System

Abstract

To provide a system that efficiently provides information based on preferences of users.SOLUTION: A system according to an embodiment comprises a learning unit, display control unit, and summarization unit. The learning unit learns preferences of users. The display control unit hides or reduces the display size of articles determined to be of no interest based on the preferences learned by the learning unit. The summarization unit summarizes a plurality of related articles together based on the preferences learned by the learning unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] In conventional techniques, articles that are not of interest to a user may continue to be displayed, leading to the risk of the user missing important or interesting news.

[0005] The system according to the embodiment aims to efficiently provide information based on the user's preferences. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, a display control unit, and a summarizing unit. The learning unit learns the user's preferences. The display control unit hides or reduces articles determined to be of no interest based on the preferences learned by the learning unit. The summarizing unit summarizes a plurality of related articles based on the preferences learned by the learning unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently provide information based on the user's preferences. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The information gathering support system according to the embodiment of the present invention is a system that learns the user's preferences, and provides a function of hiding or reducing articles that the user is not interested in, and a function of summarizing multiple related articles. When a user browses news articles, the AI ​​learns the user's preferences based on the user's browsing history and click history. For example, for a user who frequently browses sports articles, sports-related articles are preferentially displayed, and political articles that the user is not interested in are hidden or reduced. Next, the AI ​​automatically detects multiple related articles and summarizes them together. For example, if there are multiple news articles about the same incident, the AI ​​analyzes those articles, extracts important information, and generates one summary article. This saves the user the trouble of reading multiple articles and allows the user to obtain information efficiently. Furthermore, the AI ​​continues to learn based on the user's feedback and improves the accuracy of the articles displayed. For example, the AI ​​learns the genre of articles that the user has given feedback that they are "not interested in," and does not display articles of that genre from the next time. In this way, the AI ​​learns the user's preferences and provides a service that supports more efficient information gathering for the user by hiding or reducing the size of articles that the user is not interested in, and summarizing multiple related articles together. This allows the information gathering support system to efficiently display and summarize news articles based on the user's preferences.

[0029] The information collection support system according to the embodiment includes a learning unit, a display control unit, and a summarizing unit. The learning unit learns the user's preferences. The user's preferences include, for example, browsing history, click history, feedback, and the like, but are not limited to such examples. The learning unit, for example, learns the news genres that the user frequently browses, and grasps the user's preferences. The learning unit can also identify the news genre of interest based on the user's click history. For example, the learning unit analyzes the genre of the news article that the user clicked on, and learns the preferences. Furthermore, the learning unit can also learn the preferences based on the user's feedback. For example, the learning unit learns the news genre that the user has given feedback on as "interesting," and from the next time, preferentially displays articles of that genre. The display control unit hides or reduces articles that seem to be of no interest based on the preferences learned by the learning unit. Articles that seem to be of no interest include, for example, articles with a short viewing time, articles with a low click rate, articles that have been given feedback as "not interesting," and the like, but are not limited to such examples. The display control unit can, for example, completely hide articles that seem to be of no interest. The display control unit can also reduce the display size of articles that are likely to be of no interest. For example, the display control unit reduces the display size of articles to make them less noticeable. The summarization unit summarizes multiple related articles together based on the preferences learned by the learning unit. The summary includes, for example, the length of the sentences and the importance of the information to be summarized, but is not limited to such examples. The summarization unit, for example, automatically detects multiple news articles related to the same incident, extracts important information, and generates one summary article. The summarization unit can also summarize related news articles together. For example, the summarization unit summarizes multiple news articles based on related keywords and topics. This allows the information collection support system according to the embodiment to efficiently display and summarize news articles based on the user's preferences.

[0030] The learning unit learns the user's preferences. The user's preferences include, but are not limited to, browsing history, click history, and feedback. For example, the learning unit learns the news genres that the user frequently browses and grasps the user's preferences. Specifically, the learning unit analyzes the genres and contents of news articles that the user has browsed in the past, and identifies which genres the user is interested in. For example, the news articles are classified into categories such as politics, economics, sports, and entertainment, and the frequency of browsing of each category is calculated. The learning unit can also identify the news genre of interest based on the user's click history. For example, the learning unit analyzes the genres of news articles clicked by the user and learns the preferences. Metadata such as the title, subtitle, tag, and publication date and time of the clicked article can be used to analyze the click history. Furthermore, the learning unit can learn the preferences based on the user's feedback. For example, the learning unit learns the news genres that the user has feedbacked as "interesting" and preferentially displays articles of that genre from the next time. The feedback includes evaluations such as "like" and "not interested" made by the user on the article. This allows the learning unit to understand user preferences from multiple angles and collect basic data for providing optimal news articles to individual users. Furthermore, the learning unit can use a machine learning algorithm to track changes in user preferences in real time and dynamically update the learning model. For example, if a user begins to become interested in a new genre, the change can be quickly detected and the content of the articles displayed can be adjusted. This allows the learning unit to flexibly respond to user preferences and always provide the latest information.

[0031] The display control unit hides or reduces articles that are likely to be of no interest based on the preferences learned by the learning unit. Articles that are likely to be of no interest include, but are not limited to, articles with short viewing times, articles with low click rates, and articles that are "not interesting" in feedback. The display control unit can, for example, completely hide articles that are likely to be of no interest. Specifically, the display control unit calculates the display priority of each article based on data provided by the learning unit, and hides articles with low priority. The display control unit can also reduce articles that are likely to be of no interest. For example, the display control unit reduces the display size of the article to make it less noticeable. For example, the reduced display can be performed by displaying a thumbnail image of the article in a small size, or by displaying only the title of the article. This makes it easier for the user to concentrate on articles that interest them, making it easier to select and discard information. Furthermore, the display control unit can dynamically update the display content by reflecting the user's browsing history and feedback in real time. For example, if a user gives feedback that they are "not interested" in a particular article, the display control unit immediately hides that article and similar articles. The display control unit can also optimize the display method according to the user's device and screen size. For example, on small devices such as smartphones and tablets, the number of articles displayed is reduced, and only important articles are displayed. This allows the display control unit to realize flexible display control according to the user's preferences and device, thereby improving user satisfaction.

[0032] The summarizing unit summarizes a plurality of related articles based on the preferences learned by the learning unit. Examples of summarization include, but are not limited to, the length of a sentence and the importance of the information to be summarized. For example, the summarizing unit automatically detects a plurality of news articles related to the same incident, extracts important information, and generates one summary article. Specifically, the summarizing unit uses natural language processing technology to analyze the content of each article and extracts common keywords and phrases. This allows the summarizing unit to integrate important information from a plurality of articles and generate a concise and easy-to-understand summary. The summarizing unit can also summarize related news articles together. For example, the summarizing unit summarizes a plurality of news articles based on related keywords and topics. This allows the user to efficiently grasp a lot of information at once. Furthermore, the summarizing unit can adjust the style and level of detail of the summary according to the user's preferences. For example, if the user prefers detailed information, the summarizing unit generates a detailed summary, and conversely, if the user prefers concise information, the summarizing unit generates a short summary. This allows the summarizing unit to provide a flexible summary according to the user's needs. Furthermore, the summarizing unit can evaluate the quality of the generated summary before providing it to the user, and make corrections as necessary. For example, the summary unit checks the consistency of the summary and the accuracy of the information, and if there is a problem, generates the summary again. This allows the summarization unit to provide a high-quality summary and make information gathering for the user more efficient.

[0033] The information collection support system includes a feedback unit that receives user feedback. The feedback unit receives the user feedback. The feedback includes, for example, a questionnaire, a rating button, a comment, and the like, but is not limited to such examples. The feedback unit provides, for example, a button for the user to rate a news article as "interested" or "not interested". The feedback unit can also provide a function for the user to leave a comment on the news article. For example, the feedback unit provides an interface for the user to input a comment on the news article and share the opinion with other users. Furthermore, the feedback unit can collect data for improving the accuracy of the system based on the user feedback. For example, the feedback unit learns the news genre that the user has rated as "not interesting" and does not display articles of that genre from the next time. In this way, the feedback unit can improve the accuracy of the system based on the user feedback. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the user's feedback data to the generation AI and cause the generation AI to execute an analysis of the feedback.

[0034] The information collection support system includes a data protection unit that protects the user's data. The data protection unit protects the user's data. Data protection includes, for example, encryption, access restriction, data deletion, and the like, but is not limited to such examples. For example, the data protection unit encrypts and stores the user's data. The data protection unit can also restrict access to the user's data. For example, the data protection unit allows only specific users to access the data. The data protection unit can also automatically delete the user's data after a certain period of time. For example, the data protection unit stores the user's data for a certain period of time and then automatically deletes it. This allows the data protection unit to safely protect the user's data. A part or all of the above-mentioned processing in the data protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data protection unit can input the user's data to the generation AI and cause the generation AI to encrypt the data and set access restrictions.

[0035] The learning unit can learn preferences based on the user's browsing history or click history. The learning unit learns preferences based on the user's browsing history, for example. The browsing history includes, for example, the URL of the viewed page, the viewing time, etc., but is not limited to such examples. The learning unit learns, for example, the news genres that the user frequently views, and grasps the user's preferences. The learning unit can also identify the news genre of interest based on the user's click history. The click history includes, for example, the URL of the clicked link, the number of clicks, etc., but is not limited to such examples. For example, the learning unit analyzes the genre of the news article that the user clicked on, and learns the preferences. As a result, the learning unit can learn preferences based on the user's browsing history and click history, thereby enabling more accurate news display. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's browsing history and click history to the generation AI, and cause the generation AI to execute learning of preferences.

[0036] The display control unit can hide or reduce the display of articles that are determined to be of no interest based on the learned preferences. The display control unit, for example, hides articles that are determined to be of no interest based on the learned preferences. Articles that are determined to be of no interest include, for example, articles with a short viewing time, articles with a low click rate, articles that are determined to be "not interesting" in feedback, and the like, but are not limited to such examples. The display control unit can, for example, completely hide articles that are determined to be of no interest. The display control unit can also reduce the display size of articles that are determined to be of no interest. For example, the display control unit reduces the display size of the articles to make them less noticeable. In this way, the display control unit hides or reduces the display of articles that are determined to be of no interest, so that the user does not miss important news. Part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input articles that are determined to be of no interest based on the learned preferences to the generation AI, and cause the generation AI to execute the processing of hiding or reducing the display.

[0037] The summarizing unit can automatically detect multiple related articles, extract important information, and generate one summary article. The summarizing unit can, for example, automatically detect multiple related articles, extract important information, and generate one summary article. The related articles include, for example, keyword matches, topic similarities, and the like, but are not limited to such examples. The summarizing unit can, for example, automatically detect multiple news articles related to the same incident, extract important information, and generate one summary article. The summarizing unit can also summarize related news articles together. For example, the summarizing unit summarizes multiple news articles based on related keywords or topics. This allows the summarizing unit to summarize multiple related articles together, allowing the user to efficiently collect information. A part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can input multiple related articles to a generation AI and cause the generation AI to extract important information and generate a summary article.

[0038] The learning unit can analyze the user's past news viewing patterns during learning and predict changes in preferences. The learning unit, for example, analyzes the user's past news viewing patterns during learning and predicts changes in preferences. News viewing patterns include, for example, viewing time, click history, viewing frequency, etc., but are not limited to such examples. The learning unit, for example, analyzes the genres of news viewed by the user in the past month and predicts changes in preferences. The learning unit can also predict the news genres that the user prefers in a specific season. Furthermore, the learning unit can predict the tendency of the user to be interested in specific events or occurrences. In this way, the learning unit can always provide news based on the latest preferences by predicting changes in the user's preferences. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's news viewing pattern data to the generation AI and cause the generation AI to execute a prediction of changes in preferences.

[0039] The learning unit can learn preferences by referring to the user's social media activity during learning. The learning unit, for example, learns preferences by referring to the user's social media activity during learning. Social media activity includes, for example, the content of posts, the number of likes, the number of followers, and the like, but is not limited to such examples. The learning unit, for example, learns preferences based on news articles shared by the user on social media. The learning unit can also learn preferences based on news articles that the user "liked" on social media. Furthermore, the learning unit can also learn preferences based on news accounts that the user follows on social media. This allows the learning unit to learn more accurate preferences by referring to social media activity. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's social media activity data to the generation AI and cause the generation AI to execute learning of preferences.

[0040] The learning unit can learn region-specific news preferences based on the geographical location information of the user during learning. For example, the learning unit learns region-specific news preferences based on the geographical location information of the user during learning. The geographical location information includes, for example, GPS data, IP address, etc., but is not limited to such examples. For example, the learning unit preferentially learns news of the region where the user lives. The learning unit can also temporarily learn news of the region where the user is traveling. Furthermore, the learning unit can also learn news of the region where the user frequently visits. In this way, the learning unit can provide news that is more closely related to the region by learning region-specific news preferences. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the geographical location information data of the user to the generation AI and cause the generation AI to learn region-specific news preferences.

[0041] The learning unit can learn preferences by referring to the device usage history of the user during learning. For example, the learning unit learns preferences by referring to the device usage history of the user during learning. The device usage history includes, for example, the app used, the usage time, the type of device, etc., but is not limited to such examples. For example, the learning unit learns preferences based on news viewed by the user on a smartphone. The learning unit can also learn preferences based on news viewed by the user on a tablet. Furthermore, the learning unit can learn preferences based on news viewed by the user on a personal computer. This allows the learning unit to learn more accurate preferences by referring to the device usage history. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the device usage history data of the user to the generation AI and cause the generation AI to execute learning of preferences.

[0042] The display control unit can optimize the display contents by referring to the user's past click history during display control. The display control unit optimizes the display contents by referring to the user's past click history during display control, for example. The click history includes, for example, the URL of the clicked link, the number of clicks, etc., but is not limited to such examples. The display control unit preferentially displays news of interest to the user based on news articles that the user has clicked in the past. The display control unit can also hide or reduce news of interest to the user based on news articles that the user has not clicked in the past. Furthermore, the display control unit can analyze the user's click history and propose an optimal news display method. This allows the display control unit to display news more accurately by referring to the past click history. A part or all of the above-mentioned processing in the display control unit may be performed using, for example, AI, or may be performed without using AI. For example, the display control unit can input the user's click history data to the generation AI and cause the generation AI to execute optimization of the display contents.

[0043] The display control unit can analyze the user's current interests in real time during display control and dynamically change the display content. The display control unit, for example, analyzes the user's current interests in real time during display control and dynamically change the display content. The current interests include, for example, real-time search keywords, social media trends, etc., but are not limited to such examples. The display control unit, for example, preferentially displays news related to topics in which the user is currently interested. The display control unit can also hide or reduce news related to topics in which the user is not currently interested. Furthermore, the display control unit can analyze the user's interests in real time and propose an optimal news display method. As a result, the display control unit can always provide news based on the latest interests by analyzing the interests in real time. Part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input the user's real-time interest data to the generation AI and cause the generation AI to dynamically change the display content.

[0044] The display control unit can select an optimal display method based on the device information of the user during display control. The display control unit, for example, selects an optimal display method based on the device information of the user during display control. The device information includes, for example, the type of device, the OS version, the screen size, etc., but is not limited to such examples. For example, when the user is using a smartphone, the display control unit provides a display method that matches the screen size. In addition, when the user is using a tablet, the display control unit can also provide a display method optimized for a large screen. Furthermore, when the user is using a personal computer, the display control unit can also provide a display method including detailed information. As a result, the display control unit selects the optimal display method based on the device information, thereby enabling a more easily viewable news display. Part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal display method.

[0045] The display control unit can customize the display contents by referring to the user's past feedback during display control. The display control unit, for example, customizes the display contents by referring to the user's past feedback during display control. The feedback includes, for example, a questionnaire, an evaluation button, a comment, and the like, but is not limited to such examples. The display control unit, for example, preferentially displays a news genre in which the user has previously given feedback as "interested". The display control unit can also hide or reduce a news genre in which the user has previously given feedback as "not interested". Furthermore, the display control unit can also analyze the user's feedback history and suggest an optimal news display method. This allows the display control unit to display news more accurately by referring to past feedback. A part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input the user's feedback data to the generation AI and cause the generation AI to customize the display contents.

[0046] The summarizing unit can adjust the level of detail of the summary based on the importance of the news when generating the summary. For example, the summarizing unit adjusts the level of detail of the summary based on the importance of the news when generating the summary. The importance of the news includes, but is not limited to, for example, the number of views, the number of shares, and expert evaluations. For example, the summarizing unit provides a detailed summary for news with high importance. The summarizing unit can also provide a concise summary for news with low importance. Furthermore, the summarizing unit can adjust the length of the summary according to the importance of the news. As a result, the summarizing unit can provide a more appropriate summary by adjusting the level of detail of the summary based on the importance of the news. A part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can input the importance data of the news to the generating AI and cause the generating AI to adjust the level of detail of the summary.

[0047] The summarization unit can apply different summarization algorithms depending on the news category when generating a summary. For example, the summarization unit applies different summarization algorithms depending on the news category when generating a summary. The news categories include, for example, politics, economy, sports, entertainment, etc., but are not limited to such examples. For example, the summarization unit applies a summarization algorithm that emphasizes game results and player comments to sports news. In addition, the summarization unit can also apply a summarization algorithm that emphasizes policies and key points of remarks to political news. Furthermore, the summarization unit can apply a summarization algorithm that emphasizes information on events and performers to entertainment news. In this way, the summarization unit can provide a more appropriate summary by applying different summarization algorithms depending on the news category. Part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input news category data to the generation AI and cause the generation AI to apply the summary algorithm.

[0048] The summarizing unit can determine the priority of summaries based on the news source when generating summaries. The summarizing unit, for example, determines the priority of summaries based on the news source when generating summaries. The news source includes, for example, a reliable media, an official website, etc., but is not limited to such examples. The summarizing unit, for example, preferentially provides summaries from a reliable news source. The summarizing unit can also preferentially provide summaries from a news source that the user prefers. Furthermore, the summarizing unit can adjust the priority of summaries according to the reliability of the news source. Thereby, the summarizing unit can provide more reliable summaries by determining the priority of summaries based on the news source. Part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can input news source data to the generating AI and cause the generating AI to execute the determination of the priority of summaries.

[0049] The summarization unit can adjust the order of summaries based on the relevance of news when generating summaries. The summarization unit, for example, adjusts the order of summaries based on the relevance of news when generating summaries. The relevance of news includes, for example, keyword matching, topic similarity, and the like, but is not limited to such examples. For example, the summarization unit prioritizes summarization of highly relevant news. The summarization unit can also postpone news with low relevance. Furthermore, the summarization unit can adjust the order of summaries according to the relevance of news. Thereby, the summarization unit can provide a more relevant summary by adjusting the order of summaries based on the relevance of news. Part or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarization unit can input news relevance data to the generation AI and cause the generation AI to adjust the order of summaries.

[0050] The feedback unit can select the optimal collection method by referring to the user's past feedback history when collecting feedback. The feedback unit, for example, selects the optimal collection method by referring to the user's past feedback history when collecting feedback. The feedback includes, for example, a questionnaire, an evaluation button, a comment, and the like, but is not limited to such examples. The feedback unit, for example, preferentially provides a feedback method that the user has preferred in the past. The feedback unit can also avoid a feedback method that the user has avoided in the past. Furthermore, the feedback unit can analyze the user's feedback history and suggest an optimal collection method. Thereby, the feedback unit can collect more accurate feedback by referring to the past feedback history. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's feedback history data to the generation AI and cause the generation AI to select the optimal collection method.

[0051] The feedback unit can select an optimal collection method based on the device information of the user when collecting feedback. The feedback unit, for example, selects an optimal collection method based on the device information of the user when collecting feedback. The device information includes, for example, the type of device, the OS version, the screen size, etc., but is not limited to such examples. For example, when the user is using a smartphone, the feedback unit provides a feedback form suitable for touch operation. In addition, when the user is using a tablet, the feedback unit can also provide a feedback form optimized for a large screen. Furthermore, when the user is using a personal computer, the feedback unit can also provide a feedback form suitable for keyboard input. As a result, the feedback unit can collect more accurate feedback by selecting an optimal collection method based on the device information. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal collection method.

[0052] The data protection unit can select an optimal protection method by referring to the user's past data protection settings at the time of data protection. For example, the data protection unit selects an optimal protection method by referring to the user's past data protection settings at the time of data protection. The data protection settings include, for example, privacy settings, access restrictions, and the like, but are not limited to such examples. For example, the data protection unit provides an optimal protection method based on a data protection level set by the user in the past. The data protection unit can also provide a data protection option selected by the user in the past with priority. Furthermore, the data protection unit can analyze the user's data protection history and propose an optimal protection method. Thereby, the data protection unit can provide more accurate data protection by referring to the past data protection settings. A part or all of the above-mentioned processing in the data protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data protection unit can input the user's data protection setting data to the generation AI and cause the generation AI to select an optimal protection method.

[0053] The data protection unit can select an optimal protection method based on the device information of the user when protecting data. The data protection unit, for example, selects an optimal protection method based on the device information of the user when protecting data. The device information includes, for example, the type of device, the OS version, the screen size, etc., but is not limited to such examples. For example, when the user is using a smartphone, the data protection unit provides a data protection method suitable for a mobile device. In addition, when the user is using a tablet, the data protection unit can also provide a data protection method optimized for a large screen. Furthermore, when the user is using a personal computer, the data protection unit can also provide a data protection method suitable for a desktop environment. As a result, the data protection unit can provide more accurate data protection by selecting an optimal protection method based on the device information. Part or all of the above-mentioned processing in the data protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data protection unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal protection method.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The information gathering support system may further include a translation unit. The translation unit enables the user to view news articles in different languages. For example, the user may translate an English article into Japanese and view it. The translation unit may also enable the user to provide feedback in different languages. For example, if the user provides feedback in English that they are "interested," the system may translate the feedback into Japanese and process it. The translation unit may also provide summaries of news articles in different languages. In this way, the translation unit makes it easier for the user to gather information across language barriers.

[0056] The process flow of the first embodiment will be briefly described below.

[0057] Step 1: The learning unit learns the user's preferences. The user's preferences include, for example, browsing history, click history, and feedback. The learning unit identifies the news genre of interest to the user based on the news genres the user frequently browses and the click history. The learning unit also learns the user's preferences based on the user's feedback, and from the next time, displays articles of that genre with priority. Step 2: The display control unit hides or reduces the display of articles that are likely to be of no interest based on the preferences learned by the learning unit. Articles that are likely to be of no interest include, for example, articles with short viewing times, articles with low click rates, articles that have been given feedback as "not interesting," etc. The display control unit completely hides articles that are likely to be of no interest, or reduces the display size of the articles to make them less noticeable. Step 3: The summarization unit compiles and summarizes multiple related articles based on the preferences learned by the learning unit. The summary includes the length of the text and the importance of the information being summarized. The summarization unit automatically detects multiple news articles related to the same incident, extracts important information, and generates a summary article. It also summarizes multiple news articles based on related keywords and topics.

[0058] (Example 2) The information gathering support system according to the embodiment of the present invention is a system that learns the user's preferences, and provides a function of hiding or reducing articles that the user is not interested in, and a function of summarizing multiple related articles. When a user browses news articles, the AI ​​learns the user's preferences based on the user's browsing history and click history. For example, for a user who frequently browses sports articles, sports-related articles are preferentially displayed, and political articles that the user is not interested in are hidden or reduced. Next, the AI ​​automatically detects multiple related articles and summarizes them together. For example, if there are multiple news articles about the same incident, the AI ​​analyzes those articles, extracts important information, and generates one summary article. This saves the user the trouble of reading multiple articles and allows the user to obtain information efficiently. Furthermore, the AI ​​continues to learn based on the user's feedback and improves the accuracy of the articles displayed. For example, the AI ​​learns the genre of articles that the user has given feedback that they are "not interested in," and does not display articles of that genre from the next time. In this way, the AI ​​learns the user's preferences and provides a service that supports more efficient information gathering for the user by hiding or reducing the size of articles that the user is not interested in, and summarizing multiple related articles together. This allows the information gathering support system to efficiently display and summarize news articles based on the user's preferences.

[0059] The information collection support system according to the embodiment includes a learning unit, a display control unit, and a summarizing unit. The learning unit learns the user's preferences. The user's preferences include, for example, browsing history, click history, feedback, and the like, but are not limited to such examples. The learning unit, for example, learns the news genres that the user frequently browses, and grasps the user's preferences. The learning unit can also identify the news genre of interest based on the user's click history. For example, the learning unit analyzes the genre of the news article that the user clicked on, and learns the preferences. Furthermore, the learning unit can also learn the preferences based on the user's feedback. For example, the learning unit learns the news genre that the user has given feedback on as "interesting," and from the next time, preferentially displays articles of that genre. The display control unit hides or reduces articles that seem to be of no interest based on the preferences learned by the learning unit. Articles that seem to be of no interest include, for example, articles with a short viewing time, articles with a low click rate, articles that have been given feedback as "not interesting," and the like, but are not limited to such examples. The display control unit can, for example, completely hide articles that seem to be of no interest. The display control unit can also reduce the display size of articles that are likely to be of no interest. For example, the display control unit reduces the display size of articles to make them less noticeable. The summarization unit summarizes multiple related articles together based on the preferences learned by the learning unit. The summary includes, for example, the length of the sentences and the importance of the information to be summarized, but is not limited to such examples. The summarization unit, for example, automatically detects multiple news articles related to the same incident, extracts important information, and generates one summary article. The summarization unit can also summarize related news articles together. For example, the summarization unit summarizes multiple news articles based on related keywords and topics. This allows the information collection support system according to the embodiment to efficiently display and summarize news articles based on the user's preferences.

[0060] The learning unit learns the user's preferences. The user's preferences include, but are not limited to, browsing history, click history, and feedback. For example, the learning unit learns the news genres that the user frequently browses and grasps the user's preferences. Specifically, the learning unit analyzes the genres and contents of news articles that the user has browsed in the past, and identifies which genres the user is interested in. For example, the news articles are classified into categories such as politics, economics, sports, and entertainment, and the frequency of browsing of each category is calculated. The learning unit can also identify the news genre of interest based on the user's click history. For example, the learning unit analyzes the genres of news articles clicked by the user and learns the preferences. Metadata such as the title, subtitle, tag, and publication date and time of the clicked article can be used to analyze the click history. Furthermore, the learning unit can learn the preferences based on the user's feedback. For example, the learning unit learns the news genres that the user has feedbacked as "interesting" and preferentially displays articles of that genre from the next time. The feedback includes evaluations such as "like" and "not interested" made by the user on the article. This allows the learning unit to understand user preferences from multiple angles and collect basic data for providing optimal news articles to individual users. Furthermore, the learning unit can use a machine learning algorithm to track changes in user preferences in real time and dynamically update the learning model. For example, if a user begins to become interested in a new genre, the change can be quickly detected and the content of the articles displayed can be adjusted. This allows the learning unit to flexibly respond to user preferences and always provide the latest information.

[0061] The display control unit hides or reduces articles that are likely to be of no interest based on the preferences learned by the learning unit. Articles that are likely to be of no interest include, but are not limited to, articles with short viewing times, articles with low click rates, and articles that are "not interesting" in feedback. The display control unit can, for example, completely hide articles that are likely to be of no interest. Specifically, the display control unit calculates the display priority of each article based on data provided by the learning unit, and hides articles with low priority. The display control unit can also reduce articles that are likely to be of no interest. For example, the display control unit reduces the display size of the article to make it less noticeable. For example, the reduced display can be performed by displaying a thumbnail image of the article in a small size, or by displaying only the title of the article. This makes it easier for the user to concentrate on articles that interest them, making it easier to select and discard information. Furthermore, the display control unit can dynamically update the display content by reflecting the user's browsing history and feedback in real time. For example, if a user gives feedback that they are "not interested" in a particular article, the display control unit immediately hides that article and similar articles. The display control unit can also optimize the display method according to the user's device and screen size. For example, on small devices such as smartphones and tablets, the number of articles displayed is reduced, and only important articles are displayed. This allows the display control unit to realize flexible display control according to the user's preferences and device, thereby improving user satisfaction.

[0062] The summarizing unit summarizes a plurality of related articles based on the preferences learned by the learning unit. Examples of summarization include, but are not limited to, the length of a sentence and the importance of the information to be summarized. For example, the summarizing unit automatically detects a plurality of news articles related to the same incident, extracts important information, and generates one summary article. Specifically, the summarizing unit uses natural language processing technology to analyze the contents of each article and extracts common keywords and phrases. This allows the summarizing unit to integrate important information from a plurality of articles and generate a concise and easy-to-understand summary. The summarizing unit can also summarize related news articles together. For example, the summarizing unit summarizes a plurality of news articles based on related keywords and topics. This allows the user to efficiently grasp a lot of information at once. Furthermore, the summarizing unit can adjust the style and level of detail of the summary according to the user's preferences. For example, if the user prefers detailed information, the summarizing unit generates a detailed summary, and conversely, if the user prefers concise information, the summarizing unit generates a short summary. This allows the summarizing unit to provide a flexible summary according to the user's needs. Furthermore, the summarizing unit can evaluate the quality of the generated summary before providing it to the user, and make corrections as necessary. For example, the summary unit checks the consistency of the summary and the accuracy of the information, and if there is a problem, generates the summary again. This allows the summarization unit to provide a high-quality summary and make information gathering for the user more efficient.

[0063] The information collection support system includes a feedback unit that receives user feedback. The feedback unit receives the user feedback. The feedback includes, for example, a questionnaire, a rating button, a comment, and the like, but is not limited to such examples. The feedback unit provides, for example, a button for the user to rate a news article as "interested" or "not interested". The feedback unit can also provide a function for the user to leave a comment on the news article. For example, the feedback unit provides an interface for the user to input a comment on the news article and share the opinion with other users. Furthermore, the feedback unit can collect data for improving the accuracy of the system based on the user feedback. For example, the feedback unit learns the news genre that the user has rated as "not interesting" and does not display articles of that genre from the next time. In this way, the feedback unit can improve the accuracy of the system based on the user feedback. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, AI, or may be performed without using AI. For example, the feedback unit can input the user's feedback data to the generation AI and cause the generation AI to execute an analysis of the feedback.

[0064] The information collection support system includes a data protection unit that protects the user's data. The data protection unit protects the user's data. Data protection includes, for example, encryption, access restriction, data deletion, and the like, but is not limited to such examples. For example, the data protection unit encrypts and stores the user's data. The data protection unit can also restrict access to the user's data. For example, the data protection unit allows only specific users to access the data. The data protection unit can also automatically delete the user's data after a certain period of time. For example, the data protection unit stores the user's data for a certain period of time and then automatically deletes it. This allows the data protection unit to safely protect the user's data. A part or all of the above-mentioned processing in the data protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data protection unit can input the user's data to the generation AI and cause the generation AI to encrypt the data and set access restrictions.

[0065] The learning unit can learn preferences based on the user's browsing history or click history. The learning unit learns preferences based on the user's browsing history, for example. The browsing history includes, for example, the URL of the viewed page, the viewing time, etc., but is not limited to such examples. The learning unit learns, for example, the news genres that the user frequently views, and grasps the user's preferences. The learning unit can also identify the news genre of interest based on the user's click history. The click history includes, for example, the URL of the clicked link, the number of clicks, etc., but is not limited to such examples. For example, the learning unit analyzes the genre of the news article that the user clicked on, and learns the preferences. As a result, the learning unit can learn preferences based on the user's browsing history and click history, thereby enabling more accurate news display. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's browsing history and click history to the generation AI, and cause the generation AI to execute learning of preferences.

[0066] The display control unit can hide or reduce the display of articles that are determined to be of no interest based on the learned preferences. The display control unit, for example, hides articles that are determined to be of no interest based on the learned preferences. Articles that are determined to be of no interest include, for example, articles with a short viewing time, articles with a low click rate, articles that are determined to be "not interesting" in feedback, and the like, but are not limited to such examples. The display control unit can, for example, completely hide articles that are determined to be of no interest. The display control unit can also reduce the display size of articles that are determined to be of no interest. For example, the display control unit reduces the display size of the articles to make them less noticeable. In this way, the display control unit hides or reduces the display of articles that are determined to be of no interest, so that the user does not miss important news. Part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input articles that are determined to be of no interest based on the learned preferences to the generation AI, and cause the generation AI to execute the processing of hiding or reducing the display.

[0067] The summarizing unit can automatically detect multiple related articles, extract important information, and generate one summary article. The summarizing unit can, for example, automatically detect multiple related articles, extract important information, and generate one summary article. The related articles include, for example, keyword matches, topic similarities, and the like, but are not limited to such examples. The summarizing unit can, for example, automatically detect multiple news articles related to the same incident, extract important information, and generate one summary article. The summarizing unit can also summarize related news articles together. For example, the summarizing unit summarizes multiple news articles based on related keywords or topics. This allows the summarizing unit to summarize multiple related articles together, allowing the user to efficiently collect information. A part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can input multiple related articles to a generation AI and cause the generation AI to extract important information and generate a summary article.

[0068] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. The learning unit, for example, estimates the user's emotion and selects learning data based on the estimated user's emotion. Emotions include, for example, stress, excitement, calmness, and the like, but are not limited to such examples. For example, when the user is stressed, the learning unit preferentially learns news with relaxing content. In addition, when the user is excited, the learning unit can also preferentially learn entertainment and sports news. Furthermore, when the user is calm, the learning unit can also preferentially learn political and economic news. In this way, the learning unit can provide more appropriate news by selecting learning data based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input a user's emotional data into the generation AI and have the generation AI select the learning data.

[0069] The learning unit can analyze the user's past news viewing patterns during learning and predict changes in preferences. The learning unit, for example, analyzes the user's past news viewing patterns during learning and predicts changes in preferences. News viewing patterns include, for example, viewing time, click history, viewing frequency, etc., but are not limited to such examples. The learning unit, for example, analyzes the genres of news viewed by the user in the past month and predicts changes in preferences. The learning unit can also predict the news genres that the user prefers in a specific season. Furthermore, the learning unit can predict the tendency of the user to be interested in specific events or occurrences. In this way, the learning unit can always provide news based on the latest preferences by predicting changes in the user's preferences. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's news viewing pattern data to the generation AI and cause the generation AI to execute a prediction of changes in preferences.

[0070] The learning unit can learn preferences by referring to the user's social media activity during learning. The learning unit, for example, learns preferences by referring to the user's social media activity during learning. Social media activity includes, for example, the content of posts, the number of likes, the number of followers, and the like, but is not limited to such examples. The learning unit, for example, learns preferences based on news articles shared by the user on social media. The learning unit can also learn preferences based on news articles that the user "liked" on social media. Furthermore, the learning unit can also learn preferences based on news accounts that the user follows on social media. This allows the learning unit to learn more accurate preferences by referring to social media activity. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's social media activity data to the generation AI and cause the generation AI to execute learning of preferences.

[0071] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. The learning unit, for example, estimates the user's emotion and adjusts the frequency of learning based on the estimated user's emotion. Emotions include, for example, stress, excitement, calmness, and the like, but are not limited to such examples. For example, when the user is feeling stressed, the learning unit can reduce the frequency of learning and provide relaxing news. In addition, when the user is excited, the learning unit can also increase the frequency of learning and provide entertainment or sports news. Furthermore, when the user is calm, the learning unit can keep the frequency of learning normal and provide political or economic news. In this way, the learning unit can provide more appropriate news by adjusting the frequency of learning based on the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input a user's emotional data into the generation AI and cause the generation AI to adjust the frequency of learning.

[0072] The learning unit can learn region-specific news preferences based on the geographical location information of the user during learning. For example, the learning unit learns region-specific news preferences based on the geographical location information of the user during learning. The geographical location information includes, for example, GPS data, IP address, etc., but is not limited to such examples. For example, the learning unit preferentially learns news of the region where the user lives. The learning unit can also temporarily learn news of the region where the user is traveling. Furthermore, the learning unit can also learn news of the region where the user frequently visits. In this way, the learning unit can provide news that is more closely related to the region by learning region-specific news preferences. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the geographical location information data of the user to the generation AI and cause the generation AI to learn region-specific news preferences.

[0073] The learning unit can learn preferences by referring to the device usage history of the user during learning. For example, the learning unit learns preferences by referring to the device usage history of the user during learning. The device usage history includes, for example, the app used, the usage time, the type of device, etc., but is not limited to such examples. For example, the learning unit learns preferences based on news viewed by the user on a smartphone. The learning unit can also learn preferences based on news viewed by the user on a tablet. Furthermore, the learning unit can learn preferences based on news viewed by the user on a personal computer. This allows the learning unit to learn more accurate preferences by referring to the device usage history. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the device usage history data of the user to the generation AI and cause the generation AI to execute learning of preferences.

[0074] The display control unit can estimate the user's emotion and determine the priority of news to be displayed based on the estimated user's emotion. The display control unit, for example, estimates the user's emotion and determines the priority of news to be displayed based on the estimated user's emotion. Emotions include, for example, stress, excitement, calmness, and the like, but are not limited to such examples. For example, when the user is stressed, the display control unit preferentially displays relaxing news. In addition, when the user is excited, the display control unit can also preferentially display entertainment or sports news. Furthermore, when the user is calm, the display control unit can also preferentially display political or economic news. In this way, the display control unit can provide more appropriate news by determining the priority of news based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the display control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the display control unit can input user emotion data to the generation AI and have the generation AI determine the priority of news.

[0075] The display control unit can optimize the display contents by referring to the user's past click history during display control. The display control unit optimizes the display contents by referring to the user's past click history during display control, for example. The click history includes, for example, the URL of the clicked link, the number of clicks, etc., but is not limited to such examples. The display control unit preferentially displays news of interest to the user based on news articles that the user has clicked in the past. The display control unit can also hide or reduce news of interest to the user based on news articles that the user has not clicked in the past. Furthermore, the display control unit can analyze the user's click history and propose an optimal news display method. This allows the display control unit to display news more accurately by referring to the past click history. A part or all of the above-mentioned processing in the display control unit may be performed using, for example, AI, or may be performed without using AI. For example, the display control unit can input the user's click history data to the generation AI and cause the generation AI to execute optimization of the display contents.

[0076] The display control unit can analyze the user's current interests in real time during display control and dynamically change the display content. The display control unit, for example, analyzes the user's current interests in real time during display control and dynamically change the display content. The current interests include, for example, real-time search keywords, social media trends, etc., but are not limited to such examples. The display control unit, for example, preferentially displays news related to topics in which the user is currently interested. The display control unit can also hide or reduce news related to topics in which the user is not currently interested. Furthermore, the display control unit can analyze the user's interests in real time and propose an optimal news display method. As a result, the display control unit can always provide news based on the latest interests by analyzing the interests in real time. Part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input the user's real-time interest data to the generation AI and cause the generation AI to dynamically change the display content.

[0077] The display control unit can estimate the user's emotion and adjust the layout of the news to be displayed based on the estimated user's emotion. The display control unit, for example, estimates the user's emotion and adjusts the layout of the news to be displayed based on the estimated user's emotion. The emotion includes, for example, stress, excitement, calmness, and the like, but is not limited to such examples. For example, when the user is stressed, the display control unit provides a simple and highly visible layout. In addition, when the user is excited, the display control unit can also provide a visually stimulating layout. Furthermore, when the user is calm, the display control unit can also provide a layout including detailed information. Thereby, the display control unit adjusts the layout of the news based on the user's emotion, thereby enabling more appropriate news display. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the display control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the display control unit can input user emotion data to the generation AI and cause the generation AI to adjust the layout of the news.

[0078] The display control unit can select an optimal display method based on the device information of the user during display control. The display control unit, for example, selects an optimal display method based on the device information of the user during display control. The device information includes, for example, the type of device, the OS version, the screen size, etc., but is not limited to such examples. For example, when the user is using a smartphone, the display control unit provides a display method that matches the screen size. In addition, when the user is using a tablet, the display control unit can also provide a display method optimized for a large screen. Furthermore, when the user is using a personal computer, the display control unit can also provide a display method including detailed information. As a result, the display control unit selects the optimal display method based on the device information, thereby enabling a more easily viewable news display. Part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal display method.

[0079] The display control unit can customize the display contents by referring to the user's past feedback during display control. The display control unit, for example, customizes the display contents by referring to the user's past feedback during display control. The feedback includes, for example, a questionnaire, an evaluation button, a comment, and the like, but is not limited to such examples. The display control unit, for example, preferentially displays a news genre in which the user has previously given feedback as "interested". The display control unit can also hide or reduce a news genre in which the user has previously given feedback as "not interested". Furthermore, the display control unit can also analyze the user's feedback history and suggest an optimal news display method. This allows the display control unit to display news more accurately by referring to past feedback. A part or all of the above-mentioned processing in the display control unit may be performed, for example, using AI, or may be performed without using AI. For example, the display control unit can input the user's feedback data to the generation AI and cause the generation AI to customize the display contents.

[0080] The summarizing unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. The summarizing unit, for example, estimates the user's emotion and adjusts the expression method of the summary based on the estimated user's emotion. The emotion includes, for example, stress, excitement, calmness, etc., but is not limited to such examples. For example, when the user is stressed, the summarizing unit provides a concise summary that covers the main points. In addition, when the user is excited, the summarizing unit can also provide a summary that includes detailed information. Furthermore, when the user is calm, the summarizing unit can also provide a balanced summary. Thereby, the summarizing unit can provide a more appropriate summary by adjusting the expression method of the summary based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summarizing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarization unit can input a user's emotional data into the generation AI and have the generation AI adjust the way the summary is expressed.

[0081] The summarizing unit can adjust the level of detail of the summary based on the importance of the news when generating the summary. For example, the summarizing unit adjusts the level of detail of the summary based on the importance of the news when generating the summary. The importance of the news includes, but is not limited to, for example, the number of views, the number of shares, and expert evaluations. For example, the summarizing unit provides a detailed summary for news with high importance. The summarizing unit can also provide a concise summary for news with low importance. Furthermore, the summarizing unit can adjust the length of the summary according to the importance of the news. As a result, the summarizing unit can provide a more appropriate summary by adjusting the level of detail of the summary based on the importance of the news. A part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can input the importance data of the news to the generating AI and cause the generating AI to adjust the level of detail of the summary.

[0082] The summarization unit can apply different summarization algorithms depending on the news category when generating a summary. For example, the summarization unit applies different summarization algorithms depending on the news category when generating a summary. The news categories include, for example, politics, economy, sports, entertainment, etc., but are not limited to such examples. For example, the summarization unit applies a summarization algorithm that emphasizes game results and player comments to sports news. In addition, the summarization unit can also apply a summarization algorithm that emphasizes policies and key points of remarks to political news. Furthermore, the summarization unit can apply a summarization algorithm that emphasizes information on events and performers to entertainment news. In this way, the summarization unit can provide a more appropriate summary by applying different summarization algorithms depending on the news category. Part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input news category data to the generation AI and cause the generation AI to apply the summary algorithm.

[0083] The summarization unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. The summarization unit, for example, estimates the user's emotion and adjusts the length of the summary based on the estimated user's emotion. The emotion includes, for example, stress, excitement, calmness, etc., but is not limited to such examples. For example, when the user is stressed, the summarization unit provides a short summary that covers the main points. In addition, when the user is excited, the summarization unit can also provide a longer summary that includes detailed information. Furthermore, when the user is calm, the summarization unit can also provide a summary of a balanced length. Thereby, the summarization unit can provide a more appropriate summary by adjusting the length of the summary based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarization unit can input user emotion data to the generation AI and have the generation AI adjust the length of the summary.

[0084] The summarizing unit can determine the priority of summaries based on the news source when generating summaries. The summarizing unit, for example, determines the priority of summaries based on the news source when generating summaries. The news source includes, for example, a reliable media, an official website, etc., but is not limited to such examples. The summarizing unit, for example, preferentially provides summaries from a reliable news source. The summarizing unit can also preferentially provide summaries from a news source that the user prefers. Furthermore, the summarizing unit can adjust the priority of summaries according to the reliability of the news source. Thereby, the summarizing unit can provide more reliable summaries by determining the priority of summaries based on the news source. Part or all of the above-mentioned processing in the summarizing unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarizing unit can input news source data to the generating AI and cause the generating AI to execute the determination of the priority of summaries.

[0085] The summarization unit can adjust the order of summaries based on the relevance of news when generating summaries. The summarization unit, for example, adjusts the order of summaries based on the relevance of news when generating summaries. The relevance of news includes, for example, keyword matching, topic similarity, and the like, but is not limited to such examples. For example, the summarization unit prioritizes summarization of highly relevant news. The summarization unit can also postpone news with low relevance. Furthermore, the summarization unit can adjust the order of summaries according to the relevance of news. Thereby, the summarization unit can provide a more relevant summary by adjusting the order of summaries based on the relevance of news. Part or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarization unit can input news relevance data to the generation AI and cause the generation AI to adjust the order of summaries.

[0086] The feedback unit can estimate the user's emotion and adjust the feedback collection method based on the estimated user's emotion. The feedback unit, for example, estimates the user's emotion and adjusts the feedback collection method based on the estimated user's emotion. The emotion includes, for example, stress, excitement, calmness, and the like, but is not limited to such examples. For example, the feedback unit provides a simple feedback form when the user is stressed. Also, the feedback unit can provide a detailed feedback form when the user is excited. Furthermore, the feedback unit can provide a balanced feedback form when the user is calm. Thereby, the feedback unit can collect more appropriate feedback by adjusting the feedback collection method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can input user emotional data into the generation AI and cause the generation AI to adjust the method of collecting feedback.

[0087] The feedback unit can select the optimal collection method by referring to the user's past feedback history when collecting feedback. The feedback unit, for example, selects the optimal collection method by referring to the user's past feedback history when collecting feedback. The feedback includes, for example, a questionnaire, an evaluation button, a comment, and the like, but is not limited to such examples. The feedback unit, for example, preferentially provides a feedback method that the user has preferred in the past. The feedback unit can also avoid a feedback method that the user has avoided in the past. Furthermore, the feedback unit can analyze the user's feedback history and suggest an optimal collection method. Thereby, the feedback unit can collect more accurate feedback by referring to the past feedback history. A part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the user's feedback history data to the generation AI and cause the generation AI to select the optimal collection method.

[0088] The feedback unit can estimate the user's emotion and determine the priority of the feedback based on the estimated user's emotion. The feedback unit, for example, estimates the user's emotion and determines the priority of the feedback based on the estimated user's emotion. The emotion includes, for example, stress, excitement, calmness, etc., but is not limited to such examples. For example, when the user is stressed, the feedback unit preferentially collects simple feedback. In addition, when the user is excited, the feedback unit can also preferentially collect detailed feedback. Furthermore, when the user is calm, the feedback unit can also preferentially collect balanced feedback. Thereby, the feedback unit can collect more appropriate feedback by determining the priority of the feedback based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback unit can input the user's emotional data into the generation AI and have the generation AI determine the priority of the feedback.

[0089] The feedback unit can select an optimal collection method based on the device information of the user when collecting feedback. The feedback unit, for example, selects an optimal collection method based on the device information of the user when collecting feedback. The device information includes, for example, the type of device, the OS version, the screen size, etc., but is not limited to such examples. For example, when the user is using a smartphone, the feedback unit provides a feedback form suitable for touch operation. In addition, when the user is using a tablet, the feedback unit can also provide a feedback form optimized for a large screen. Furthermore, when the user is using a personal computer, the feedback unit can also provide a feedback form suitable for keyboard input. As a result, the feedback unit can collect more accurate feedback by selecting an optimal collection method based on the device information. Part or all of the above-mentioned processing in the feedback unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal collection method.

[0090] The data protection unit can estimate the user's emotion and adjust the level of data protection based on the estimated user's emotion. The data protection unit, for example, estimates the user's emotion and adjusts the level of data protection based on the estimated user's emotion. The emotion includes, for example, stress, excitement, calmness, and the like, but is not limited to such examples. For example, when the user is feeling stressed, the data protection unit increases the level of data protection to provide a sense of security. In addition, when the user is excited, the data protection unit can also keep the level of data protection as normal. Furthermore, when the user is calm, the data protection unit can also adjust the level of data protection according to the user's preference. Thereby, the data protection unit can provide more appropriate data protection by adjusting the level of data protection based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the data protection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the data protection unit can input a user's emotional data to the generation AI and have the generation AI adjust the level of data protection.

[0091] The data protection unit can select an optimal protection method by referring to the user's past data protection settings at the time of data protection. For example, the data protection unit selects an optimal protection method by referring to the user's past data protection settings at the time of data protection. The data protection settings include, for example, privacy settings, access restrictions, and the like, but are not limited to such examples. For example, the data protection unit provides an optimal protection method based on a data protection level set by the user in the past. The data protection unit can also provide a data protection option selected by the user in the past with priority. Furthermore, the data protection unit can analyze the user's data protection history and propose an optimal protection method. Thereby, the data protection unit can provide more accurate data protection by referring to the past data protection settings. A part or all of the above-mentioned processing in the data protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data protection unit can input the user's data protection setting data to the generation AI and cause the generation AI to select an optimal protection method.

[0092] The data protection unit can estimate the user's emotion and adjust the frequency of data protection based on the estimated user's emotion. The data protection unit, for example, estimates the user's emotion and adjusts the frequency of data protection based on the estimated user's emotion. Emotions include, for example, stress, excitement, calmness, and the like, but are not limited to such examples. For example, when the user is feeling stressed, the data protection unit increases the frequency of data protection to provide a sense of security. In addition, when the user is excited, the data protection unit can also keep the frequency of data protection at a normal level. Furthermore, when the user is calm, the data protection unit can also adjust the frequency of data protection according to the user's preference. Thereby, the data protection unit can provide more appropriate data protection by adjusting the frequency of data protection based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the data protection unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the data protection unit can input a user's emotional data to the generation AI and have the generation AI adjust the frequency of data protection.

[0093] The data protection unit can select an optimal protection method based on the device information of the user when protecting data. The data protection unit, for example, selects an optimal protection method based on the device information of the user when protecting data. The device information includes, for example, the type of device, the OS version, the screen size, etc., but is not limited to such examples. For example, when the user is using a smartphone, the data protection unit provides a data protection method suitable for a mobile device. In addition, when the user is using a tablet, the data protection unit can also provide a data protection method optimized for a large screen. Furthermore, when the user is using a personal computer, the data protection unit can also provide a data protection method suitable for a desktop environment. As a result, the data protection unit can provide more accurate data protection by selecting an optimal protection method based on the device information. Part or all of the above-mentioned processing in the data protection unit may be performed, for example, using AI, or may be performed without using AI. For example, the data protection unit can input the device information data of the user to the generation AI and cause the generation AI to select the optimal protection method.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] The information gathering support system may further include a voice recognition unit. The voice recognition unit enables the user to search for news articles and provide feedback by voice. For example, when the user gives a voice command such as "Tell me the latest sports news," the voice recognition unit analyzes the command and displays related sports news. The user may also provide a voice command such as "This article was interesting." Furthermore, the voice recognition unit may analyze the user's voice tone and speed and estimate the user's emotions. This allows the voice recognition unit to provide more intuitive and convenient operations based on the user's voice input.

[0096] The information gathering support system may further include a translation unit. The translation unit enables the user to view news articles in different languages. For example, the user may translate an English article into Japanese and view it. The translation unit may also enable the user to provide feedback in different languages. For example, if the user provides feedback in English that they are "interested," the system may translate the feedback into Japanese and process it. The translation unit may also provide summaries of news articles in different languages. In this way, the translation unit makes it easier for the user to gather information across language barriers.

[0097] The information collection support system may further include a notification unit. The notification unit transmits a notification in real time when news that may interest the user is updated. For example, if the user is interested in sports news, the notification unit transmits a push notification when new sports news is published. The notification unit may also transmit a notification when news related to a specific keyword set by the user is updated. Furthermore, the notification unit may estimate the user's emotions and make adjustments such as refraining from notifications when the user is highly stressed. In this way, the notification unit supports the user so that the user does not miss important news.

[0098] The information gathering support system may further include an image analysis unit. The image analysis unit analyzes images included in news articles and provides related information. For example, it recognizes a specific person or place from an image included in a news article and provides the information to the user. The image analysis unit may also display a news article related to an image when the user clicks on the image. Furthermore, the image analysis unit may estimate the user's emotions and preferentially display images that are likely to interest the user. In this way, the image analysis unit utilizes visual information to provide richer information.

[0099] The information collection support system may further include a calendar linking unit. The calendar linking unit refers to the user's calendar information and provides related news. For example, if the user plans to participate in a specific event, news related to that event is preferentially displayed. The calendar linking unit can also adjust the timing of news display based on the user's schedule. Furthermore, the calendar linking unit can estimate the user's emotions and provide relaxing news during times of high stress. In this way, the calendar linking unit provides information tailored to the user's schedule.

[0100] The information gathering support system may further include a bookmark unit. The bookmark unit allows the user to save news articles that interest the user and view them again later. For example, the user can add an article that interests the user to a bookmark, and easily find and view the article again later. The bookmark unit may also analyze the history of articles bookmarked by the user and suggest related news. Furthermore, the bookmark unit may estimate the user's emotions and suggest articles that will help the user relax if the user is under high stress. In this way, the bookmark unit allows the user to efficiently manage information that interests the user.

[0101] The information gathering support system may further include a social sharing unit. The social sharing unit enables a user to easily share news articles on social media. For example, an article that the user finds interesting can be shared on social media such as Facebook (registered trademark) or X (formerly Twitter (registered trademark)) with one click. The social sharing unit can also analyze the user's sharing history and suggest related news. Furthermore, the social sharing unit can estimate the user's emotions and suggest articles that will help them relax if they are under a lot of stress. In this way, the social sharing unit makes it easier for the user to share information that interests them with others.

[0102] The information gathering support system may further include an offline mode unit. The offline mode unit enables the user to view news articles even in an environment without an Internet connection. For example, the user may view news articles that have been downloaded in advance offline. The offline mode unit may also save a history of articles that the user has viewed offline, and reflect the history in the system when the user returns online. Furthermore, the offline mode unit may estimate the user's emotions, and provide relaxing articles offline when the user is under high stress. In this way, the offline mode unit makes it easier for the user to gather information even in an environment without an Internet connection.

[0103] The information collection support system may further include an advertisement control unit. The advertisement control unit displays advertisements that are highly relevant to the user based on the user's preferences and browsing history. For example, if the user frequently browses sports news, advertisements for sports-related products and services are preferentially displayed. The advertisement control unit may also hide advertisements in which the user is not interested. Furthermore, the advertisement control unit may estimate the user's emotions and make adjustments such as refraining from displaying advertisements when the user is highly stressed. In this way, the advertisement control unit realizes advertisement display that is more appropriate for the user.

[0104] The information gathering support system may further include a news ranking unit. The news ranking unit displays news that is likely to interest the user in a ranking format. For example, news that is likely to interest the user may be displayed in a top 10 format so that the user does not miss important news. The news ranking unit may also customize the ranking based on the user's browsing history and feedback. Furthermore, the news ranking unit may estimate the user's emotions, and display relaxing news at the top of the ranking when the user is under high stress. In this way, the news ranking unit enables the user to efficiently grasp important news.

[0105] The process flow of the second embodiment will be briefly described below.

[0106] Step 1: The learning unit learns the user's preferences. The user's preferences include, for example, browsing history, click history, and feedback. The learning unit identifies the news genre of interest to the user based on the news genres the user frequently browses and the click history. The learning unit also learns the user's preferences based on the user's feedback, and from the next time, displays articles of that genre with priority. Step 2: The display control unit hides or reduces the display of articles that are likely to be of no interest based on the preferences learned by the learning unit. Articles that are likely to be of no interest include, for example, articles with short viewing times, articles with low click rates, articles that have been given feedback as "not interesting," etc. The display control unit completely hides articles that are likely to be of no interest, or reduces the display size of the articles to make them less noticeable. Step 3: The summarization unit compiles and summarizes multiple related articles based on the preferences learned by the learning unit. The summary includes the length of the text and the importance of the information being summarized. The summarization unit automatically detects multiple news articles related to the same incident, extracts important information, and generates a summary article. It also summarizes multiple news articles based on related keywords and topics.

[0107] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0109] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0110] Each of the multiple elements including the learning unit, display control unit, summarizing unit, feedback unit, and data protection unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart device 14, and learns preferences based on the user's browsing history and click history. The display control unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and hides or reduces articles that the user is not interested in. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes multiple related articles together. The feedback unit is realized, for example, by the control unit 46A of the smart device 14, and receives user feedback. The data protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects the user's data. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0118] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0121] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0123] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0125] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements including the learning unit, the display control unit, the summarizing unit, the feedback unit, and the data protection unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart glasses 214, and learns preferences based on the user's browsing history and click history. The display control unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and hides or reduces articles that are likely to be of no interest. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes multiple related articles together. The feedback unit is realized, for example, by the control unit 46A of the smart glasses 214, and receives user feedback. The data protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects the user's data. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0127] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0128] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0129] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0134] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0137] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0141] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements including the learning unit, display control unit, summarizing unit, feedback unit, and data protection unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the headset type terminal 314, and learns preferences based on the user's browsing history and click history. The display control unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and hides or reduces articles that are likely to be of no interest. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes multiple related articles together. The feedback unit is realized, for example, by the control unit 46A of the headset type terminal 314, and receives user feedback. The data protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects the user's data. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0145] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0146] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0150] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0151] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0152] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0154] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0155] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0156] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0158] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0159] Each of the multiple elements including the learning unit, display control unit, summarizing unit, feedback unit, and data protection unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the robot 414, and learns preferences based on the user's browsing history and click history. The display control unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and hides or reduces articles that the user is not interested in. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and summarizes multiple related articles together. The feedback unit is realized, for example, by the control unit 46A of the robot 414, and receives user feedback. The data protection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and protects the user's data. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0160] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0161] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0162] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0163] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0164] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0165] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0168] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0169] In addition, 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 upon request from the data processing device 12.

[0170] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0171] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0172] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0173] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0174] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0175] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0176] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0177] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0178] (Appendix 1) a learning unit for learning user preferences; a display control unit that hides or reduces an article that is determined to be of no interest based on the preferences learned by the learning unit; A summarizing unit that summarizes a plurality of related articles based on the preferences learned by the learning unit. A system characterized by: (Appendix 2) A feedback unit for receiving user feedback is provided. 2. The system of claim 1, (Appendix 3) Equipped with a data protection section that protects user data 2. The system of claim 1, (Appendix 4) The learning unit is Learn your preferences based on your browsing or clicking history 2. The system of claim 1, (Appendix 5) The display control unit is Hide or collapse articles that are deemed uninteresting based on learned preferences 2. The system of claim 1, (Appendix 6) The summary portion comprises: Automatically detect multiple related articles, extract key information, and generate a single summary article 2. The system of claim 1, (Appendix 7) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 8) The learning unit is During training, the system analyzes users' past news browsing patterns to predict changes in preferences. 2. The system of claim 1, (Appendix 9) The learning unit is During learning, it references the user's social media activity to learn their preferences 2. The system of claim 1, (Appendix 10) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 11) The learning unit is During training, it learns region-specific news preferences based on the user’s geographic location. 2. The system of claim 1, (Appendix 12) The learning unit is During learning, the device learns your preferences by looking at your device usage history 2. The system of claim 1, (Appendix 13) The display control unit is Estimate user sentiment and prioritize news items based on the estimated sentiment 2. The system of claim 1, (Appendix 14) The display control unit is When controlling display, optimize the display content by referring to the user's past click history. 2. The system of claim 1, (Appendix 15) The display control unit is When controlling the display, the display content is dynamically changed based on a real-time analysis of the user's current interests. 2. The system of claim 1, (Appendix 16) The display control unit is Estimate user emotions and adjust the layout of news displayed based on the estimated user emotions 2. The system of claim 1, (Appendix 17) The display control unit is When controlling display, the optimal display method is selected based on the user's device information. 2. The system of claim 1, (Appendix 18) The display control unit is When controlling display, customize the display content by referring to the user's past feedback 2. The system of claim 1, (Appendix 19) The summary portion comprises: Estimate the user's emotions and adjust the way summaries are presented based on the estimated user emotions. 2. The system of claim 1, (Appendix 20) The summary portion comprises: When generating summaries, adjust the level of detail in the summary based on the importance of the news. 2. The system of claim 1, (Appendix 21) The summary portion comprises: When generating summaries, different summarization algorithms are applied depending on the news category. 2. The system of claim 1, (Appendix 22) The summary portion comprises: Estimating user sentiment and adjusting the length of a summary based on the estimated user sentiment 2. The system of claim 1, (Appendix 23) The summary portion comprises: Prioritize summaries based on news source when generating summaries 2. The system of claim 1, (Appendix 24) The summary portion comprises: Adjust the order of summaries based on news relevance during summary generation 2. The system of claim 1, (Appendix 25) The feedback unit is Infer user sentiment and adjust feedback collection methods based on the inferred user sentiment 3. The system of claim 2, (Appendix 26) The feedback unit is When collecting feedback, choose the best method by looking at the user's past feedback history 3. The system of claim 2, (Appendix 27) The feedback unit is Estimate user emotions and prioritize feedback based on the estimated user emotions 3. The system of claim 2, (Appendix 28) The feedback unit is When collecting feedback, select the optimal collection method based on the user's device information 3. The system of claim 2, (Appendix 29) The data protection unit includes: Inferring user sentiment and adjusting the level of data protection based on the inferred user sentiment 4. The system of claim 3. (Appendix 30) The data protection unit includes: When protecting data, the system selects the optimal protection method by referring to the user's past data protection settings. 4. The system of claim 3. (Appendix 31) The data protection unit includes: Inferring user sentiment and adjusting the frequency of data protection based on the inferred user sentiment 4. The system of claim 3. (Appendix 32) The data protection unit includes: When protecting data, the optimal protection method is selected based on the user's device information. 4. The system of claim 3. [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a learning unit for learning user preferences; a display control unit that hides or reduces an article that is determined to be of no interest based on the preferences learned by the learning unit; A summarizing unit that summarizes a plurality of related articles based on the preferences learned by the learning unit. A system characterized by:

2. A feedback unit for receiving user feedback is provided.

2. The system of claim 1 .

3. Equipped with a data protection section that protects user data 2. The system of claim 1 .

4. The learning unit is Learn your preferences based on your browsing or clicking history 2. The system of claim 1 .

5. The display control unit is Hide or collapse articles that are deemed uninteresting based on learned preferences 2. The system of claim 1 .

6. The summary portion comprises: Automatically detect multiple related articles, extract key information, and generate a single summary article 2. The system of claim 1 .

7. The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions.

2. The system of claim 1 .

8. The learning unit is During training, the system analyzes users' past news browsing patterns to predict changes in preferences.

2. The system of claim 1 .

9. The learning unit is During training, the app looks at your social media activity to learn your preferences 2. The system of claim 1 .

10. The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions.

2. The system of claim 1 .

Images