit can also apply a text analysis algorithm to analysis results related to cooking to extract recipe details. For example, the generation unit analyzes the analysis results related to cooking using natural language processing technology to identify recipe details. The generation unit can also apply a video analysis algorithm to analysis results related to events to extract event highlights. For example, the generation unit analyzes the analysis results related to events using video analysis technology to identify event highlights. This makes it possible to apply different generation algorithms depending on the category of the analysis results.

[0048] When generating a dataset, the generation unit can improve the accuracy of generation by referring to the user's past generation results. The generation unit, for example, improves the accuracy of generation of a dataset with similar content based on a dataset previously generated by the user. For example, the generation unit obtains the user's past generation results from a database and optimizes the generation algorithm. The generation unit can also analyze the user's past generation results and optimize the generation algorithm. For example, the generation unit analyzes the user's past generation results and adjusts the parameters of the algorithm. The generation unit can also adjust the generation parameters by referring to the user's past generation results to improve accuracy. For example, the generation unit adjusts the generation parameters based on the user's past generation results. This makes it possible to improve the accuracy of generation by referring to the user's past generation results.

[0049] When generating a dataset, the generation unit can determine the generation priority based on the submission time of the analysis results. The generation unit, for example, prioritizes generating the latest analysis results and provides information in real time. For example, the generation unit obtains the submission date and time of the analysis results from a database and identifies the latest analysis results. The generation unit can also prioritize generating analysis results during a specific event period and provide information related to the event. For example, the generation unit obtains analysis results during the event period from a database and generates them. The generation unit can also prioritize generating analysis results within a period specified by the user and provide necessary information quickly. For example, the generation unit obtains analysis results within a period specified by the user from a database and generates them. This makes it possible to determine the generation priority based on the submission time of the analysis results.

[0050] When generating a dataset, the generation unit can adjust the order of generation based on the relevance of the analysis results. For example, the generation unit prioritizes the generation of highly relevant analysis results to provide useful information to the user. For example, the generation unit obtains the relevance of the analysis results from a database and identifies highly relevant analysis results. The generation unit can also postpone less relevant analysis results and provide important information quickly. For example, the generation unit evaluates the relevance of the analysis results and postpones less relevant analysis results. The generation unit can also appropriately allocate generation resources according to the relevance of the analysis results to perform efficient generation. For example, the generation unit allocates more resources to more relevant analysis results. This makes it possible to adjust the order of generation based on the relevance of the analysis results.

[0051] When generating a dataset, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates the dataset using detailed technical terminology. For example, the generation unit evaluates the user's level of expertise from survey results and uses technical terminology. Furthermore, if the user does not have technical expertise, the generation unit can generate the dataset using simple and easy-to-understand language. For example, the generation unit analyzes the user's past posts and evaluates the level of expertise. Furthermore, the generation unit can adjust the way the dataset is expressed according to the user's level of expertise to provide information that is easy to understand. For example, the generation unit provides definitions of technical terms and uses simple expressions. This makes it possible to generate a dataset according to the user's level of expertise.

[0052] The recommendation unit can adjust the level of detail of the recommendation based on the importance of the posted content when making a recommendation. For example, the recommendation unit makes a detailed recommendation for highly important posted content and provides deep insight. For example, the recommendation unit evaluates the influence of the posted content and identifies its importance. The recommendation unit can also make a concise recommendation and provide basic information for less important posted content. For example, the recommendation unit evaluates the urgency of the posted content and identifies its importance. The recommendation unit can also appropriately allocate recommendation resources according to the importance of the posted content and make efficient recommendations. For example, the recommendation unit allocates more resources to highly important posted content. This makes it possible to adjust the level of detail of the recommendation based on the importance of the posted content.

[0053] When making recommendations, the recommendation unit can apply different recommendation algorithms depending on the category of the post content. For example, the recommendation unit applies an image analysis algorithm to travel-related posts to extract features of travel destinations. For example, the recommendation unit analyzes travel-related posts using image analysis technology to identify features of travel destinations. The recommendation unit can also apply a text analysis algorithm to cooking-related posts to extract recipe details. For example, the recommendation unit analyzes cooking-related posts using natural language processing technology to identify recipe details. The recommendation unit can also apply a video analysis algorithm to event-related posts to extract event highlights. For example, the recommendation unit analyzes event-related posts using video analysis technology to identify event highlights. This makes it possible to apply different recommendation algorithms depending on the category of the post content.

[0054] The recommendation unit can improve the accuracy of recommendations by referring to the user's past recommendation results when making recommendations. The recommendation unit can improve the accuracy of recommendations of similar content, for example, based on content that has been recommended to the user in the past. For example, the recommendation unit can obtain the user's past recommendation results from a database and optimize the recommendation algorithm. The recommendation unit can also analyze the user's past recommendation results and optimize the recommendation algorithm. For example, the recommendation unit can analyze the user's past recommendation results and adjust the algorithm parameters. The recommendation unit can also adjust the recommendation parameters by referring to the user's past recommendation results to improve accuracy. For example, the recommendation unit can adjust the recommendation parameters based on the user's past recommendation results. This makes it possible to improve the accuracy of recommendations by referring to the user's past recommendation results.

[0055] When making a recommendation, the recommendation unit can determine the priority of recommendations based on the time when the posted content was submitted. The recommendation unit, for example, prioritizes recommending the most recent posted content and provides information in real time. For example, the recommendation unit retrieves the submission date and time of the posted content from a database and identifies the most recent post. The recommendation unit can also prioritize recommending content posted during a specific event period and provide information related to the event. For example, the recommendation unit retrieves and recommends content posted during the event period from a database. The recommendation unit can also prioritize recommending content posted within a period specified by the user and provide necessary information quickly. For example, the recommendation unit retrieves and recommends content posted within a period specified by the user from a database. This makes it possible to determine the priority of recommendations based on the time when the posted content was submitted.

[0056] The recommendation unit can adjust the order of recommendations based on the relevance of the posted content when making recommendations. For example, the recommendation unit prioritizes recommending highly relevant posted content and provides useful information to the user. For example, the recommendation unit obtains the relevance of the posted content from a database and identifies highly relevant posts. The recommendation unit can also postpone less relevant posted content and provide important information quickly. For example, the recommendation unit evaluates the relevance of the posted content and postpones less relevant posts. The recommendation unit can also appropriately allocate recommendation resources according to the relevance of the posted content and make efficient recommendations. For example, the recommendation unit allocates more resources to more relevant posted content. This makes it possible to adjust the order of recommendations based on the relevance of the posted content.

[0057] The recommendation unit may adjust the use of technical terminology in the recommendation according to the user's level of expertise when making a recommendation. For example, if the user has technical expertise, the recommendation unit may provide the recommendation content using detailed technical terminology. For example, the recommendation unit may evaluate the user's level of expertise from a survey result and use technical terminology. Furthermore, if the user does not have technical expertise, the recommendation unit may provide the recommendation content using simple and easy-to-understand language. For example, the recommendation unit may analyze the user's past posts and evaluate the user's level of expertise. Furthermore, the recommendation unit may adjust the way the recommendation content is expressed according to the user's level of expertise and provide information that is easy to understand. For example, the recommendation unit may provide definitions of technical terms and use simple expressions. This allows the recommendation content to be provided according to the user's level of expertise.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The reception unit can automatically adjust the appropriate publication timing of a post based on the content of the user's post. For example, if the content posted by the user is related to a specific event or season, the reception unit will publish the post in accordance with the event or season. The reception unit can also analyze the time periods when the user's followers are active and publish the post at those time periods. Furthermore, the reception unit can estimate the most effective publication timing based on engagement data of the user's past posts and publish the post at that timing. This allows the user's posts to be seen by more people.

[0060] The generation unit can generate a customized dataset based on the content posted by the user. For example, the generation unit can generate a dataset of tourist spots and restaurants at travel destinations based on travel photos posted by the user. The generation unit can also generate a dataset of related ingredients and cooking methods based on cooking recipes posted by the user. Furthermore, the generation unit can generate a dataset of event highlights and participant feedback based on event videos posted by the user. This makes it possible to provide a customized dataset based on the content posted by the user.

[0061] The reception unit can automatically adjust the privacy settings of posts based on the content of the user's post. For example, if a user posts a post containing personal information, the reception unit can set the post to private. Alternatively, if a user posts a post containing general information, the reception unit can set the post to public. Furthermore, the reception unit can analyze the user's past privacy setting history and recommend optimal privacy settings. This makes it possible to set an appropriate level of visibility while protecting the user's privacy.

[0062] The generation unit can adjust the update frequency of the dataset based on the content posted by the user. For example, if the user posts frequently, the generation unit updates the dataset in real time. Alternatively, if the user posts occasionally, the generation unit can update the dataset periodically. Furthermore, if the user posts related to a specific event or campaign, the generation unit can update the dataset intensively during the period of the event or campaign. This allows the dataset to be updated optimally according to the user's posting frequency.

[0063] The reception unit can automatically adjust the format of a post based on the content of the user's post. For example, if a user posts a long piece of text, the reception unit can summarize and shorten the text. Also, if a user posts multiple images, the reception unit can group the images into a single album. Furthermore, if a user posts a video, the reception unit can automatically generate thumbnails for the video and display them in a visually appealing format. This makes it possible to provide the optimal format for the content of the user's post.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The reception unit receives content such as text, images, videos, etc. posted by users. For example, the reception unit can receive each of the text, images, and videos posted by users. Step 2: The analysis unit uses the generation AI to analyze the content of the posts received by the reception unit and classify them into specific themes or categories. For example, the analysis unit analyzes the text, images, and videos posted by users and classifies them into specific themes or categories. Step 3: The generation unit generates an open dataset based on the content analyzed by the analysis unit. For example, the generation unit generates an open dataset based on the text data, image data, and video data analyzed by the analysis unit. Step 4: The recommendation unit recommends related content based on the dataset generated by the generation unit. For example, the recommendation unit uses a generation AI to recommend content related to the text, images, and videos posted by the user.

[0066] (Example 2) A social networking service (SNS) service according to an embodiment of the present invention is a system that uses generative AI technology to analyze content posted by users and automatically generate an open dataset. This SNS service accepts content posted by users, such as text, images, and videos, and the generative AI analyzes the posted content and classifies it into specific themes or categories. For example, when a user posts travel photos, the generative AI analyzes the photos and adds them to a travel-related dataset. This dataset is made public as an open dataset that researchers and developers can freely use. Furthermore, the generative AI also analyzes user posts and automatically recommends related content. For example, when a user posts a recipe for a specific dish, the generative AI recommends other recipes and photos of dishes related to the recipe. This allows users to easily find content that matches their interests. By utilizing generative AI technology, SNS services can efficiently analyze user-posted content, automatically generate open datasets, and recommend content that matches users' interests, improving the user experience. This is expected to significantly contribute to the spread of AI services, including generative AI.

[0067] An SNS service according to an embodiment includes a reception unit, an analysis unit, a generation unit, and a recommendation unit. The reception unit receives content such as text, images, and videos posted by users. For example, the reception unit can receive text posted by users. The reception unit can also receive images posted by users. The reception unit can also receive videos posted by users. The analysis unit uses a generation AI to analyze the content posted by the reception unit and classify it into specific themes or categories. For example, the analysis unit uses a generation AI to analyze text posted by users and classify it into specific themes. The analysis unit can also use a generation AI to analyze images posted by users and classify them into specific categories. The analysis unit can also use a generation AI to analyze videos posted by users and classify them into specific themes. The generation unit generates an open dataset based on the content analyzed by the analysis unit. For example, the generation unit generates an open dataset based on text data analyzed by the analysis unit. The generation unit can also generate an open dataset based on image data analyzed by the analysis unit. The generation unit can also generate an open dataset based on the video data analyzed by the analysis unit. The recommendation unit recommends related content based on the dataset generated by the generation unit. For example, the recommendation unit uses the generation AI to recommend content related to text posted by a user. The recommendation unit can also use the generation AI to recommend content related to an image posted by a user. The recommendation unit can also use the generation AI to recommend content related to a video posted by a user. This allows the SNS service according to the embodiment to efficiently analyze user posts, generate a dataset, and recommend related content.

[0068] The reception unit can receive text, image, and video content posted by users. The reception unit, for example, receives text posted by users. For example, the reception unit can receive text posted by users with a character limit. The reception unit can also receive images posted by users. For example, the reception unit can receive images posted by users in JPEG format. The reception unit can also receive videos posted by users. For example, the reception unit can receive videos posted by users in high resolution. This allows users to post content in various formats.

[0069] The analysis unit can use the generation AI to analyze the posted content and classify it into specific themes or categories. For example, the analysis unit can use the generation AI to analyze text posted by users and classify it into specific themes. For example, the analysis unit can use the generation AI to analyze text posted by users using natural language processing technology and classify it into themes such as news, entertainment, and technology. The analysis unit can also use the generation AI to analyze images posted by users and classify them into specific categories. For example, the analysis unit can use the generation AI to analyze images posted by users using image analysis technology and classify them into categories such as travel, cooking, and events. The analysis unit can also use the generation AI to analyze videos posted by users and classify them into specific themes. For example, the analysis unit can use the generation AI to analyze videos posted by users using video analysis technology and classify them into themes such as news, entertainment, and technology. This allows the posted content to be efficiently analyzed and classified.

[0070] The generation unit can generate an open dataset based on the analysis results. The generation unit generates the open dataset based on, for example, text data analyzed by the analysis unit. For example, the generation unit generates the text data analyzed by the analysis unit as an open dataset in CSV format. The generation unit can also generate the open dataset based on image data analyzed by the analysis unit. For example, the generation unit generates the image data analyzed by the analysis unit as an open dataset in JPEG format. The generation unit can also generate the open dataset based on video data analyzed by the analysis unit. For example, the generation unit generates the video data analyzed by the analysis unit as an open dataset in MP4 format. This makes it possible to generate a dataset based on the analysis results.

[0071] The recommendation unit can use the generation AI to recommend content related to the content posted by the user. For example, the recommendation unit uses the generation AI to recommend content related to text posted by the user. For example, the recommendation unit uses the generation AI to recommend other text content related to the text posted by the user. The recommendation unit can also use the generation AI to recommend content related to images posted by the user. For example, the recommendation unit uses the generation AI to recommend other image content related to images posted by the user. The recommendation unit can also use the generation AI to recommend content related to videos posted by the user. For example, the recommendation unit uses the generation AI to recommend other video content related to the video posted by the user. This makes it possible to automatically recommend content related to the content posted by the user.

[0072] The reception unit can estimate the user's emotions and adjust the timing of post acceptance based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit temporarily delays the acceptance of posts to allow the user to post in a relaxed state. For example, the reception unit captures the user's facial expression with a camera and estimates stress using an emotion estimation algorithm. Furthermore, if the user is excited, the reception unit can immediately accept posts to encourage posting when emotions are high. For example, the reception unit records the user's voice and estimates excitement using voice analysis technology. Furthermore, if the user is tired, the reception unit can simplify the acceptance of posts to allow posts to be posted in a shorter time. For example, the reception unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates fatigue using an emotion estimation algorithm. This allows the timing of post acceptance to be adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0073] The reception unit can analyze the user's past posting history and select an appropriate reception method. For example, the reception unit analyzes the time periods in which the user frequently posted in the past and sends a notification encouraging the user to post during those time periods. For example, the reception unit retrieves the user's past posting history from a database and identifies the time periods in which the user frequently posted. The reception unit can also preferentially suggest posting formats (text, image, video, etc.) that the user has used in the past. For example, the reception unit analyzes the user's past posting history and identifies the most frequently used posting format. The reception unit can also analyze the content of the user's past posts and automatically suggest related themes and categories. For example, the reception unit analyzes the content of the user's past posts using natural language processing technology and identifies related themes and categories. This makes it possible to select the optimal reception method based on the user's past posting history.

[0074] The reception unit can filter posts based on the user's current areas of interest when receiving the posts. For example, the reception unit preferentially receives only posts related to topics that the user has recently been interested in. For example, the reception unit can analyze the user's past browsing history and identify topics that the user has recently been interested in. The reception unit can also analyze the content of posts from accounts the user follows and preferentially receive related posts. For example, the reception unit can retrieve the content of posts from accounts the user follows from a database and identify related posts. The reception unit can also filter and receive related posts based on keywords recently searched by the user. For example, the reception unit can analyze the user's search history and identify related keywords. This makes it possible to filter posts based on the user's areas of interest.

[0075] When accepting a post, the acceptance unit can select the optimal acceptance means depending on the user's input method. For example, if the user selects voice input, the acceptance unit converts the voice into text using voice recognition technology and accepts the post. For example, the acceptance unit records the user's voice with a microphone and converts it into text using voice recognition software. Furthermore, when the user posts an image, the acceptance unit can analyze the content using image analysis technology and classify it into an appropriate category before accepting the post. For example, the acceptance unit analyzes the image posted by the user using image analysis software and classifies it into a category. Furthermore, when the user posts a video, the acceptance unit can analyze the content using video analysis technology and add it to an appropriate dataset before accepting the post. For example, the acceptance unit analyzes the video posted by the user using video analysis software and adds it to a dataset. This makes it possible to select the optimal acceptance means depending on the user's input method.

[0076] The reception unit can estimate the user's emotions and determine the priority of posts to be received based on the estimated user emotions. For example, if the user is excited, the reception unit can prioritize the reception of the user's posts and share them with other users quickly. For example, the reception unit can capture the user's facial expression with a camera and estimate the user's excitement using an emotion estimation algorithm. If the user is calm, the reception unit can also review the content of the post in detail and classify it into an appropriate category before receiving it. For example, the reception unit can record the user's voice and estimate the user's calmness using voice analysis technology. If the user is feeling stressed, the reception unit can temporarily hold the post and review and receive it again later. For example, the reception unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the user's stress using an emotion estimation algorithm. This allows the priority of posts to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0077] When accepting posts, the reception unit can prioritize accepting posts that are highly relevant by taking into account the user's geographical location information. For example, if the user is in a specific area, the reception unit prioritizes accepting posts related to that area. For example, the reception unit acquires the user's GPS data and identifies the user's current location. Furthermore, if the user is traveling, the reception unit can prioritize accepting posts related to the user's travel destination. For example, the reception unit analyzes the user's IP address and identifies the user's travel destination. Furthermore, if the user is at an event venue, the reception unit can prioritize accepting posts related to the event. For example, the reception unit acquires the user's location information in real time and identifies the event venue. This allows posts that are highly relevant to be accepted preferentially based on the user's geographical location information.

[0078] The reception unit can analyze the user's social media activity when receiving a post and receive related posts. The reception unit, for example, analyzes content shared by the user on social media and preferentially receives related posts. For example, the reception unit acquires and analyzes content shared from the user's social media account. The reception unit can also analyze content posted by accounts the user follows on social media and preferentially receive related posts. For example, the reception unit acquires and analyzes content posted by accounts the user follows from a database. The reception unit can also analyze activity content of groups the user participates in on social media and preferentially receive related posts. For example, the reception unit acquires and analyzes activity content of groups the user participates in from a database. This makes it possible to receive related posts based on the user's social media activity.

[0079] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a post. For example, the reception unit analyzes feedback on content previously posted by the user and preferentially receives posts with similar content. For example, the reception unit acquires and analyzes rating comments on the user's past posts from a database. The reception unit can also preferentially receive posts with high ratings based on the ratings on content previously posted by the user. For example, the reception unit acquires and analyzes star ratings on the user's past posts from a database. The reception unit can also analyze comments on content previously posted by the user and preferentially receive related posts. For example, the reception unit acquires and analyzes comments on the user's past posts from a database. This makes it possible to customize the reception method based on the user's past feedback.

[0080] The analysis unit can estimate the user's emotions and adjust the presentation of the analysis based on the estimated user emotions. For example, if the user is relaxed, the analysis unit provides detailed analysis results to attract the user's interest. For example, the analysis unit captures the user's facial expressions with a camera and estimates relaxation using an emotion estimation algorithm. If the user is in a hurry, the analysis unit can provide concise analysis results to enable the user to quickly obtain information. For example, the analysis unit records the user's voice and estimates that the user is in a hurry using voice analysis technology. If the user is excited, the analysis unit can provide visually appealing analysis results to attract the user's attention. For example, the analysis unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates excitement using an emotion estimation algorithm. This allows the presentation of the analysis to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0081] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the posted content. For example, the analysis unit performs a detailed analysis on posted content with a high level of importance to provide deep insight. For example, the analysis unit evaluates the influence of the posted content and identifies its importance. The analysis unit can also perform a concise analysis on posted content with a low level of importance to provide basic information. For example, the analysis unit evaluates the urgency of the posted content and identifies its importance. The analysis unit can also appropriately allocate analysis resources according to the importance of the posted content to perform efficient analysis. For example, the analysis unit allocates more resources to posted content with a high level of importance. This makes it possible to adjust the level of detail of the analysis based on the importance of the posted content.

[0082] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the post content. For example, the analysis unit applies an image analysis algorithm to travel-related posts to extract features of travel destinations. For example, the analysis unit analyzes travel-related posts using image analysis technology to identify features of travel destinations. The analysis unit can also apply a text analysis algorithm to cooking-related posts to extract recipe details. For example, the analysis unit analyzes cooking-related posts using natural language processing technology to identify recipe details. The analysis unit can also apply a video analysis algorithm to event-related posts to extract event highlights. For example, the analysis unit analyzes event-related posts using video analysis technology to identify event highlights. This makes it possible to apply different analysis algorithms depending on the category of the post content.

[0083] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit improves the analysis accuracy of posts with similar content based on the analysis results of content posted by the user in the past. For example, the analysis unit obtains the user's past analysis results from a database and optimizes the analysis algorithm. The analysis unit can also analyze the user's past analysis results and optimize the analysis algorithm. For example, the analysis unit analyzes the user's past analysis results and adjusts the parameters of the algorithm. The analysis unit can also adjust the analysis parameters by referring to the user's past analysis results to improve accuracy. For example, the analysis unit adjusts the analysis parameters based on the user's past analysis results. In this way, the analysis accuracy can be improved by referring to the user's past analysis results.

[0084] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit provides a short and concise analysis result. For example, the analysis unit captures the user's facial expression with a camera and estimates that the user is in a hurry using an emotion estimation algorithm. Furthermore, if the user is relaxed, the analysis unit can provide a detailed analysis result to attract the user's interest. For example, the analysis unit records the user's voice and estimates relaxation using voice analysis technology. Furthermore, if the user is excited, the analysis unit can provide a visually appealing analysis result to attract the user's attention. For example, the analysis unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates excitement using an emotion estimation algorithm. This allows the length of the analysis to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0085] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the posted content. The analysis unit, for example, prioritizes analysis of the most recent posted content and provides information in real time. For example, the analysis unit retrieves the submission date and time of the posted content from a database and identifies the most recent post. The analysis unit can also prioritize analysis of posted content during a specific event period and provide information related to the event. For example, the analysis unit retrieves and analyzes posted content during the event period from a database. The analysis unit can also prioritize analysis of posted content within a period specified by the user and provide necessary information quickly. For example, the analysis unit retrieves and analyzes posted content within a period specified by the user from a database. This makes it possible to determine the priority of analysis based on the submission time of the posted content.

[0086] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the posted content. For example, the analysis unit prioritizes analysis of highly relevant posted content and provides useful information to the user. For example, the analysis unit obtains the relevance of the posted content from a database and identifies highly relevant posts. The analysis unit can also postpone less relevant posted content and provide important information quickly. For example, the analysis unit evaluates the relevance of the posted content and postpones less relevant posts. The analysis unit can also appropriately allocate analysis resources according to the relevance of the posted content and perform efficient analysis. For example, the analysis unit allocates more resources to more relevant posted content. This makes it possible to adjust the order of analysis based on the relevance of the posted content.

[0087] During analysis, the analysis unit can adjust the use of technical terminology in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides the analysis results using detailed technical terminology. For example, the analysis unit evaluates the user's level of expertise from survey results and uses technical terminology. Furthermore, if the user does not have technical expertise, the analysis unit can provide the analysis results using simple and easy-to-understand language. For example, the analysis unit analyzes the user's past posts and evaluates the level of expertise. Furthermore, the analysis unit can adjust the way the analysis results are expressed according to the user's level of expertise and provide information that is easy to understand. For example, the analysis unit provides definitions of technical terms and uses simple expressions. This makes it possible to provide analysis results according to the user's level of expertise.

[0088] The generation unit can estimate the user's emotions and adjust the method of dataset generation based on the estimated user emotions. For example, if the user is relaxed, the generation unit generates a detailed dataset to interest the user. For example, the generation unit captures the user's facial expressions with a camera and estimates relaxation using an emotion estimation algorithm. If the user is in a hurry, the generation unit can generate a concise dataset to enable the user to quickly obtain information. For example, the generation unit records the user's voice and estimates that the user is in a hurry using voice analysis technology. If the user is excited, the generation unit can generate a visually appealing dataset to attract the user's attention. For example, the generation unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates excitement using an emotion estimation algorithm. This allows the method of dataset generation to be adjusted based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] When generating a dataset, the generation unit can adjust the level of detail of the generation based on the importance of the analysis result. For example, the generation unit generates a detailed dataset for analysis results with high importance to provide deep insight. For example, the generation unit evaluates the impact of the analysis result and identifies its importance. The generation unit can also generate a concise dataset for analysis results with low importance to provide basic information. For example, the generation unit evaluates the urgency of the analysis result and identifies its importance. The generation unit can also appropriately allocate resources for dataset generation according to the importance of the analysis result to perform efficient generation. For example, the generation unit allocates more resources to analysis results with high importance. This makes it possible to adjust the level of detail of dataset generation based on the importance of the analysis result.

[0090] When generating a dataset, the generation unit can apply different generation algorithms depending on the category of the analysis results. For example, the generation unit applies an image analysis algorithm to analysis results related to travel to extract features of travel destinations. For example, the generation unit analyzes the analysis results related to travel using image analysis technology to identify features of travel destinations. The generation unit can also apply a text analysis algorithm to analysis results related to cooking to extract recipe details. For example, the generation unit analyzes the analysis results related to cooking using natural language processing technology to identify recipe details. The generation unit can also apply a video analysis algorithm to analysis results related to events to extract event highlights. For example, the generation unit analyzes the analysis results related to events using video analysis technology to identify event highlights. This makes it possible to apply different generation algorithms depending on the category of the analysis results.

[0091] When generating a dataset, the generation unit can improve the accuracy of generation by referring to the user's past generation results. The generation unit, for example, improves the accuracy of generation of a dataset with similar content based on a dataset previously generated by the user. For example, the generation unit obtains the user's past generation results from a database and optimizes the generation algorithm. The generation unit can also analyze the user's past generation results and optimize the generation algorithm. For example, the generation unit analyzes the user's past generation results and adjusts the parameters of the algorithm. The generation unit can also adjust the generation parameters by referring to the user's past generation results to improve accuracy. For example, the generation unit adjusts the generation parameters based on the user's past generation results. This makes it possible to improve the accuracy of generation by referring to the user's past generation results.

[0092] The generation unit can estimate the user's emotions and prioritize the datasets to be generated based on the estimated user emotions. For example, if the user is excited, the generation unit prioritizes generating that dataset and sharing it with other users quickly. For example, the generation unit captures the user's facial expression with a camera and estimates the user's excitement using an emotion estimation algorithm. If the user is calm, the generation unit can also review the contents of the dataset in detail and generate it by classifying it into an appropriate category. For example, the generation unit records the user's voice and estimates the user's calmness using voice analysis technology. If the user is feeling stressed, the generation unit can temporarily hold the dataset and review and generate it again later. For example, the generation unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's stress using an emotion estimation algorithm. This allows the priority of datasets to be determined based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] When generating a dataset, the generation unit can determine the generation priority based on the submission time of the analysis results. The generation unit, for example, prioritizes generating the latest analysis results and provides information in real time. For example, the generation unit obtains the submission date and time of the analysis results from a database and identifies the latest analysis results. The generation unit can also prioritize generating analysis results during a specific event period and provide information related to the event. For example, the generation unit obtains analysis results during the event period from a database and generates them. The generation unit can also prioritize generating analysis results within a period specified by the user and provide necessary information quickly. For example, the generation unit obtains analysis results within a period specified by the user from a database and generates them. This makes it possible to determine the generation priority based on the submission time of the analysis results.

[0094] When generating a dataset, the generation unit can adjust the order of generation based on the relevance of the analysis results. For example, the generation unit prioritizes the generation of highly relevant analysis results to provide useful information to the user. For example, the generation unit obtains the relevance of the analysis results from a database and identifies highly relevant analysis results. The generation unit can also postpone less relevant analysis results and provide important information quickly. For example, the generation unit evaluates the relevance of the analysis results and postpones less relevant analysis results. The generation unit can also appropriately allocate generation resources according to the relevance of the analysis results to perform efficient generation. For example, the generation unit allocates more resources to more relevant analysis results. This makes it possible to adjust the order of generation based on the relevance of the analysis results.

[0095] When generating a dataset, the generation unit can adjust the use of technical terminology in the generation according to the user's level of expertise. For example, if the user has technical expertise, the generation unit generates the dataset using detailed technical terminology. For example, the generation unit evaluates the user's level of expertise from survey results and uses technical terminology. Furthermore, if the user does not have technical expertise, the generation unit can generate the dataset using simple and easy-to-understand language. For example, the generation unit analyzes the user's past posts and evaluates the level of expertise. Furthermore, the generation unit can adjust the way the dataset is expressed according to the user's level of expertise to provide information that is easy to understand. For example, the generation unit provides definitions of technical terms and uses simple expressions. This makes it possible to generate a dataset according to the user's level of expertise.

[0096] The recommendation unit can estimate the user's emotions and adjust the way recommendations are presented based on the estimated user emotions. For example, if the user is relaxed, the recommendation unit provides detailed recommendations to pique the user's interest. For example, the recommendation unit captures the user's facial expressions with a camera and estimates relaxation using an emotion estimation algorithm. If the user is in a hurry, the recommendation unit can provide concise recommendations to enable the user to quickly obtain information. For example, the recommendation unit records the user's voice and estimates that the user is in a hurry using voice analysis technology. If the user is excited, the recommendation unit can provide visually appealing recommendations to attract the user's attention. For example, the recommendation unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates excitement using an emotion estimation algorithm. This allows the way recommendations are presented to be adjusted 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, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The recommendation unit can adjust the level of detail of the recommendation based on the importance of the posted content when making a recommendation. For example, the recommendation unit makes a detailed recommendation for highly important posted content and provides deep insight. For example, the recommendation unit evaluates the influence of the posted content and identifies its importance. The recommendation unit can also make a concise recommendation and provide basic information for less important posted content. For example, the recommendation unit evaluates the urgency of the posted content and identifies its importance. The recommendation unit can also appropriately allocate recommendation resources according to the importance of the posted content and make efficient recommendations. For example, the recommendation unit allocates more resources to highly important posted content. This makes it possible to adjust the level of detail of the recommendation based on the importance of the posted content.

[0098] When making recommendations, the recommendation unit can apply different recommendation algorithms depending on the category of the post content. For example, the recommendation unit applies an image analysis algorithm to travel-related posts to extract features of travel destinations. For example, the recommendation unit analyzes travel-related posts using image analysis technology to identify features of travel destinations. The recommendation unit can also apply a text analysis algorithm to cooking-related posts to extract recipe details. For example, the recommendation unit analyzes cooking-related posts using natural language processing technology to identify recipe details. The recommendation unit can also apply a video analysis algorithm to event-related posts to extract event highlights. For example, the recommendation unit analyzes event-related posts using video analysis technology to identify event highlights. This makes it possible to apply different recommendation algorithms depending on the category of the post content.

[0099] The recommendation unit can improve the accuracy of recommendations by referring to the user's past recommendation results when making recommendations. The recommendation unit can improve the accuracy of recommendations of similar content, for example, based on content that has been recommended to the user in the past. For example, the recommendation unit can obtain the user's past recommendation results from a database and optimize the recommendation algorithm. The recommendation unit can also analyze the user's past recommendation results and optimize the recommendation algorithm. For example, the recommendation unit can analyze the user's past recommendation results and adjust the algorithm parameters. The recommendation unit can also adjust the recommendation parameters by referring to the user's past recommendation results to improve accuracy. For example, the recommendation unit can adjust the recommendation parameters based on the user's past recommendation results. This makes it possible to improve the accuracy of recommendations by referring to the user's past recommendation results.

[0100] The recommendation unit can estimate the user's emotions and adjust the length of the recommendation based on the estimated user emotions. For example, if the user is in a hurry, the recommendation unit provides short and to-the-point recommendations. For example, the recommendation unit captures the user's facial expressions with a camera and estimates that the user is in a hurry using an emotion estimation algorithm. Furthermore, if the user is relaxed, the recommendation unit can provide detailed recommendations to pique the user's interest. For example, the recommendation unit records the user's voice and estimates that the user is relaxed using voice analysis technology. Furthermore, if the user is excited, the recommendation unit can provide visually appealing recommendations to attract the user's attention. For example, the recommendation unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates that the user is excited using an emotion estimation algorithm. This allows the length of the recommendation to be adjusted 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, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] When making a recommendation, the recommendation unit can determine the priority of recommendations based on the time when the posted content was submitted. The recommendation unit, for example, prioritizes recommending the most recent posted content and provides information in real time. For example, the recommendation unit retrieves the submission date and time of the posted content from a database and identifies the most recent post. The recommendation unit can also prioritize recommending content posted during a specific event period and provide information related to the event. For example, the recommendation unit retrieves and recommends content posted during the event period from a database. The recommendation unit can also prioritize recommending content posted within a period specified by the user and provide necessary information quickly. For example, the recommendation unit retrieves and recommends content posted within a period specified by the user from a database. This makes it possible to determine the priority of recommendations based on the time when the posted content was submitted.

[0102] The recommendation unit can adjust the order of recommendations based on the relevance of the posted content when making recommendations. For example, the recommendation unit prioritizes recommending highly relevant posted content and provides useful information to the user. For example, the recommendation unit obtains the relevance of the posted content from a database and identifies highly relevant posts. The recommendation unit can also postpone less relevant posted content and provide important information quickly. For example, the recommendation unit evaluates the relevance of the posted content and postpones less relevant posts. The recommendation unit can also appropriately allocate recommendation resources according to the relevance of the posted content and make efficient recommendations. For example, the recommendation unit allocates more resources to more relevant posted content. This makes it possible to adjust the order of recommendations based on the relevance of the posted content.

[0103] The recommendation unit may adjust the use of technical terminology in the recommendation according to the user's level of expertise when making a recommendation. For example, if the user has technical expertise, the recommendation unit may provide the recommendation content using detailed technical terminology. For example, the recommendation unit may evaluate the user's level of expertise from a survey result and use technical terminology. Furthermore, if the user does not have technical expertise, the recommendation unit may provide the recommendation content using simple and easy-to-understand language. For example, the recommendation unit may analyze the user's past posts and evaluate the user's level of expertise. Furthermore, the recommendation unit may adjust the way the recommendation content is expressed according to the user's level of expertise and provide information that is easy to understand. For example, the recommendation unit may provide definitions of technical terms and use simple expressions. This allows the recommendation content to be provided according to the user's level of expertise. === Hard Collateral 1-1 === Each of the multiple elements including the above-described reception unit, analysis unit, generation unit, and recommendation 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 receives content such as text, images, and videos posted by users. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the posted content using a generation AI and classifies the content into specific themes or categories. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an open dataset based on the analyzed content. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends related content based on the generated dataset. === Hard Collateral 1-2 === Each of the multiple elements including the above-described reception unit, analysis unit, generation unit, and recommendation 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 of the smart glasses 214 and receives content such as text, images, and videos posted by users. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the posted content using a generation AI and classifies it into specific themes or categories. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an open dataset based on the analyzed content. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends related content based on the generated dataset. === Hard Collateral 1-3 === Each of the multiple elements including the above-described reception unit, analysis unit, generation unit, and recommendation 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 of the headset-type terminal 314 and receives content such as text, images, and videos posted by users. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the posted content using a generation AI and classifies it into specific themes or categories. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an open dataset based on the analyzed content. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends related content based on the generated dataset. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, generation unit, and recommendation 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 of the robot 414 and receives content such as text, images, and videos posted by users. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the posted content using a generation AI and classifies it into specific themes or categories. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates an open dataset based on the analyzed content. The recommendation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and recommends related content based on the generated dataset.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The reception unit can automatically adjust the appropriate publication timing of a post based on the content of the user's post. For example, if the content posted by the user is related to a specific event or season, the reception unit will publish the post in accordance with the event or season. The reception unit can also analyze the time periods when the user's followers are active and publish the post at those time periods. Furthermore, the reception unit can estimate the most effective publication timing based on engagement data of the user's past posts and publish the post at that timing. This allows the user's posts to be seen by more people.

[0106] The analysis unit can analyze the emotional tone of a post based on the content of the user's post and provide feedback according to that tone. For example, the analysis unit can analyze the emotional tone of text posted by a user using natural language processing technology, and provide an encouraging message if the tone is positive. The analysis unit can also provide support or advice if the tone is negative. Furthermore, the analysis unit can provide information or reference materials if the tone is neutral. This makes it possible to provide appropriate feedback according to the user's emotions.

[0107] The generation unit can generate a customized dataset based on the content posted by the user. For example, the generation unit can generate a dataset of tourist spots and restaurants at travel destinations based on travel photos posted by the user. The generation unit can also generate a dataset of related ingredients and cooking methods based on cooking recipes posted by the user. Furthermore, the generation unit can generate a dataset of event highlights and participant feedback based on event videos posted by the user. This makes it possible to provide a customized dataset based on the content posted by the user.

[0108] The recommendation unit can estimate the user's emotions and adjust how content is recommended to the user based on the estimated emotions. For example, if the user is relaxed, the recommendation unit can provide detailed content to pique the user's interest. If the user is in a hurry, the recommendation unit can provide concise content to enable the user to quickly obtain information. Furthermore, if the user is excited, the recommendation unit can provide visually appealing content to attract the user's attention. This makes it possible to recommend optimal content according to the user's emotions.

[0109] The reception unit can automatically adjust the privacy settings of posts based on the content of the user's post. For example, if a user posts a post containing personal information, the reception unit can set the post to private. Alternatively, if a user posts a post containing general information, the reception unit can set the post to public. Furthermore, the reception unit can analyze the user's past privacy setting history and recommend optimal privacy settings. This makes it possible to set an appropriate level of visibility while protecting the user's privacy.

[0110] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results to interest the user. If the user is in a hurry, the analysis unit can provide concise analysis results to enable the user to obtain information quickly. Furthermore, if the user is excited, the analysis unit can provide visually appealing analysis results to attract the user's attention. In this way, it is possible to provide optimal analysis results according to the user's emotions.

[0111] The generation unit can adjust the update frequency of the dataset based on the content posted by the user. For example, if the user posts frequently, the generation unit updates the dataset in real time. Alternatively, if the user posts occasionally, the generation unit can update the dataset periodically. Furthermore, if the user posts related to a specific event or campaign, the generation unit can update the dataset intensively during the period of the event or campaign. This allows the dataset to be updated optimally according to the user's posting frequency.

[0112] The recommendation unit can estimate the user's emotions and adjust the type of content to be recommended based on the estimated emotions. For example, if the user is relaxed, the recommendation unit can recommend content related to entertainment or hobbies. If the user is in a hurry, the recommendation unit can recommend content related to news or breaking news. Furthermore, if the user is excited, the recommendation unit can recommend content related to action or adventure. This makes it possible to recommend optimal content according to the user's emotions.

[0113] The reception unit can automatically adjust the format of a post based on the content of the user's post. For example, if a user posts a long piece of text, the reception unit can summarize and shorten the text. Also, if a user posts multiple images, the reception unit can group the images into a single album. Furthermore, if a user posts a video, the reception unit can automatically generate thumbnails for the video and display them in a visually appealing format. This makes it possible to provide the optimal format for the content of the user's post.

[0114] The analysis unit can estimate the user's emotions and adjust the priority of analysis based on the estimated emotions. For example, if the user is excited, the analysis unit can prioritize analyzing the user's posts and provide results quickly. If the user is relaxed, the analysis unit can perform a detailed analysis and provide deeper insights. Furthermore, if the user is feeling stressed, the analysis unit can temporarily suspend the post and analyze it again later. This allows for optimal analysis according to the user's emotions.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The reception unit receives content such as text, images, videos, etc. posted by users. For example, the reception unit can receive each of the text, images, and videos posted by users. Step 2: The analysis unit uses the generation AI to analyze the content of the posts received by the reception unit and classify them into specific themes or categories. For example, the analysis unit analyzes the text, images, and videos posted by users and classifies them into specific themes or categories. Step 3: The generation unit generates an open dataset based on the content analyzed by the analysis unit. For example, the generation unit generates an open dataset based on the text data, image data, and video data analyzed by the analysis unit. Step 4: The recommendation unit recommends related content based on the dataset generated by the generation unit. For example, the recommendation unit uses a generation AI to recommend content related to the text, images, and videos posted by the user.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

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

[0151] 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.

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

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The 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.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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 unit that receives posts from users; an analysis unit that analyzes the posted content received by the reception unit; a generation unit that generates a data set based on the content analyzed by the analysis unit; a recommendation unit that recommends related content based on the dataset generated by the generation unit; Equipped with A system characterized by:

2. The reception unit Accepts user-submitted text, image, and video content 2. The system of claim 1.

3. The analysis unit Using generative AI to analyze posts and categorize them into specific themes and categories 2. The system of claim 1.

4. The generation unit Generate open datasets based on analysis results 2. The system of claim 1.

5. The recommendation unit Using generative AI to recommend content related to user posts 2. The system of claim 1.

6. The reception unit Estimate user emotions and adjust the timing of posting based on the estimated user emotions 2. The system of claim 1.

7. The reception unit Analyze the user's past posting history and select the appropriate reception method 2. The system of claim 1.

8. The reception unit As posts are accepted, they are filtered based on the user's current interests.

2. The system of claim 1.

Images