system

Abstract

The system according to this embodiment aims to efficiently manage and organize clipped articles and support the utilization of that information. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, an organization unit, a grouping unit, and a recommendation unit. The reception unit uploads clipped articles to the cloud. The analysis unit analyzes the articles uploaded by the reception unit and records basic information. The organization unit automatically organizes information files based on the basic information recorded by the analysis unit. The grouping unit groups the information files organized by the organization unit. The recommendation unit makes recommendations based on the information files grouped by the grouping unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is laborious to manage and organize clipped articles, and it is difficult to efficiently utilize information.

[0005] The system according to the embodiment aims to efficiently manage and organize clipped articles and support information utilization. <00OO029>

Means for Solving the Problems

[0007] The system according to this embodiment can efficiently manage and organize clipped articles and support the utilization of information. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The support AI system according to an embodiment of the present invention is a system that centrally manages clipped articles, records basic information, automatically organizes information files, groups them, and provides recommendations. This support AI system records necessary basic information, automatically organizes information files, groups them, and provides recommendations from an information utilization perspective (reminders for sharing and timing of use) simply by uploading clipped articles to the cloud. For example, a user uploads articles clipped from various media sources to a designated cloud. Next, the support AI analyzes the uploaded articles and automatically records the necessary basic information. For example, it extracts the article title, author, publication date, summary of content, keywords, etc. Then, the support AI automatically organizes the information files and groups related articles. For example, it groups articles on the same theme or topic. Furthermore, from an information utilization perspective, it provides reminders for sharing and timing of use. For example, it can remind users of relevant articles before a specific meeting or presentation. For corporate use, it is useful for sales pitches, creating prospect lists, preparing documents, and use in meetings. For example, sales representatives can be reminded of relevant articles to make more effective sales pitches to prospects. Also, when creating prospect lists, lists can be created based on relevant articles. For individuals, it can be useful for providing investment advice. For instance, an investor can clip articles about a specific stock, and the support AI analyzes those articles to provide investment advice. For example, it can remind users of the latest news and analysis articles on a specific stock. In this way, the support AI centrally manages clipped articles, records necessary basic information, automatically organizes information files, groups them, and provides recommendations from an information utilization perspective, thus providing effective support for both corporate and individual clients. This allows the support AI system to centrally manage clipped articles, record basic information, automatically organizes information files, groups them, and provides recommendations.

[0029] The support AI system according to this embodiment comprises a reception unit, an analysis unit, an organization unit, a grouping unit, and a recommendation unit. The reception unit uploads clipped articles to the cloud. Clipped articles include, but are not limited to, news articles, blog posts, and academic papers. The reception unit uploads articles to the cloud, for example, by having the user drag and drop the articles. The reception unit can also upload articles using a file selection dialog. Furthermore, the reception unit has a scheduled upload function, allowing it to automatically upload articles at a specific time. The analysis unit analyzes the uploaded articles and records basic information. Basic information includes, but is not limited to, the article title, author, publication date, summary of content, and keywords. The analysis unit analyzes the content of the articles and extracts basic information, for example, using natural language processing technology. The analysis unit can also extract important information from the articles using machine learning algorithms. The organization unit automatically organizes the information files based on the basic information recorded by the analysis unit. Methods of organization include, but are not limited to, alphabetical order, publication date order, and category order. The organization unit can, for example, sort article titles alphabetically. It can also organize articles by publication date. Furthermore, it can classify and organize articles by category. The grouping unit groups the information files organized by the organization unit. Criteria for grouping include, but are not limited to, theme, topic, and keyword similarity. The grouping unit can, for example, group articles on the same theme into one group. It can also group articles on the same topic into one group. Furthermore, it can group articles based on keyword similarity. The recommendation unit makes recommendations based on the information files grouped by the grouping unit. Methods of recommendation include, but are not limited to, the user's past behavior history, areas of interest, and article content.The recommendation unit can, for example, remind users of relevant articles before specific meetings or presentations. It can also recommend the most suitable articles based on the user's past browsing history. Furthermore, it can recommend articles based on the user's areas of interest. This allows the support AI system according to the embodiment to centrally manage clipped articles, record basic information, automatically organize and group information files, and perform recommendations.

[0030] The reception desk uploads clipped articles to the cloud. Clipped articles include, but are not limited to, news articles, blog posts, and academic papers. The reception desk uploads articles to the cloud, for example, by allowing users to drag and drop articles. It also allows users to upload articles using a file selection dialog. Furthermore, the reception desk has a scheduled upload function that allows articles to be automatically uploaded at a specific time. Specifically, when a user drags and drops an article, the reception desk detects the operation, verifies the file format and content of the article, and securely transfers it to cloud storage. When using the file selection dialog, users can select multiple files from their local disk and upload them at once. The scheduled upload function automatically uploads articles based on a time set by the user. For example, it can automatically detect new articles in a specific folder at 9:00 AM every day and upload them to the cloud. This function saves users the trouble of manually uploading. Furthermore, the reception desk automatically retrieves metadata of uploaded articles to facilitate management in the cloud. For example, it retrieves basic information such as file name, creation date and time, and file size, and records it in the cloud database. This allows users to easily search and manage uploaded articles.

[0031] The analysis unit analyzes uploaded articles and records basic information. This basic information includes, but is not limited to, the article title, author, publication date, summary, and keywords. The analysis unit can, for example, use natural language processing techniques to analyze the article content and extract basic information. It can also use machine learning algorithms to extract important information from articles. Specifically, it uses natural language processing techniques to analyze the article text and automatically extracts metadata such as the article title, author name, and publication date. Furthermore, it applies topic modeling and keyword extraction algorithms to summarize the article content and extract important keywords. For example, Latent Dirichlet Allocation (LDA) can be used to identify the article's topic and extract important keywords. By using machine learning algorithms, it becomes possible to extract important information from articles with high accuracy. For example, classification algorithms such as Support Vector Machines (SVM) and Random Forests can be used to classify the article content and identify important information. This allows the analysis unit to analyze the uploaded article content in detail and accurately record basic information. Furthermore, the analysis unit can select an appropriate analysis method depending on the language and format of the article when analyzing its content. For example, it can apply an English natural language processing model to English articles and a Japanese model to Japanese articles. This enables the analysis unit to handle multiple languages ​​and accurately analyze articles in various languages.

[0032] The organization unit automatically organizes information files based on the basic information recorded by the analysis unit. Organization methods include, but are not limited to, alphabetical order, publication date order, and category order. For example, the organization unit sorts article titles alphabetically. It can also sort articles by publication date. Furthermore, it can classify and organize articles by category. Specifically, it applies an algorithm to sort article titles alphabetically based on the basic information provided by the analysis unit. When sorting by publication date, articles can be sorted in ascending or descending order based on their publication date. When sorting by category, the organization unit automatically assigns appropriate categories based on the content and keywords of the articles. For example, news articles are classified into categories such as "Politics," "Economy," and "Sports," while academic papers are classified into categories such as "Physics," "Chemistry," and "Biology." The organization unit classifies articles based on these categories to make them easily accessible to users. Furthermore, the organization unit can flexibly change the organization method based on user custom settings. For example, if a user wants to organize articles based on specific keywords, the organization unit can filter and organize articles based on those keywords. This allows the organization unit to provide flexible organization methods tailored to user needs, thereby streamlining information management.

[0033] The grouping unit groups the information files organized by the organization unit. Grouping criteria include, but are not limited to, themes, topics, and keyword similarity. For example, the grouping unit can group articles on the same theme. It can also group articles on the same topic. Furthermore, the grouping unit can group articles based on keyword similarity. Specifically, it uses natural language processing techniques to analyze the content of articles and identify themes and topics. For example, it can use topic modeling techniques to extract the topics of articles and group articles on the same topic. When grouping based on keyword similarity, it vectorizes the keywords of the articles and calculates similarity using methods such as cosine similarity. By grouping articles with high similarity into the same group, highly relevant articles can be consolidated into a single group. Furthermore, the grouping unit can change the grouping criteria based on user custom settings. For example, if a user wants to group articles based on specific keywords, the unit can filter and group articles based on those keywords. This allows the grouping unit to provide flexible grouping methods tailored to user needs, thereby streamlining information management.

[0034] The recommendation unit makes recommendations based on information files grouped by the grouping unit. Recommendation methods include, but are not limited to, the user's past browsing history, areas of interest, and article content. For example, the recommendation unit might remind users of relevant articles before a specific meeting or presentation. It can also recommend the most relevant articles based on the user's past browsing history. Furthermore, it can recommend articles based on the user's areas of interest. Specifically, it analyzes the user's past browsing and search history to identify articles that are likely to interest the user. For example, it might use collaborative filtering technology to recommend articles based on their similarity to articles viewed by other users. It can also use content-based filtering technology to recommend articles based on their content and keywords. Additionally, the recommendation unit can modify its recommendation methods based on the user's custom settings. For example, if a user is interested in a particular topic, it can prioritize recommending articles related to that topic. This allows the recommendation system to provide flexible recommendation methods tailored to user needs, maximizing the utilization of information. Furthermore, the recommendation system can collect user feedback and continuously improve the accuracy of its recommendation algorithm. For example, it can provide a function that allows users to rate recommended articles and adjust the algorithm based on those ratings. This enables the recommendation system to provide users with more appropriate articles and maximize the value of the information.

[0035] The analysis unit can record the article's title, author, publication date, summary, and keywords. For example, the analysis unit can extract and record the article's title. For example, the analysis unit can analyze and record the article's title using natural language processing technology. The analysis unit can also extract and record the article's author. For example, the analysis unit can analyze and record the article's author's name. The analysis unit can also extract and record the article's publication date. For example, the analysis unit can analyze and record the article's publication date. The analysis unit can also summarize and record the article's content. For example, the analysis unit can summarize and record the article's content using natural language processing technology. The analysis unit can also extract and record the article's keywords. For example, the analysis unit can analyze and record the article's keywords using keyword extraction technology. This allows for detailed recording of the article's basic information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of an article into a generation AI and have the generation AI extract basic information.

[0036] The grouping unit can group articles related to the same theme or topic. For example, the grouping unit can group articles related to the same theme. For example, the grouping unit can analyze the theme of the articles using natural language processing technology and group articles related to the same theme. The grouping unit can also group articles related to the same topic. For example, the grouping unit can analyze the topic of the articles using a topic model and group articles related to the same topic. The grouping unit can also group articles based on keyword similarity. For example, the grouping unit can analyze the keywords of the articles using keyword extraction technology and group articles with highly similar keywords. This allows for efficient grouping of related articles. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the theme or topic of the articles into a generative AI and leave the grouping to the generative AI.

[0037] The recommendation unit can remind users of relevant articles before specific meetings or presentations. For example, the recommendation unit can remind users of relevant articles before specific meetings or presentations. For example, the recommendation unit can analyze meeting schedules and remind users of relevant articles. The recommendation unit can also analyze presentation content and remind users of relevant articles. For example, the recommendation unit can remind users of relevant articles based on the presentation theme. This allows the recommendation unit to provide relevant information before meetings or presentations. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or not using AI. For example, the recommendation unit can input meeting or presentation schedules into a generating AI and have the generating AI perform the task of reminding users of relevant articles.

[0038] The recommendation unit can make recommendations based on the user's past browsing history or the content of clipped articles. For example, the recommendation unit can make recommendations based on the user's past browsing history. For example, the recommendation unit can analyze the user's browsing history and recommend relevant articles. The recommendation unit can also analyze the user's click history and recommend relevant articles. Furthermore, the recommendation unit can analyze the user's search history and recommend relevant articles. For example, the recommendation unit can recommend relevant articles based on keywords the user has searched for in the past. The recommendation unit can also make recommendations based on the content of clipped articles. For example, the recommendation unit can analyze the content of clipped articles and recommend relevant articles. This allows the recommendation unit to provide optimal recommendations based on the user's browsing history. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation section can input the user's behavior history and the content of clipped articles into a generating AI, and then leave the execution of recommendations to the generating AI.

[0039] The recommendation unit can remind users of the latest news or analysis articles related to specific stocks. For example, the recommendation unit can remind users of the latest news related to specific stocks. For example, the recommendation unit can analyze news articles related to specific stocks and remind users of the latest news. The recommendation unit can also remind users of analysis articles related to specific stocks. For example, the recommendation unit can analyze analysis articles related to specific stocks and remind users of the latest analysis. This allows the recommendation unit to provide users with the latest information to help them make informed investment decisions. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input news or analysis articles related to specific stocks into a generating AI and leave the reminder execution to the generating AI.

[0040] The reception desk can analyze a user's past upload history and select an appropriate upload method. For example, the reception desk may prioritize suggesting upload methods that the user has frequently used in the past (e.g., drag and drop, file selection). For instance, the reception desk analyzes the user's past upload history and selects the optimal upload method. The reception desk can also send notifications prompting users to upload during specific time periods if they tend to upload at those times. For example, the reception desk analyzes the user's past upload times and sends notifications at the optimal time. Furthermore, if a user has previously failed to upload, the reception desk can analyze the cause and suggest solutions. For example, the reception desk analyzes the cause of the upload failure and suggests specific solutions to the user. This allows the reception desk to provide the optimal upload method based on the user's past history. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the user's upload history into a generating AI and have the generating AI select the optimal upload method.

[0041] The reception desk can filter articles based on the user's current areas of interest when they are uploaded. For example, the reception desk can prioritize uploading only articles related to topics the user has recently been interested in. For example, the reception desk can analyze the user's browsing and search history to identify their current areas of interest. The reception desk can also filter and display articles related to keywords if the user frequently searches for those keywords. For example, the reception desk can analyze the user's search keywords and filter related articles. The reception desk can also prioritize uploading articles related to a particular category if the user has shown interest in that category. For example, the reception desk can analyze the user's browsing history and filter articles related to that category. This allows the reception desk to upload the most relevant articles based on the user's areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the user's areas of interest into a generating AI and leave the filtering to the generating AI.

[0042] The reception desk can prioritize uploading articles that are highly relevant to the user based on their geographical location when an article is uploaded. For example, if the user is in a specific region, the reception desk will prioritize uploading news articles related to that region. For example, the reception desk will analyze the user's geographical location and identify relevant articles. The reception desk can also prioritize uploading tourist information and news articles related to the user's travel destination if the user is traveling. For example, the reception desk will analyze the user's geographical location and identify articles related to the travel destination. The reception desk can also prioritize uploading articles related to an event if the user is participating in a specific event. For example, the reception desk will analyze the user's geographical location and identify articles related to the event. This allows the reception desk to upload the most relevant articles based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's geographical location into a generating AI and have the generating AI identify relevant articles.

[0043] The reception desk can analyze a user's social media activity when uploading an article and upload relevant articles. For example, the reception desk can prioritize uploading new articles related to articles the user has shared on social media. For example, the reception desk can analyze the user's social media activity and identify relevant articles. The reception desk can also prioritize uploading articles related to topics the user follows on social media. For example, the reception desk can analyze the topics the user follows and identify relevant articles. The reception desk can also prioritize uploading articles related to groups and communities the user participates in on social media. For example, the reception desk can analyze the groups the user participates in and identify relevant articles. This allows the reception desk to upload the most suitable articles based on the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media activity into a generating AI and have the generating AI identify relevant articles.

[0044] The analysis unit can adjust the level of detail recorded based on the importance of the article during analysis. For example, the analysis unit can record detailed information for high-importance articles. For example, the analysis unit can evaluate the importance of the article and record detailed information. The analysis unit can also record only the main points for low-importance articles. For example, the analysis unit can evaluate the importance of the article and record only the main points. The analysis unit can also record information with an appropriate level of detail for articles of moderate importance. For example, the analysis unit can evaluate the importance of the article and record information with an appropriate level of detail. This allows information to be recorded with the optimal level of detail according to the importance of the article. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the article into a generating AI and have the generating AI adjust the level of detail of the recording.

[0045] The analysis unit can apply different analysis algorithms depending on the article category when analyzing an article. For example, the analysis unit can apply a news-specific analysis algorithm to news articles. For example, the analysis unit analyzes news articles and applies a news-specific algorithm. The analysis unit can also apply a detailed analysis algorithm to analytical articles. For example, the analysis unit analyzes analytical articles and applies a detailed algorithm. The analysis unit can also apply an analysis algorithm that emphasizes visual elements to entertainment articles. For example, the analysis unit analyzes entertainment articles and applies an algorithm that emphasizes visual elements. This allows for optimal analysis depending on the article category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the article category into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0046] The analysis unit can determine the priority of recording based on the publication date of the articles when analyzing them. For example, the analysis unit can prioritize recording the most recent articles. For example, the analysis unit can evaluate the publication date of the articles and prioritize recording the most recent articles. The analysis unit can also record only the main points for older articles. For example, the analysis unit can evaluate the publication date of the articles and record only the main points. The analysis unit can also record information with a moderate level of detail for articles of moderate recency. For example, the analysis unit can evaluate the publication date of the articles and record information with a moderate level of detail. This allows information to be recorded in the optimal order based on the publication date of the articles. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the publication date of the articles into a generating AI and have the generating AI determine the priority of recording.

[0047] The analysis unit can adjust the order of recording based on the relevance of the articles during analysis. For example, the analysis unit can prioritize recording highly relevant articles. For example, the analysis unit can evaluate the relevance of the articles and prioritize recording those with high relevance. The analysis unit can also record only the main points for less relevant articles. For example, the analysis unit can evaluate the relevance of the articles and record only the main points. The analysis unit can also record information with an appropriate level of detail for articles of moderate relevance. For example, the analysis unit can evaluate the relevance of the articles and record information with an appropriate level of detail. This allows information to be recorded in the optimal order based on the relevance of the articles. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the articles into a generating AI and have the generating AI adjust the order of recording.

[0048] The organization unit can adjust the level of detail in organizing information files based on the importance of each file. For example, the organization unit can perform detailed organization on files of high importance. For example, the organization unit can evaluate the importance of a file and perform detailed organization. The organization unit can also perform simplified organization on files of low importance. For example, the organization unit can evaluate the importance of a file and perform simplified organization. The organization unit can also organize files of medium importance with an appropriate level of detail. For example, the organization unit can evaluate the importance of a file and organize with an appropriate level of detail. This allows for organization with the optimal level of detail according to the importance of each file. Some or all of the above processes in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the importance of files into a generating AI and have the generating AI adjust the level of detail in the organization.

[0049] The organization unit can apply different organization algorithms depending on the file category when organizing information files. For example, the organization unit can apply a news-specific organization algorithm to news files. For example, the organization unit can analyze news files and apply a news-specific algorithm. The organization unit can also apply a detailed organization algorithm to analysis files. For example, the organization unit can analyze analysis files and apply a detailed algorithm. The organization unit can also apply an organization algorithm that emphasizes visual elements to entertainment files. For example, the organization unit can analyze entertainment files and apply an algorithm that emphasizes visual elements. This allows for optimal organization according to the file category. Some or all of the above processing in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the file categories into a generating AI and have the generating AI execute the application of the organization algorithm.

[0050] The organization unit can determine the priority of information files based on their creation date. For example, the organization unit can prioritize organizing the most recent files. For example, the organization unit can evaluate the creation date of the files and prioritize organizing the most recent files. The organization unit can also organize older files by summarizing only the essentials. For example, the organization unit can evaluate the creation date of the files and organize only the essentials. The organization unit can also organize moderately new files with an appropriate level of detail. For example, the organization unit can evaluate the creation date of the files and organize them with an appropriate level of detail. This allows for organizing files in the optimal order based on their creation date. Some or all of the above processes in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the file creation dates into a generating AI and have the generating AI determine the organization priority.

[0051] The organization unit can adjust the order of organization based on the relationships between files when organizing information files. For example, the organization unit can prioritize organizing files that are highly relevant. For example, the organization unit can evaluate the relationships between files and prioritize organizing those that are highly relevant. The organization unit can also organize only the essential points of files that are not highly relevant. For example, the organization unit can evaluate the relationships between files and organize only the essential points. The organization unit can also organize files of moderate relevance with an appropriate level of detail. For example, the organization unit can evaluate the relationships between files and organize them with an appropriate level of detail. This allows for organization in the optimal order based on the relationships between files. Some or all of the above processing in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the relationships between files into a generating AI and have the generating AI adjust the order of organization.

[0052] The grouping unit can improve the accuracy of grouping by considering the interrelationships between articles during the grouping process. For example, the grouping unit can group highly relevant articles together based on their content. For example, the grouping unit can analyze the content of articles and group highly relevant articles. The grouping unit can also group highly relevant articles together by considering the author and publication date of the articles. For example, the grouping unit can analyze the author and publication date of the articles and group highly relevant articles. The grouping unit can also analyze the keywords of the articles and group highly relevant articles together. For example, the grouping unit can analyze the keywords of the articles using keyword extraction technology and group highly relevant articles. This enables optimal grouping based on the interrelationships between articles. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the interrelationships between articles into a generating AI and leave the grouping to the generating AI.

[0053] The grouping unit can group articles while considering the attribute information of the article submitters. For example, the grouping unit can group highly relevant articles together based on the submitter's occupation or position. For example, the grouping unit can analyze the submitter's occupation or position and group highly relevant articles. The grouping unit can also group highly relevant articles together based on the submitter's field of expertise. For example, the grouping unit can analyze the submitter's field of expertise and group highly relevant articles. The grouping unit can also group highly relevant articles together based on the submitter's past submission history. For example, the grouping unit can analyze the submitter's past submission history and group highly relevant articles. This allows for optimal grouping based on the submitter's attribute information. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the submitter's attribute information into a generating AI and leave the grouping to the generating AI.

[0054] The grouping unit can group articles considering their geographical distribution. For example, it can group highly relevant articles together based on their publication location. For instance, it can analyze the publication locations of articles and group highly relevant articles. Furthermore, if the content of an article relates to a specific region, the grouping unit can group it based on that region. For example, it can analyze the content of an article and group articles related to a specific region. The grouping unit can also group highly relevant articles together based on the location of the article's author. For instance, it can analyze the author's location and group highly relevant articles. This allows for optimal grouping based on the geographical distribution of articles. Some or all of the above processing in the grouping unit may be performed using AI, or without AI. For example, the grouping unit can input the geographical distribution of articles into a generating AI and entrust the grouping to the generating AI.

[0055] The grouping unit can improve the accuracy of grouping by referring to the relevant literature of the articles during the grouping process. For example, the grouping unit can analyze the references of the articles and group together highly relevant articles. For example, the grouping unit can analyze the references of the articles and group together highly relevant articles. The grouping unit can also consider the citations of the articles and group together highly relevant articles. For example, the grouping unit can analyze the citations of the articles and group together highly relevant articles. The grouping unit can also improve the accuracy of grouping by referring to the relevant literature of the articles. For example, the grouping unit can analyze the relevant literature of the articles and improve the accuracy of grouping. This allows for optimal grouping based on the relevant literature of the articles. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the relevant literature of the articles into a generating AI and leave the grouping to the generating AI.

[0056] The recommendation unit can analyze the user's past behavior history to select the optimal recommendation method when making recommendations. For example, the recommendation unit can recommend highly relevant articles based on articles the user has previously viewed. For example, the recommendation unit can analyze the user's browsing history and recommend highly relevant articles. The recommendation unit can also analyze the user's past search history and recommend highly relevant articles. For example, the recommendation unit can analyze the user's search history and recommend highly relevant articles. The recommendation unit can also consider the user's past clipping history to select the optimal recommendation method. For example, the recommendation unit can analyze the user's clipping history and select the optimal recommendation method. This allows the recommendation unit to provide optimal recommendations based on the user's past behavior history. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without using AI. For example, the recommendation unit can input the user's behavioral history into a generating AI and have the AI ​​select a recommendation method.

[0057] The recommendation unit can customize its recommendation methods based on the user's current areas of interest. For example, the recommendation unit can recommend articles related to topics the user has recently been interested in. For example, the recommendation unit can analyze the user's browsing and search history to identify their current areas of interest. The recommendation unit can also recommend articles related to keywords if the user frequently searches for those keywords. For example, the recommendation unit can analyze the user's search keywords and recommend relevant articles. The recommendation unit can also recommend articles related to categories if the user has shown interest in those categories. For example, the recommendation unit can analyze the user's browsing history and recommend articles related to those categories. This allows the recommendation unit to provide optimal recommendations based on the user's areas of interest. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's areas of interest into a generating AI and have the AI ​​customize the recommendation methods.

[0058] The recommendation unit can select the optimal recommendation method by considering the user's geographical location information when making recommendations. For example, if the user is in a specific region, the recommendation unit can recommend articles related to that region. For example, the recommendation unit can analyze the user's geographical location information and identify relevant articles. The recommendation unit can also recommend tourist information or news articles related to the travel destination if the user is traveling. For example, the recommendation unit can analyze the user's geographical location information and identify articles related to the travel destination. The recommendation unit can also recommend articles related to an event if the user is participating in a specific event. For example, the recommendation unit can analyze the user's geographical location information and identify articles related to the event. This allows the recommendation unit to provide optimal recommendations based on the user's geographical location information. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's geographical location information into a generating AI and have the AI ​​select a recommendation method.

[0059] The recommendation unit can analyze the user's social media activity and propose recommendation methods when making recommendations. For example, the recommendation unit can recommend new articles related to articles the user has shared on social media. For example, the recommendation unit can analyze the user's social media activity and identify relevant articles. The recommendation unit can also recommend articles related to topics the user follows on social media. For example, the recommendation unit can analyze the topics the user follows and identify relevant articles. The recommendation unit can also recommend articles related to groups and communities the user participates in on social media. For example, the recommendation unit can analyze the groups the user participates in and identify relevant articles. This allows the recommendation unit to provide optimal recommendations based on the user's social media activity. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's social media activity into a generating AI and have the generating AI propose recommendation methods.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The reception desk can analyze a user's past upload history and suggest the optimal upload method. For example, it can prioritize suggesting upload methods the user has frequently used in the past (such as drag and drop or file selection). It can also send notifications prompting users to upload during specific time periods if they tend to upload at those times. Furthermore, if a user has previously failed to upload, the system can analyze the cause and suggest solutions. This allows the system to provide the most suitable upload method based on the user's past history.

[0062] The analysis unit can adjust the level of detail recorded based on the importance of the article. For example, for highly important articles, detailed information is recorded. For less important articles, only the main points can be recorded. Furthermore, for articles of moderate importance, information can be recorded with an appropriate level of detail. This allows for the recording of information with the optimal level of detail according to the importance of the article.

[0063] The grouping function can improve the accuracy of grouping by considering the interrelationships between articles. For example, it can group highly relevant articles together based on their content. It can also group highly relevant articles together by considering the author and publication date. Furthermore, it can analyze the keywords of the articles and group highly relevant articles together. This allows for optimal grouping based on the interrelationships between articles.

[0064] The recommendation system can select the optimal recommendation method by considering the user's geographical location. For example, if a user is in a specific region, it can recommend articles related to that region. If a user is traveling, it can also recommend tourist information and news articles related to their destination. Furthermore, if a user is attending a specific event, it can recommend articles related to that event. This allows the system to provide optimal recommendations based on the user's geographical location.

[0065] The recommendation system can analyze users' social media activity and propose recommendation methods. For example, it can recommend new articles related to articles users have shared on social media. It can also recommend articles related to topics users follow on social media. Furthermore, it can recommend articles related to groups and communities users participate in on social media. This allows the system to provide optimal recommendations based on users' social media activity.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The reception desk uploads the clipped articles to the cloud. Clipped articles include news articles, blog posts, academic papers, etc. Users can upload articles by dragging and dropping them or by using the file selection dialog. They can also use the scheduled upload function to automatically upload articles at specific times. Step 2: The analysis unit analyzes the uploaded articles and records basic information. This basic information includes the article title, author, publication date, summary of content, and keywords. The analysis unit uses natural language processing technology and machine learning algorithms to analyze the content of the articles and extract the basic information. Step 3: The organization unit automatically organizes the information files based on the basic information recorded by the analysis unit. Organization methods include alphabetical order, publication date order, and category order. For example, article titles can be sorted alphabetically, organized by publication date, or categorized. Step 4: The grouping section groups the information files organized by the organization section. Grouping criteria include themes, topics, and keyword similarities. For example, articles on the same theme or topic can be grouped together, or articles can be grouped based on keyword similarity. Step 5: The recommendation unit makes recommendations based on the information files grouped by the grouping unit. Recommendation methods include the user's past behavior history, areas of interest, and article content. For example, it can remind users of relevant articles before a specific meeting or presentation, or recommend the most suitable articles based on the user's past behavior history and areas of interest.

[0068] (Example of form 2) The support AI system according to an embodiment of the present invention is a system that centrally manages clipped articles, records basic information, automatically organizes information files, groups them, and provides recommendations. This support AI system records necessary basic information, automatically organizes information files, groups them, and provides recommendations from an information utilization perspective (reminders for sharing and timing of use) simply by uploading clipped articles to the cloud. For example, a user uploads articles clipped from various media sources to a designated cloud. Next, the support AI analyzes the uploaded articles and automatically records the necessary basic information. For example, it extracts the article title, author, publication date, summary of content, keywords, etc. Then, the support AI automatically organizes the information files and groups related articles. For example, it groups articles on the same theme or topic. Furthermore, from an information utilization perspective, it provides reminders for sharing and timing of use. For example, it can remind users of relevant articles before a specific meeting or presentation. For corporate use, it is useful for sales pitches, creating prospect lists, preparing documents, and use in meetings. For example, sales representatives can be reminded of relevant articles to make more effective sales pitches to prospects. Also, when creating prospect lists, lists can be created based on relevant articles. For individuals, it can be useful for providing investment advice. For instance, an investor can clip articles about a specific stock, and the support AI analyzes those articles to provide investment advice. For example, it can remind users of the latest news and analysis articles on a specific stock. In this way, the support AI centrally manages clipped articles, records necessary basic information, automatically organizes information files, groups them, and provides recommendations from an information utilization perspective, thus providing effective support for both corporate and individual clients. This allows the support AI system to centrally manage clipped articles, record basic information, automatically organizes information files, groups them, and provides recommendations.

[0069] The support AI system according to this embodiment comprises a reception unit, an analysis unit, an organization unit, a grouping unit, and a recommendation unit. The reception unit uploads clipped articles to the cloud. Clipped articles include, but are not limited to, news articles, blog posts, and academic papers. The reception unit uploads articles to the cloud, for example, by having the user drag and drop the articles. The reception unit can also upload articles using a file selection dialog. Furthermore, the reception unit has a scheduled upload function, allowing it to automatically upload articles at a specific time. The analysis unit analyzes the uploaded articles and records basic information. Basic information includes, but is not limited to, the article title, author, publication date, summary of content, and keywords. The analysis unit analyzes the content of the articles and extracts basic information, for example, using natural language processing technology. The analysis unit can also extract important information from the articles using machine learning algorithms. The organization unit automatically organizes the information files based on the basic information recorded by the analysis unit. Methods of organization include, but are not limited to, alphabetical order, publication date order, and category order. The organization unit can, for example, sort article titles alphabetically. It can also organize articles by publication date. Furthermore, it can classify and organize articles by category. The grouping unit groups the information files organized by the organization unit. Criteria for grouping include, but are not limited to, theme, topic, and keyword similarity. The grouping unit can, for example, group articles on the same theme into one group. It can also group articles on the same topic into one group. Furthermore, it can group articles based on keyword similarity. The recommendation unit makes recommendations based on the information files grouped by the grouping unit. Methods of recommendation include, but are not limited to, the user's past behavior history, areas of interest, and article content.The recommendation unit can, for example, remind users of relevant articles before specific meetings or presentations. It can also recommend the most suitable articles based on the user's past browsing history. Furthermore, it can recommend articles based on the user's areas of interest. This allows the support AI system according to the embodiment to centrally manage clipped articles, record basic information, automatically organize and group information files, and perform recommendations.

[0070] The reception desk uploads clipped articles to the cloud. Clipped articles include, but are not limited to, news articles, blog posts, and academic papers. The reception desk uploads articles to the cloud, for example, by allowing users to drag and drop articles. It also allows users to upload articles using a file selection dialog. Furthermore, the reception desk has a scheduled upload function that allows articles to be automatically uploaded at a specific time. Specifically, when a user drags and drops an article, the reception desk detects the operation, verifies the file format and content of the article, and securely transfers it to cloud storage. When using the file selection dialog, users can select multiple files from their local disk and upload them at once. The scheduled upload function automatically uploads articles based on a time set by the user. For example, it can automatically detect new articles in a specific folder at 9:00 AM every day and upload them to the cloud. This function saves users the trouble of manually uploading. Furthermore, the reception desk automatically retrieves metadata of uploaded articles to facilitate management in the cloud. For example, it retrieves basic information such as file name, creation date and time, and file size, and records it in the cloud database. This allows users to easily search and manage uploaded articles.

[0071] The analysis unit analyzes uploaded articles and records basic information. This basic information includes, but is not limited to, the article title, author, publication date, summary, and keywords. The analysis unit can, for example, use natural language processing techniques to analyze the article content and extract basic information. It can also use machine learning algorithms to extract important information from articles. Specifically, it uses natural language processing techniques to analyze the article text and automatically extracts metadata such as the article title, author name, and publication date. Furthermore, it applies topic modeling and keyword extraction algorithms to summarize the article content and extract important keywords. For example, Latent Dirichlet Allocation (LDA) can be used to identify the article's topic and extract important keywords. By using machine learning algorithms, it becomes possible to extract important information from articles with high accuracy. For example, classification algorithms such as Support Vector Machines (SVM) and Random Forests can be used to classify the article content and identify important information. This allows the analysis unit to analyze the uploaded article content in detail and accurately record basic information. Furthermore, the analysis unit can select an appropriate analysis method depending on the language and format of the article when analyzing its content. For example, it can apply an English natural language processing model to English articles and a Japanese model to Japanese articles. This enables the analysis unit to handle multiple languages ​​and accurately analyze articles in various languages.

[0072] The organization unit automatically organizes information files based on the basic information recorded by the analysis unit. Organization methods include, but are not limited to, alphabetical order, publication date order, and category order. For example, the organization unit sorts article titles alphabetically. It can also sort articles by publication date. Furthermore, it can classify and organize articles by category. Specifically, it applies an algorithm to sort article titles alphabetically based on the basic information provided by the analysis unit. When sorting by publication date, articles can be sorted in ascending or descending order based on their publication date. When sorting by category, the organization unit automatically assigns appropriate categories based on the content and keywords of the articles. For example, news articles are classified into categories such as "Politics," "Economy," and "Sports," while academic papers are classified into categories such as "Physics," "Chemistry," and "Biology." The organization unit classifies articles based on these categories to make them easily accessible to users. Furthermore, the organization unit can flexibly change the organization method based on user custom settings. For example, if a user wants to organize articles based on specific keywords, the organization unit can filter and organize articles based on those keywords. This allows the organization unit to provide flexible organization methods tailored to user needs, thereby streamlining information management.

[0073] The grouping unit groups the information files organized by the organization unit. Grouping criteria include, but are not limited to, themes, topics, and keyword similarity. For example, the grouping unit can group articles on the same theme. It can also group articles on the same topic. Furthermore, the grouping unit can group articles based on keyword similarity. Specifically, it uses natural language processing techniques to analyze the content of articles and identify themes and topics. For example, it can use topic modeling techniques to extract the topics of articles and group articles on the same topic. When grouping based on keyword similarity, it vectorizes the keywords of the articles and calculates similarity using methods such as cosine similarity. By grouping articles with high similarity into the same group, highly relevant articles can be consolidated into a single group. Furthermore, the grouping unit can change the grouping criteria based on user custom settings. For example, if a user wants to group articles based on specific keywords, the unit can filter and group articles based on those keywords. This allows the grouping unit to provide flexible grouping methods tailored to user needs, thereby streamlining information management.

[0074] The recommendation unit makes recommendations based on information files grouped by the grouping unit. Recommendation methods include, but are not limited to, the user's past browsing history, areas of interest, and article content. For example, the recommendation unit might remind users of relevant articles before a specific meeting or presentation. It can also recommend the most relevant articles based on the user's past browsing history. Furthermore, it can recommend articles based on the user's areas of interest. Specifically, it analyzes the user's past browsing and search history to identify articles that are likely to interest the user. For example, it might use collaborative filtering technology to recommend articles based on their similarity to articles viewed by other users. It can also use content-based filtering technology to recommend articles based on their content and keywords. Additionally, the recommendation unit can modify its recommendation methods based on the user's custom settings. For example, if a user is interested in a particular topic, it can prioritize recommending articles related to that topic. This allows the recommendation system to provide flexible recommendation methods tailored to user needs, maximizing the utilization of information. Furthermore, the recommendation system can collect user feedback and continuously improve the accuracy of its recommendation algorithm. For example, it can provide a function that allows users to rate recommended articles and adjust the algorithm based on those ratings. This enables the recommendation system to provide users with more appropriate articles and maximize the value of the information.

[0075] The analysis unit can record the article's title, author, publication date, summary, and keywords. For example, the analysis unit can extract and record the article's title. For example, the analysis unit can analyze and record the article's title using natural language processing technology. The analysis unit can also extract and record the article's author. For example, the analysis unit can analyze and record the article's author's name. The analysis unit can also extract and record the article's publication date. For example, the analysis unit can analyze and record the article's publication date. The analysis unit can also summarize and record the article's content. For example, the analysis unit can summarize and record the article's content using natural language processing technology. The analysis unit can also extract and record the article's keywords. For example, the analysis unit can analyze and record the article's keywords using keyword extraction technology. This allows for detailed recording of the article's basic information. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of an article into a generation AI and have the generation AI extract basic information.

[0076] The grouping unit can group articles related to the same theme or topic. For example, the grouping unit can group articles related to the same theme. For example, the grouping unit can analyze the theme of the articles using natural language processing technology and group articles related to the same theme. The grouping unit can also group articles related to the same topic. For example, the grouping unit can analyze the topic of the articles using a topic model and group articles related to the same topic. The grouping unit can also group articles based on keyword similarity. For example, the grouping unit can analyze the keywords of the articles using keyword extraction technology and group articles with highly similar keywords. This allows for efficient grouping of related articles. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the theme or topic of the articles into a generative AI and leave the grouping to the generative AI.

[0077] The recommendation unit can remind users of relevant articles before specific meetings or presentations. For example, the recommendation unit can remind users of relevant articles before specific meetings or presentations. For example, the recommendation unit can analyze meeting schedules and remind users of relevant articles. The recommendation unit can also analyze presentation content and remind users of relevant articles. For example, the recommendation unit can remind users of relevant articles based on the presentation theme. This allows the recommendation unit to provide relevant information before meetings or presentations. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or not using AI. For example, the recommendation unit can input meeting or presentation schedules into a generating AI and have the generating AI perform the task of reminding users of relevant articles.

[0078] The recommendation unit can make recommendations based on the user's past browsing history or the content of clipped articles. For example, the recommendation unit can make recommendations based on the user's past browsing history. For example, the recommendation unit can analyze the user's browsing history and recommend relevant articles. The recommendation unit can also analyze the user's click history and recommend relevant articles. Furthermore, the recommendation unit can analyze the user's search history and recommend relevant articles. For example, the recommendation unit can recommend relevant articles based on keywords the user has searched for in the past. The recommendation unit can also make recommendations based on the content of clipped articles. For example, the recommendation unit can analyze the content of clipped articles and recommend relevant articles. This allows the recommendation unit to provide optimal recommendations based on the user's browsing history. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation section can input the user's behavior history and the content of clipped articles into a generating AI, and then leave the execution of recommendations to the generating AI.

[0079] The recommendation unit can remind users of the latest news or analysis articles related to specific stocks. For example, the recommendation unit can remind users of the latest news related to specific stocks. For example, the recommendation unit can analyze news articles related to specific stocks and remind users of the latest news. The recommendation unit can also remind users of analysis articles related to specific stocks. For example, the recommendation unit can analyze analysis articles related to specific stocks and remind users of the latest analysis. This allows the recommendation unit to provide users with the latest information to help them make informed investment decisions. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input news or analysis articles related to specific stocks into a generating AI and leave the reminder execution to the generating AI.

[0080] The reception desk can estimate the user's emotions and adjust the timing of article uploads based on the estimated emotions. For example, if the reception desk is stressed, it can automatically delay the upload and prompt the user again when they are relaxed. For example, the reception desk can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. Also, if the reception desk is focused, it can immediately prompt the user to upload to avoid interrupting the workflow. For example, the reception desk can record the user's voice and estimate their emotions using voice analysis technology. Also, if the reception desk is tired, it can postpone the upload to the next day, prioritizing rest. For example, the reception desk can collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the article to be uploaded at the optimal time according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reception area may be performed using AI, for example, or without AI. For example, the reception area can input user emotion data into a generating AI and have the generating AI adjust the upload timing.

[0081] The reception desk can analyze a user's past upload history and select an appropriate upload method. For example, the reception desk may prioritize suggesting upload methods that the user has frequently used in the past (e.g., drag and drop, file selection). For instance, the reception desk analyzes the user's past upload history and selects the optimal upload method. The reception desk can also send notifications prompting users to upload during specific time periods if they tend to upload at those times. For example, the reception desk analyzes the user's past upload times and sends notifications at the optimal time. Furthermore, if a user has previously failed to upload, the reception desk can analyze the cause and suggest solutions. For example, the reception desk analyzes the cause of the upload failure and suggests specific solutions to the user. This allows the reception desk to provide the optimal upload method based on the user's past history. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the user's upload history into a generating AI and have the generating AI select the optimal upload method.

[0082] The reception desk can filter articles based on the user's current areas of interest when they are uploaded. For example, the reception desk can prioritize uploading only articles related to topics the user has recently been interested in. For example, the reception desk can analyze the user's browsing and search history to identify their current areas of interest. The reception desk can also filter and display articles related to keywords if the user frequently searches for those keywords. For example, the reception desk can analyze the user's search keywords and filter related articles. The reception desk can also prioritize uploading articles related to a particular category if the user has shown interest in that category. For example, the reception desk can analyze the user's browsing history and filter articles related to that category. This allows the reception desk to upload the most relevant articles based on the user's areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input the user's areas of interest into a generating AI and leave the filtering to the generating AI.

[0083] The reception system can estimate the user's emotions and prioritize the articles to upload based on those emotions. For example, if the user is excited, the reception system will prioritize uploading the latest news articles. For example, the reception system may capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Also, if the user is relaxed, the reception system will prioritize uploading long analytical articles. For example, the reception system may record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is in a hurry, the reception system will prioritize uploading short summary articles. For example, the reception system may collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to prioritize uploading the most suitable articles according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reception area may be performed using AI, for example, or without AI. For example, the reception area can input user sentiment data into a generating AI and have the generating AI determine the priority of articles to be uploaded.

[0084] The reception desk can prioritize uploading articles that are highly relevant to the user based on their geographical location when an article is uploaded. For example, if the user is in a specific region, the reception desk will prioritize uploading news articles related to that region. For example, the reception desk will analyze the user's geographical location and identify relevant articles. The reception desk can also prioritize uploading tourist information and news articles related to the user's travel destination if the user is traveling. For example, the reception desk will analyze the user's geographical location and identify articles related to the travel destination. The reception desk can also prioritize uploading articles related to an event if the user is participating in a specific event. For example, the reception desk will analyze the user's geographical location and identify articles related to the event. This allows the reception desk to upload the most relevant articles based on the user's geographical location. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's geographical location into a generating AI and have the generating AI identify relevant articles.

[0085] The reception desk can analyze a user's social media activity when uploading an article and upload relevant articles. For example, the reception desk can prioritize uploading new articles related to articles the user has shared on social media. For example, the reception desk can analyze the user's social media activity and identify relevant articles. The reception desk can also prioritize uploading articles related to topics the user follows on social media. For example, the reception desk can analyze the topics the user follows and identify relevant articles. The reception desk can also prioritize uploading articles related to groups and communities the user participates in on social media. For example, the reception desk can analyze the groups the user participates in and identify relevant articles. This allows the reception desk to upload the most suitable articles based on the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's social media activity into a generating AI and have the generating AI identify relevant articles.

[0086] The analysis unit can estimate the user's emotions and adjust the method of recording basic information based on the estimated user emotions. For example, if the user is relaxed, the analysis unit records detailed basic information. For example, the analysis unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. If the user is in a hurry, the analysis unit records only the essentials. For example, the analysis unit records the user's voice and estimates the emotions using voice analysis technology. If the user is excited, the analysis unit records basic information in a visually easy-to-understand format. For example, the analysis unit collects the user's biometric data (heart rate and skin electrical activity) with sensors and estimates the emotions using an emotion estimation algorithm. This allows for the recording of basic information in the most optimal way according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generating AI and have the generating AI adjust the method of recording basic information.

[0087] The analysis unit can adjust the level of detail recorded based on the importance of the article during analysis. For example, the analysis unit can record detailed information for high-importance articles. For example, the analysis unit can evaluate the importance of the article and record detailed information. The analysis unit can also record only the main points for low-importance articles. For example, the analysis unit can evaluate the importance of the article and record only the main points. The analysis unit can also record information with an appropriate level of detail for articles of moderate importance. For example, the analysis unit can evaluate the importance of the article and record information with an appropriate level of detail. This allows information to be recorded with the optimal level of detail according to the importance of the article. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the article into a generating AI and have the generating AI adjust the level of detail of the recording.

[0088] The analysis unit can apply different analysis algorithms depending on the article category when analyzing an article. For example, the analysis unit can apply a news-specific analysis algorithm to news articles. For example, the analysis unit analyzes news articles and applies a news-specific algorithm. The analysis unit can also apply a detailed analysis algorithm to analytical articles. For example, the analysis unit analyzes analytical articles and applies a detailed algorithm. The analysis unit can also apply an analysis algorithm that emphasizes visual elements to entertainment articles. For example, the analysis unit analyzes entertainment articles and applies an algorithm that emphasizes visual elements. This allows for optimal analysis depending on the article category. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the article category into a generating AI and have the generating AI execute the application of the analysis algorithm.

[0089] The analysis unit can estimate the user's emotions and determine the priority of the basic information to record based on the estimated emotions. For example, if the user is relaxed, the analysis unit prioritizes recording detailed basic information. For instance, it might capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the user is in a hurry, the analysis unit prioritizes recording only the essentials. For example, it might record the user's voice and estimate their emotions using voice analysis technology. If the user is excited, the analysis unit prioritizes recording visually easy-to-understand basic information. For example, it might collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to prioritize recording the most appropriate basic information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI determine the priority of the basic information.

[0090] The analysis unit can determine the priority of recording based on the publication date of the articles when analyzing them. For example, the analysis unit can prioritize recording the most recent articles. For example, the analysis unit can evaluate the publication date of the articles and prioritize recording the most recent articles. The analysis unit can also record only the main points for older articles. For example, the analysis unit can evaluate the publication date of the articles and record only the main points. The analysis unit can also record information with a moderate level of detail for articles of moderate recency. For example, the analysis unit can evaluate the publication date of the articles and record information with a moderate level of detail. This allows information to be recorded in the optimal order based on the publication date of the articles. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the publication date of the articles into a generating AI and have the generating AI determine the priority of recording.

[0091] The analysis unit can adjust the order of recording based on the relevance of the articles during analysis. For example, the analysis unit can prioritize recording highly relevant articles. For example, the analysis unit can evaluate the relevance of the articles and prioritize recording those with high relevance. The analysis unit can also record only the main points for less relevant articles. For example, the analysis unit can evaluate the relevance of the articles and record only the main points. The analysis unit can also record information with an appropriate level of detail for articles of moderate relevance. For example, the analysis unit can evaluate the relevance of the articles and record information with an appropriate level of detail. This allows information to be recorded in the optimal order based on the relevance of the articles. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the articles into a generating AI and have the generating AI adjust the order of recording.

[0092] The organization unit can estimate the user's emotions and adjust the method of organizing information files based on the estimated emotions. For example, if the user is relaxed, the organization unit applies a detailed organization method. For example, the organization unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. If the user is in a hurry, the organization unit applies a simplified organization method. For example, the organization unit records the user's voice and estimates the emotions using voice analysis technology. If the user is excited, the organization unit organizes information files in a visually easy-to-understand format. For example, the organization unit collects the user's biometric data (heart rate and skin electrical activity) with sensors and estimates the emotions using an emotion estimation algorithm. This allows information files to be organized in the most optimal way according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input user emotion data into a generating AI and have the generating AI adjust the organization method.

[0093] The organization unit can adjust the level of detail in organizing information files based on the importance of each file. For example, the organization unit can perform detailed organization on files of high importance. For example, the organization unit can evaluate the importance of a file and perform detailed organization. The organization unit can also perform simplified organization on files of low importance. For example, the organization unit can evaluate the importance of a file and perform simplified organization. The organization unit can also organize files of medium importance with an appropriate level of detail. For example, the organization unit can evaluate the importance of a file and organize with an appropriate level of detail. This allows for organization with the optimal level of detail according to the importance of each file. Some or all of the above processes in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the importance of files into a generating AI and have the generating AI adjust the level of detail in the organization.

[0094] The organization unit can apply different organization algorithms depending on the file category when organizing information files. For example, the organization unit can apply a news-specific organization algorithm to news files. For example, the organization unit can analyze news files and apply a news-specific algorithm. The organization unit can also apply a detailed organization algorithm to analysis files. For example, the organization unit can analyze analysis files and apply a detailed algorithm. The organization unit can also apply an organization algorithm that emphasizes visual elements to entertainment files. For example, the organization unit can analyze entertainment files and apply an algorithm that emphasizes visual elements. This allows for optimal organization according to the file category. Some or all of the above processing in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the file categories into a generating AI and have the generating AI execute the application of the organization algorithm.

[0095] The organization unit can estimate the user's emotions and determine the priority of information files to organize based on the estimated emotions. For example, if the user is relaxed, the organization unit will prioritize organizing detailed information files. For example, the organization unit may capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Also, if the user is in a hurry, the organization unit will prioritize organizing only the essentials. For example, the organization unit may record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is excited, the organization unit will prioritize organizing visually easy-to-understand information files. For example, the organization unit may collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the organization unit to prioritize the most appropriate information files according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the sorting unit may be performed using AI, for example, or without AI. For example, the sorting unit can input user emotion data into a generating AI and have the generating AI determine the priority of information files.

[0096] The organization unit can determine the priority of information files based on their creation date. For example, the organization unit can prioritize organizing the most recent files. For example, the organization unit can evaluate the creation date of the files and prioritize organizing the most recent files. The organization unit can also organize older files by summarizing only the essentials. For example, the organization unit can evaluate the creation date of the files and organize only the essentials. The organization unit can also organize moderately new files with an appropriate level of detail. For example, the organization unit can evaluate the creation date of the files and organize them with an appropriate level of detail. This allows for organizing files in the optimal order based on their creation date. Some or all of the above processes in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the file creation dates into a generating AI and have the generating AI determine the organization priority.

[0097] The organization unit can adjust the order of organization based on the relationships between files when organizing information files. For example, the organization unit can prioritize organizing files that are highly relevant. For example, the organization unit can evaluate the relationships between files and prioritize organizing those that are highly relevant. The organization unit can also organize only the essential points of files that are not highly relevant. For example, the organization unit can evaluate the relationships between files and organize only the essential points. The organization unit can also organize files of moderate relevance with an appropriate level of detail. For example, the organization unit can evaluate the relationships between files and organize them with an appropriate level of detail. This allows for organization in the optimal order based on the relationships between files. Some or all of the above processing in the organization unit may be performed using AI, for example, or without AI. For example, the organization unit can input the relationships between files into a generating AI and have the generating AI adjust the order of organization.

[0098] The grouping unit can estimate the user's emotions and adjust the grouping criteria based on the estimated emotions. For example, if the user is relaxed, the grouping unit applies detailed grouping criteria. For example, the grouping unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. If the user is in a hurry, the grouping unit applies simplified grouping criteria. For example, the grouping unit records the user's voice and estimates the emotions using voice analysis technology. If the user is excited, the grouping unit performs grouping in a visually easy-to-understand format. For example, the grouping unit collects the user's biometric data (heart rate and skin electrical activity) with sensors and estimates the emotions using an emotion estimation algorithm. This allows for grouping with the optimal criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input user emotion data into a generating AI and have the generating AI adjust the grouping criteria.

[0099] The grouping unit can improve the accuracy of grouping by considering the interrelationships between articles during the grouping process. For example, the grouping unit can group highly relevant articles together based on their content. For example, the grouping unit can analyze the content of articles and group highly relevant articles. The grouping unit can also group highly relevant articles together by considering the author and publication date of the articles. For example, the grouping unit can analyze the author and publication date of the articles and group highly relevant articles. The grouping unit can also analyze the keywords of the articles and group highly relevant articles together. For example, the grouping unit can analyze the keywords of the articles using keyword extraction technology and group highly relevant articles. This enables optimal grouping based on the interrelationships between articles. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the interrelationships between articles into a generating AI and leave the grouping to the generating AI.

[0100] The grouping unit can group articles while considering the attribute information of the article submitters. For example, the grouping unit can group highly relevant articles together based on the submitter's occupation or position. For example, the grouping unit can analyze the submitter's occupation or position and group highly relevant articles. The grouping unit can also group highly relevant articles together based on the submitter's field of expertise. For example, the grouping unit can analyze the submitter's field of expertise and group highly relevant articles. The grouping unit can also group highly relevant articles together based on the submitter's past submission history. For example, the grouping unit can analyze the submitter's past submission history and group highly relevant articles. This allows for optimal grouping based on the submitter's attribute information. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the submitter's attribute information into a generating AI and leave the grouping to the generating AI.

[0101] The grouping unit can estimate the user's emotions and adjust the order in which the grouping results are displayed based on the estimated emotions. For example, if the user is relaxed, the grouping unit will prioritize displaying detailed grouping results. For example, the grouping unit may capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Also, if the user is in a hurry, the grouping unit will prioritize displaying only the essentials. For example, the grouping unit may record the user's voice and estimate their emotions using voice analysis technology. Furthermore, if the user is excited, the grouping unit will display the grouping results in a visually easy-to-understand format. For example, the grouping unit may collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the grouping results to be displayed in the optimal order according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input user emotion data into a generating AI and have the generating AI adjust the display order of the grouping results.

[0102] The grouping unit can group articles considering their geographical distribution. For example, it can group highly relevant articles together based on their publication location. For instance, it can analyze the publication locations of articles and group highly relevant articles. Furthermore, if the content of an article relates to a specific region, the grouping unit can group it based on that region. For example, it can analyze the content of an article and group articles related to a specific region. The grouping unit can also group highly relevant articles together based on the location of the article's author. For instance, it can analyze the author's location and group highly relevant articles. This allows for optimal grouping based on the geographical distribution of articles. Some or all of the above processing in the grouping unit may be performed using AI, or without AI. For example, the grouping unit can input the geographical distribution of articles into a generating AI and entrust the grouping to the generating AI.

[0103] The grouping unit can improve the accuracy of grouping by referring to the relevant literature of the articles during the grouping process. For example, the grouping unit can analyze the references of the articles and group together highly relevant articles. For example, the grouping unit can analyze the references of the articles and group together highly relevant articles. The grouping unit can also consider the citations of the articles and group together highly relevant articles. For example, the grouping unit can analyze the citations of the articles and group together highly relevant articles. The grouping unit can also improve the accuracy of grouping by referring to the relevant literature of the articles. For example, the grouping unit can analyze the relevant literature of the articles and improve the accuracy of grouping. This allows for optimal grouping based on the relevant literature of the articles. Some or all of the above processing in the grouping unit may be performed using AI, for example, or without AI. For example, the grouping unit can input the relevant literature of the articles into a generating AI and leave the grouping to the generating AI.

[0104] The recommendation system can estimate the user's emotions and adjust its recommendation method based on those emotions. For example, if the user is relaxed, the recommendation system provides detailed recommendations. For instance, it might capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the user is in a hurry, the recommendation system will only recommend the essentials. For example, it might record the user's voice and estimate their emotions using voice analysis technology. If the user is excited, the recommendation system will provide recommendations in a visually easy-to-understand format. For example, it might collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to provide recommendations in the most optimal way according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to these examples. Some or all of the processing described above in the recommendation unit may be performed using AI, or not using AI. For example, the recommendation unit may input user sentiment data into the generative AI and have the generative AI adjust the recommendation method.

[0105] The recommendation unit can analyze the user's past behavior history to select the optimal recommendation method when making recommendations. For example, the recommendation unit can recommend highly relevant articles based on articles the user has previously viewed. For example, the recommendation unit can analyze the user's browsing history and recommend highly relevant articles. The recommendation unit can also analyze the user's past search history and recommend highly relevant articles. For example, the recommendation unit can analyze the user's search history and recommend highly relevant articles. The recommendation unit can also consider the user's past clipping history to select the optimal recommendation method. For example, the recommendation unit can analyze the user's clipping history and select the optimal recommendation method. This allows the recommendation unit to provide optimal recommendations based on the user's past behavior history. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without using AI. For example, the recommendation unit can input the user's behavioral history into a generating AI and have the AI ​​select a recommendation method.

[0106] The recommendation unit can customize its recommendation methods based on the user's current areas of interest. For example, the recommendation unit can recommend articles related to topics the user has recently been interested in. For example, the recommendation unit can analyze the user's browsing and search history to identify their current areas of interest. The recommendation unit can also recommend articles related to keywords if the user frequently searches for those keywords. For example, the recommendation unit can analyze the user's search keywords and recommend relevant articles. The recommendation unit can also recommend articles related to categories if the user has shown interest in those categories. For example, the recommendation unit can analyze the user's browsing history and recommend articles related to those categories. This allows the recommendation unit to provide optimal recommendations based on the user's areas of interest. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's areas of interest into a generating AI and have the AI ​​customize the recommendation methods.

[0107] The recommendation system can estimate the user's emotions and determine recommendation priorities based on those emotions. For example, if the user is relaxed, the recommendation system will prioritize detailed recommendations. For instance, it might capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the user is in a hurry, the recommendation system will prioritize recommendations that are concise and to the point. For example, it might record the user's voice and estimate their emotions using voice analysis technology. If the user is excited, the recommendation system will prioritize recommendations in a visually easy-to-understand format. For example, it might collect the user's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. This allows the system to prioritize and provide the most appropriate recommendations according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be a text-generating AI (e.g., LLM) or a multimodal generative AI, but is not limited to such examples. Some or all of the processing described above in the recommendation section may be performed using AI, or not using AI. For example, the recommendation section may input user sentiment data into the generative AI and have the generative AI determine the recommendation priority.

[0108] The recommendation unit can select the optimal recommendation method by considering the user's geographical location information when making recommendations. For example, if the user is in a specific region, the recommendation unit can recommend articles related to that region. For example, the recommendation unit can analyze the user's geographical location information and identify relevant articles. The recommendation unit can also recommend tourist information or news articles related to the travel destination if the user is traveling. For example, the recommendation unit can analyze the user's geographical location information and identify articles related to the travel destination. The recommendation unit can also recommend articles related to an event if the user is participating in a specific event. For example, the recommendation unit can analyze the user's geographical location information and identify articles related to the event. This allows the recommendation unit to provide optimal recommendations based on the user's geographical location information. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's geographical location information into a generating AI and have the AI ​​select a recommendation method.

[0109] The recommendation unit can analyze the user's social media activity and propose recommendation methods when making recommendations. For example, the recommendation unit can recommend new articles related to articles the user has shared on social media. For example, the recommendation unit can analyze the user's social media activity and identify relevant articles. The recommendation unit can also recommend articles related to topics the user follows on social media. For example, the recommendation unit can analyze the topics the user follows and identify relevant articles. The recommendation unit can also recommend articles related to groups and communities the user participates in on social media. For example, the recommendation unit can analyze the groups the user participates in and identify relevant articles. This allows the recommendation unit to provide optimal recommendations based on the user's social media activity. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's social media activity into a generating AI and have the generating AI propose recommendation methods.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The reception desk can analyze a user's past upload history and suggest the optimal upload method. For example, it can prioritize suggesting upload methods the user has frequently used in the past (such as drag and drop or file selection). It can also send notifications prompting users to upload during specific time periods if they tend to upload at those times. Furthermore, if a user has previously failed to upload, the system can analyze the cause and suggest solutions. This allows the system to provide the most suitable upload method based on the user's past history.

[0112] The analysis unit can adjust the level of detail recorded based on the importance of the article. For example, for highly important articles, detailed information is recorded. For less important articles, only the main points can be recorded. Furthermore, for articles of moderate importance, information can be recorded with an appropriate level of detail. This allows for the recording of information with the optimal level of detail according to the importance of the article.

[0113] The grouping function can improve the accuracy of grouping by considering the interrelationships between articles. For example, it can group highly relevant articles together based on their content. It can also group highly relevant articles together by considering the author and publication date. Furthermore, it can analyze the keywords of the articles and group highly relevant articles together. This allows for optimal grouping based on the interrelationships between articles.

[0114] The recommendation system can select the optimal recommendation method by considering the user's geographical location. For example, if a user is in a specific region, it can recommend articles related to that region. If a user is traveling, it can also recommend tourist information and news articles related to their destination. Furthermore, if a user is attending a specific event, it can recommend articles related to that event. This allows the system to provide optimal recommendations based on the user's geographical location.

[0115] The recommendation system can analyze users' social media activity and propose recommendation methods. For example, it can recommend new articles related to articles users have shared on social media. It can also recommend articles related to topics users follow on social media. Furthermore, it can recommend articles related to groups and communities users participate in on social media. This allows the system to provide optimal recommendations based on users' social media activity.

[0116] The reception desk can estimate the user's emotions and adjust the timing of article uploads based on those estimates. For example, if a user is stressed, the upload will be automatically delayed and prompted again when the user is relaxed. If a user is focused, the upload will be prompted immediately to avoid interrupting the workflow. Furthermore, if a user is tired, the upload will be postponed until the next day to prioritize rest. This allows articles to be uploaded at the optimal time according to the user's emotions.

[0117] The analysis unit can estimate the user's emotions and adjust the method of recording basic information based on the estimated emotions. For example, if the user is relaxed, detailed basic information is recorded. If the user is in a hurry, only the essentials are recorded. Furthermore, if the user is excited, basic information is recorded in a visually easy-to-understand format. This allows basic information to be recorded in the most optimal way according to the user's emotions.

[0118] The organization unit can estimate the user's emotions and adjust the organization method of information files based on the estimated emotions. For example, if the user is relaxed, a detailed organization method is applied. If the user is in a hurry, a simplified organization method is applied. Furthermore, if the user is excited, information files are organized in a visually easy-to-understand format. This allows information files to be organized in the most optimal way according to the user's emotions.

[0119] The grouping unit can estimate the user's emotions and adjust the grouping criteria based on those estimates. For example, if the user is relaxed, detailed grouping criteria are applied. If the user is in a hurry, simplified grouping criteria are applied. Furthermore, if the user is excited, grouping is performed in a visually easy-to-understand format. This allows for grouping using the most appropriate criteria according to the user's emotions.

[0120] The recommendation system can estimate the user's emotions and adjust its recommendation methods based on those estimates. For example, if the user is relaxed, it provides detailed recommendations. If the user is in a hurry, it recommends only the essentials. Furthermore, if the user is excited, it provides recommendations in a visually easy-to-understand format. This allows for recommendations to be made in the most appropriate way according to the user's emotions.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The reception desk uploads the clipped articles to the cloud. Clipped articles include news articles, blog posts, academic papers, etc. Users can upload articles by dragging and dropping them or by using the file selection dialog. They can also use the scheduled upload function to automatically upload articles at specific times. Step 2: The analysis unit analyzes the uploaded articles and records basic information. This basic information includes the article title, author, publication date, summary of content, and keywords. The analysis unit uses natural language processing technology and machine learning algorithms to analyze the content of the articles and extract the basic information. Step 3: The organization unit automatically organizes the information files based on the basic information recorded by the analysis unit. Organization methods include alphabetical order, publication date order, and category order. For example, article titles can be sorted alphabetically, organized by publication date, or categorized. Step 4: The grouping section groups the information files organized by the organization section. Grouping criteria include themes, topics, and keyword similarities. For example, articles on the same theme or topic can be grouped together, or articles can be grouped based on keyword similarity. Step 5: The recommendation unit makes recommendations based on the information files grouped by the grouping unit. Recommendation methods include the user's past behavior history, areas of interest, and article content. For example, it can remind users of relevant articles before a specific meeting or presentation, or recommend the most suitable articles based on the user's past behavior history and areas of interest.

[0123] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0126] For example, the reception unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the function that allows the user to upload articles to the cloud by dragging and dropping them is implemented by the control unit 46A of the smart device 14. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and analyzes the content of articles using natural language processing technology and extracts basic information. The organization unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and automatically organizes information files based on the basic information. The grouping unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and groups articles based on themes and topics. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and recommends articles based on the user's past behavior history and areas of interest. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the function that allows the user to upload articles to the cloud by dragging and dropping them is implemented by the control unit 46A of the smart glasses 214. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which analyzes the content of articles using natural language processing technology and extracts basic information. The organization unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which automatically organizes information files based on the basic information. The grouping unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which groups articles based on themes and topics. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which recommends articles based on the user's past behavior history and areas of interest. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the function that allows the user to upload articles to the cloud by dragging and dropping them is implemented by the control unit 46A of the headset terminal 314. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which analyzes the content of articles using natural language processing technology and extracts basic information. The organization unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which automatically organizes information files based on the basic information. The grouping unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which groups articles based on themes and topics. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12, for example, which recommends articles based on the user's past behavior history and areas of interest. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] For example, the reception unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the function that allows the user to upload articles to the cloud by dragging and dropping them is implemented by the control unit 46A of the robot 414. The analysis unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and analyzes the content of articles using natural language processing technology and extracts basic information. The organization unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and automatically organizes information files based on the basic information. The grouping unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and groups articles based on themes and topics. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12, for example, and recommends articles based on the user's past behavior history and areas of interest. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0176] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) The reception desk uploads the clipped articles to the cloud, An analysis unit analyzes the articles uploaded by the reception unit and records basic information, A sorting unit that automatically organizes information files based on the basic information recorded by the analysis unit, A grouping unit that groups the information files organized by the aforementioned organizing unit, The system includes a recommendation unit that makes recommendations based on information files grouped by the grouping unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Record the article title, author, publication date, summary of content, and keywords. The system described in Appendix 1, characterized by the features described herein. (Note 3) The grouping section is, Group articles on the same theme or topic into one group. The system described in Appendix 1, characterized by the features described herein. (Note 4) The recommendation unit is, Remind yourself of relevant articles before a specific meeting or presentation. The system described in Appendix 1, characterized by the features described herein. (Note 5) The recommendation unit is, Recommendations are made based on the user's past browsing history or the content of clipped articles. The system described in Appendix 1, characterized by the features described herein. (Note 6) The recommendation unit is, Remind me of the latest news or analysis articles on specific stocks. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates user sentiment and adjusts the timing of article uploads based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is Analyze the user's past upload history and select the appropriate upload method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When uploading articles, filtering is performed based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is It estimates user sentiment and determines the priority of articles to upload based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When uploading articles, the system prioritizes uploading articles that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is When uploading an article, the system analyzes the user's social media activity and uploads relevant articles. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, We estimate the user's emotions and adjust the method of recording basic information based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, When analyzing articles, adjust the level of detail in the records based on the importance of the article. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing articles, different analysis algorithms are applied depending on the article category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and determines the priority of the underlying information to record based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing articles, the priority of records is determined based on the publication date of the articles. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When analyzing articles, the order of records is adjusted based on the relevance of the articles. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned editing unit, It estimates the user's emotions and adjusts how information files are organized based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned editing unit, When organizing information files, adjust the level of detail based on the importance of each file. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned editing unit, When organizing information files, different organization algorithms are applied depending on the file category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned editing unit, It estimates the user's emotions and determines the priority of information files to organize based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned editing unit, When organizing information files, determine the priority of organization based on when the files were created. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned editing unit, When organizing information files, adjust the order of organization based on the relationships between files. The system described in Appendix 1, characterized by the features described herein. (Note 25) The grouping section is, It estimates user sentiment and adjusts grouping criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The grouping section is, When grouping articles, consider the interrelationships between them to improve the accuracy of the grouping. The system described in Appendix 1, characterized by the features described herein. (Note 27) The grouping section is, When grouping articles, the attribute information of the article submitters is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 28) The grouping section is, It estimates the user's sentiment and adjusts the order in which grouping results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The grouping section is, When grouping articles, consider their geographical distribution. The system described in Appendix 1, characterized by the features described herein. (Note 30) The grouping section is, When grouping articles, refer to related literature to improve the accuracy of the grouping. The system described in Appendix 1, characterized by the features described herein. (Note 31) The recommendation unit is, It estimates the user's emotions and adjusts the recommendation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The recommendation unit is, When making recommendations, the system analyzes the user's past behavior history to select the most suitable recommendation method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The recommendation unit is, When making recommendations, customize the recommendation method based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 34) The recommendation unit is, It estimates the user's emotions and determines the priority of recommendations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The recommendation unit is, When making recommendations, the system selects the optimal recommendation method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The recommendation unit is, When making recommendations, the system analyzes the user's social media activity to suggest appropriate recommendation methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The reception desk uploads the clipped articles to the cloud, An analysis unit analyzes the articles uploaded by the reception unit and records basic information, A sorting unit that automatically organizes information files based on the basic information recorded by the analysis unit, A grouping unit that groups the information files organized by the aforementioned organizing unit, The system includes a recommendation unit that makes recommendations based on information files grouped by the grouping unit. A system characterized by the following features.

2. The aforementioned analysis unit, Record the article title, author, publication date, summary of content, and keywords. The system according to feature 1.

3. The grouping section is, Group articles on the same theme or topic into one group. The system according to feature 1.

4. The recommendation unit is, Remind yourself of relevant articles before a specific meeting or presentation. The system according to feature 1.

5. The recommendation unit is, Recommendations are made based on the user's past behavior history or the content of clipped articles. The system according to feature 1.

6. The recommendation unit is, Remind me of the latest news or analysis articles on specific stocks. The system according to feature 1.

7. The aforementioned reception unit is It estimates user sentiment and adjusts the timing of article uploads based on the estimated user sentiment. The system according to feature 1.

8. The aforementioned reception unit is Analyze the user's past upload history and select the appropriate upload method. The system according to feature 1.

9. The aforementioned reception unit is When uploading articles, filtering is performed based on the user's current areas of interest. The system according to feature 1.

10. The aforementioned reception unit is It estimates user sentiment and determines the priority of articles to upload based on the estimated user sentiment. The system according to feature 1.

Images