system

Abstract

The system according to this embodiment aims to select news articles based on the user's interests and browsing history, and to provide highly reliable information. [Solution] The system according to the embodiment comprises a selection unit, a summarization unit, an analysis unit, and a countermeasure unit. The selection unit selects news articles based on the user's interests and browsing history. The summarization unit automatically summarizes the articles selected by the selection unit. The analysis unit analyzes trends based on the articles summarized by the summarization unit. The countermeasure unit detects clickbait based on the trends analyzed by the analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, when providing news articles based on a user's interests and browsing history, clickbait detection and trend analysis are not sufficiently performed, and there is room for improvement.

[0005] The system according to an embodiment aims to select news articles based on a user's interests and browsing history and provide highly reliable information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a selection unit, a summarization unit, an analysis unit, and a countermeasure unit. The selection unit selects news articles based on the user's interests and browsing history. The summarization unit automatically summarizes the articles selected by the selection unit. The analysis unit analyzes trends based on the articles summarized by the summarization unit. The countermeasure unit detects clickbait based on the trends analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can select news articles based on the user's interests and browsing history, and provide reliable information. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An information provision system according to an embodiment of the present invention is a system that allows users to easily grasp the latest AI information without specialized knowledge by providing personalized feeds and summarization functions. Based on the user's interests and browsing history, the AI ​​selects the most suitable news articles for each individual and provides a personalized feed. Next, the AI ​​automatically summarizes long articles and presents the important points as "Key Takeaways." This allows the user to grasp the main points of the article in a short time. In addition, the AI ​​analyzes currently trending topics and news, compiles particularly important news as "Top Stories," and displays them preferentially to the user. Furthermore, as a measure against clickbait, the user flags clickbait-like articles, and the AI ​​detects them and rewrites them with reliable information. This allows users to confidently use AI in their daily lives and work and efficiently obtain the latest information in a limited time. For example, the information provision system selects news articles based on the user's interests and browsing history. For example, the information provision system automatically summarizes long articles and presents the important points as "Key Takeaways." For example, the information provision system analyzes currently trending topics and news, compiles particularly important news as "Top Stories," and displays it preferentially to users. For instance, the system allows users to flag clickbait articles, and the AI ​​detects and rewrites them into more reliable information. This enables the information provision system to empower users to confidently utilize AI in their daily lives and work, and to efficiently obtain the latest information within a limited time. In this way, the information provision system can contribute to advancing the world that SoftBank aims for by deepening users' understanding of AI and fostering positive feelings towards it.

[0029] The information provision system according to this embodiment comprises a selection unit, a summarization unit, an analysis unit, and a countermeasure unit. The selection unit selects news articles based on the user's interests and browsing history. The selection unit analyzes, for example, the user's past browsing history, search history, and social media activity to select the most suitable news articles. The selection unit can also filter news articles based on the user's current areas of interest. For example, the selection unit prioritizes selecting articles related to keywords recently searched by the user. The summarization unit automatically summarizes the articles selected by the selection unit. For example, the summarization unit automatically summarizes long articles and presents key points as "Key Takeaways." The summarization unit can extract the main points of an article and summarize them concisely using natural language processing technology and machine learning algorithms. The analysis unit analyzes trends based on the articles summarized by the summarization unit. For example, the analysis unit analyzes currently trending topics and trends, compiles particularly important news as "Top Stories," and displays them preferentially to the user. The analysis unit can identify trends by extracting frequently occurring keywords and analyzing changes over time. The countermeasures unit detects clickbait based on trends analyzed by the analysis unit. For example, the countermeasures unit flags clickbait-like articles as users flag them, and the AI ​​detects them and rewrites them into reliable information. The countermeasures unit can identify clickbait by analyzing the frequency of occurrence of specific keywords and user response patterns. As a result, the information provision system according to this embodiment can provide reliable information by selecting news articles based on the user's interests and browsing history, summarizing them, performing trend analysis, and detecting clickbait.

[0030] The selection unit selects news articles based on the user's interests and browsing history. For example, it analyzes the user's past browsing history, search history, and social media activity to select the most relevant news articles. Specifically, the selection unit analyzes the user's browser history and search engine query logs to identify topics the user has been interested in in the past. It also collects social media activity data and analyzes the content of posts the user has "liked" or "shared" to understand their current areas of interest. Furthermore, the selection unit can utilize location and time-of-day data collected from the user's device to prioritize news articles related to specific regions or time periods. For example, if a user is staying in a particular city, it will prioritize displaying local news related to that city. The selection unit can also learn the user's past behavior patterns and build machine learning models to predict future interests. As a result, the selection unit can comprehensively analyze diverse user data and provide news articles optimized for each individual user.

[0031] The summarization section automatically summarizes articles selected by the selection section. For example, the summarization section can automatically summarize a long article and present the key points as "Key Takeaways." Specifically, the summarization section can extract the main points of an article and summarize them concisely using natural language processing technology and machine learning algorithms. First, the summarization section analyzes the entire article and applies a scoring algorithm to evaluate the importance of each sentence. Next, it selects the most important sentences and combines them to generate a summary. Furthermore, the summarization section can present the summary in a heading or bulleted list format to make the article easier to understand. For example, the summarization section can list the main points of an article as "Key Takeaways" in bullet points, allowing users to grasp the important information in a short time. The summarization section can also convert articles written in different languages ​​into multilingual summaries, enabling it to provide useful information to a global user base. In this way, the summarization section provides support for users to efficiently acquire and understand information.

[0032] The analysis department analyzes trends based on articles summarized by the summarization department. For example, the analysis department analyzes currently trending topics and trends, compiles particularly important news as "Top Stories," and displays it preferentially to users. Specifically, the analysis department analyzes the content of summarized articles and extracts frequently occurring keywords and phrases. This allows it to evaluate how much attention a particular topic is receiving. The analysis department can also analyze changes over time to identify when trends started and when they peaked. For example, it can identify periods when a particular keyword surged and analyze the events and factors behind it. Furthermore, the analysis department can integrate data collected from different sources to conduct comprehensive trend analysis. This allows the analysis department to provide users with the latest trend information and help them avoid missing important news. The analysis department can also build models to predict future trends based on historical data. This allows users to know in advance about topics that are likely to attract attention in the future.

[0033] The countermeasures department detects clickbait based on trends analyzed by the analysis department. For example, users flag clickbait-like articles, and the AI ​​detects and rewrites them with reliable information. Specifically, the countermeasures department can identify clickbait by analyzing the frequency of occurrence of specific keywords and user response patterns. First, the countermeasures department analyzes the title and content of articles and applies natural language processing techniques to detect overly exaggerated expressions and misleading phrases. Next, it analyzes user response data such as click history, time spent on the site, and comments to identify user response patterns to clickbait-like articles. Furthermore, the countermeasures department evaluates the reliability of articles by comparing them with data from reliable sources. For example, it cross-references multiple sources on the same topic to eliminate unreliable information. The countermeasures department can also collect user feedback and continuously improve the accuracy of its clickbait detection algorithm. This allows the countermeasures department to provide users with reliable information and prevent confusion caused by misinformation and clickbait.

[0034] The selection unit can analyze the user's past browsing history and select the most relevant news articles. For example, the selection unit can prioritize articles from categories that the user has frequently viewed in the past. It can also analyze the trends of articles that the user has previously given high ratings to and select similar articles. Furthermore, the selection unit can analyze the characteristics of articles that the user has viewed for extended periods in the past and select articles with similar characteristics. This allows the system to provide more relevant news articles by analyzing the user's past browsing history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's past browsing history data into a generating AI and have the generating AI select the most relevant news articles.

[0035] The selection unit can filter news articles based on the user's current areas of interest. For example, the selection unit can prioritize articles related to keywords the user has recently searched for. It can also select articles related to events the user has recently attended. Furthermore, the selection unit can select articles based on the content of newsletters the user has recently subscribed to. This allows for the provision of more interesting articles by filtering news articles based on the user's current areas of interest. Some or all of the above processing in the selection unit may be performed using AI, for example, or not. For example, the selection unit can input the user's current areas of interest data into a generating AI and have the generating AI perform the filtering of news articles.

[0036] The selection unit can prioritize selecting news articles that are highly relevant, taking into account the user's geographical location. For example, the selection unit can prioritize local news related to the user's current location. Furthermore, if the user is traveling, the selection unit can select news related to their travel destination. In addition, based on the user's geographical location, the selection unit can select articles that include local events and weather information. This allows for the provision of more relevant news articles by considering the user's geographical location. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's geographical location data into a generating AI and have the generating AI select highly relevant news articles.

[0037] The selection unit can analyze a user's social media activity and select relevant articles when choosing news articles. For example, the selection unit can select news related to articles the user has shared on social media. It can also select articles based on the content of posts from accounts the user follows on social media. Furthermore, the selection unit can select articles related to topics in groups the user participates in on social media. This allows for the provision of more relevant news articles by analyzing the user's social media activity. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's social media activity data into a generating AI and have the generating AI perform the selection of relevant news articles.

[0038] The summarization unit can adjust the level of detail in the summary based on the importance of the article during summary generation. For example, the summarization unit can provide a detailed summary for highly important articles. It can also provide a concise summary for less important articles. Furthermore, it can provide a summary with a moderate level of detail for articles of moderate importance. By adjusting the level of detail in the summary based on the importance of the article, a more appropriate summary can be provided. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input article importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0039] The summarization unit can apply different summarization algorithms depending on the article category when generating summaries. For example, the summarization unit can apply a summarization algorithm that includes technical details to technology articles. It can also apply a summarization algorithm that emphasizes storytelling to entertainment articles. Furthermore, it can apply a summarization algorithm that emphasizes statistical data to business articles. By applying different summarization algorithms depending on the article category, it is possible to provide more appropriate summaries. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input article category data into a generation AI and have the generation AI perform the application of the summarization algorithm.

[0040] The summarization unit can determine the priority of summaries based on the publication date of the articles when generating summaries. For example, the summarization unit will prioritize summaries for the most recent articles. It can also lower the priority of summaries for older articles. Furthermore, the summarization unit can set a priority for articles related to a specific period, according to that period. This allows for the provision of more appropriate summaries by determining the priority of summaries based on the publication date of the articles. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input article publication date data into a generation AI and have the generation AI perform the determination of the summary priority.

[0041] The summarization unit can adjust the order of summaries based on the relevance of the articles during summary generation. For example, the summarization unit can set highly relevant articles higher in the summary order. It can also set less relevant articles lower in the summary order. Furthermore, it can set articles of moderate relevance to an appropriate order. By adjusting the order of summaries based on the relevance of the articles, a more appropriate summary can be provided. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input article relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0042] The analysis unit can improve the accuracy of trend analysis by considering the interrelationships between articles. For example, the analysis unit can analyze links between related articles to clarify the correlation of trends. It can also analyze the sources cited in articles to identify reliable trends. Furthermore, the analysis unit can analyze common keywords in articles to clarify the themes of trends. This improves the accuracy of trend analysis by considering the interrelationships between articles. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input interrelationship data between articles into a generating AI and have the generating AI perform the task of improving the accuracy of trend analysis.

[0043] The analysis unit can perform trend analysis while considering the attribute information of the article's author. For example, the analysis unit can consider the article's author's field of expertise to identify specialized trends. The analysis unit can also evaluate the reliability of the article's author and identify reliable trends. Furthermore, the analysis unit can analyze the article's author's past posting history to identify consistent trends. This allows for more reliable trend analysis by considering the attribute information of the article's author. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the article's author attribute information data into a generating AI and have the generating AI perform the trend analysis.

[0044] The analysis unit can perform trend analysis while considering the geographical distribution of articles. For example, the analysis unit can analyze the origin of articles and identify trends in each region. It can also analyze the geographical distribution of article readers and identify interests in each region. Furthermore, the analysis unit can analyze the geographical scope of articles and identify the impact of trends in each region. By considering the geographical distribution of articles, it is possible to provide more region-specific trend analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical distribution data of articles into a generating AI and have the generating AI perform the trend analysis.

[0045] The analysis unit can improve the accuracy of its analysis by referring to relevant literature for articles during trend analysis. For example, the analysis unit can refer to relevant academic papers to improve the reliability of the trend. It can also refer to relevant news articles to clarify the breadth of the trend. Furthermore, the analysis unit can refer to relevant blog posts to clarify the diversity of the trend. In this way, the accuracy of trend analysis is improved by referring to relevant literature for articles. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the relevant literature data for articles into a generating AI and have the generating AI perform the task of improving the accuracy of the trend analysis.

[0046] The countermeasures unit can improve the accuracy of clickbait detection by considering the interrelationships between articles. For example, the unit can analyze links between related articles to clarify the correlation between clickbait. The unit can also analyze the sources of citations in articles to identify reliable information. Furthermore, the unit can analyze common keywords in articles to clarify the themes of the clickbait. This improves the accuracy of clickbait detection by considering the interrelationships between articles. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or without AI. For example, the countermeasures unit can input interrelationship data between articles into a generating AI and have the generating AI perform the task of improving the accuracy of clickbait detection.

[0047] The countermeasures unit can perform clickbait detection while considering the attribute information of the article's author. For example, the unit can consider the article's author's field of expertise to identify specialized clickbait. The unit can also evaluate the reliability of the article's author and identify reliable information. Furthermore, the unit can analyze the article's author's past posting history to identify consistent information. By considering the attribute information of the article's author, a more reliable clickbait detection can be provided. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or without AI. For example, the countermeasures unit can input the article's author attribute information data into a generating AI and have the generating AI perform clickbait detection.

[0048] The countermeasures unit can perform clickbait detection while considering the geographical distribution of articles. For example, the unit can analyze the origin of articles and identify clickbait for each region. It can also analyze the geographical distribution of article readers and identify interests for each region. Furthermore, the unit can analyze the geographical scope of influence of articles and identify the impact of clickbait for each region. By considering the geographical distribution of articles, it is possible to provide more region-specific clickbait detection. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or without AI. For example, the countermeasures unit can input geographical distribution data of articles into a generating AI and have the generating AI perform clickbait detection.

[0049] The countermeasures unit can improve the accuracy of clickbait detection by referring to related literature for the article. For example, the unit can refer to related academic papers to improve the reliability of the clickbait. The unit can also refer to related news articles to clarify the spread of the clickbait. Furthermore, the unit can refer to related blog posts to clarify the diversity of the clickbait. In this way, the accuracy of clickbait detection is improved by referring to related literature for the article. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or not using AI. For example, the countermeasures unit can input related literature data for the article into a generating AI and have the generating AI perform the task of improving the accuracy of clickbait detection.

[0050] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0051] The selection unit can adjust the criteria for selecting news articles based on the user's musical preferences. For example, if the user prefers classical music, the selection unit will prioritize articles related to culture and history. If the user prefers pop music, the selection unit can also select articles related to entertainment and trends. Furthermore, if the user prefers jazz music, the selection unit can select articles related to creativity and art. This allows for the provision of more interesting articles by adjusting the selection criteria according to the user's musical preferences. Music preference data can be obtained, for example, from music streaming services or the user's playlists. Some or all of the processing described above in the selection unit may be performed using AI, or not. For example, the selection unit can input the user's musical preference data into a generating AI and have the generating AI adjust the news article selection criteria based on musical preferences.

[0052] The summarization unit can estimate the user's reading speed and adjust the length of the summary based on the estimated reading speed. For example, if the user is good at speed reading, the summarization unit can provide a detailed summary. If the user reads slowly, the summarization unit can also provide a concise summary. Furthermore, if the user has a moderate reading speed, the summarization unit can provide a summary of appropriate length. This allows for the provision of more appropriate summaries by adjusting the length of the summary according to the user's reading speed. Estimation of reading speed is achieved, for example, by analyzing the user's past reading history and scrolling speed. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the user's reading speed data into a generating AI and have the generating AI adjust the length of the summary based on the reading speed.

[0053] The selection unit can analyze the user's purchase history and adjust the criteria for selecting news articles based on that history. For example, the selection unit can prioritize articles related to products the user has recently purchased. It can also select articles related to products the user has previously given high ratings to. Furthermore, it can select articles related to products in categories that the user frequently purchases. This allows for the provision of more relevant articles by adjusting the news article selection criteria according to the user's purchase history. Purchase history data can be obtained, for example, from online shopping sites or loyalty card history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's purchase history data into a generating AI and have the generating AI adjust the news article selection criteria based on the purchase history.

[0054] The summarization unit can evaluate the reliability of an article and adjust the level of detail in the summary based on that reliability. For example, the summarization unit can provide a detailed summary for highly reliable articles. It can also provide a concise summary for less reliable articles. Furthermore, it can provide a summary with a moderate level of detail for articles of moderate reliability. This allows for the provision of more appropriate summaries by adjusting the level of detail in the summary based on the article's reliability. Reliability is evaluated, for example, by analyzing the reliability of the article's sources and authors. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input article reliability data into a generating AI and have the generating AI perform the adjustment of the level of detail in the summary based on reliability.

[0055] The analysis unit can adjust the criteria for trend analysis based on the user's occupation. For example, if the user is in a technical profession, the analysis unit can provide a trend analysis that focuses on technical topics. Similarly, if the user is in a marketing profession, the analysis unit can provide a trend analysis that focuses on marketing-related topics. Furthermore, if the user is in an education profession, the analysis unit can provide a trend analysis that focuses on education-related topics. This allows for the provision of more relevant trend analysis by adjusting the criteria according to the user's occupation. Occupational data can be obtained, for example, from the user's profile information or work history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's occupational data into a generating AI and have the generating AI perform the adjustment of the trend analysis criteria based on occupation.

[0056] The countermeasures unit can evaluate the reliability of news articles and adjust the criteria for clickbait detection based on that reliability. For example, the unit can detect clickbait using lenient criteria for highly reliable articles. It can also detect clickbait using strict criteria for less reliable articles. Furthermore, it can detect clickbait using moderate criteria for articles of moderate reliability. By adjusting the criteria for clickbait detection based on the reliability of news articles, it is possible to provide more appropriate clickbait detection. Reliability evaluation is achieved, for example, by analyzing the reliability of the sources and authors cited in the article. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or not using AI. For example, the countermeasures unit can input reliability data of news articles into a generating AI and have the generating AI perform adjustments to the clickbait detection criteria based on reliability.

[0057] The following briefly describes the processing flow for example form 1.

[0058] Step 1: The selection unit selects news articles based on the user's interests and browsing history. The selection unit analyzes, for example, the user's past browsing history, search history, and social media activity to select the most relevant news articles. The selection unit can also filter news articles based on the user's current areas of interest. For example, the selection unit prioritizes articles related to keywords the user has recently searched for. Step 2: The summarization section automatically summarizes the articles selected by the selection section. For example, the summarization section can automatically summarize a long article and present the key points as "Key Takeaways." The summarization section can use natural language processing techniques and machine learning algorithms to extract the main points of an article and summarize them concisely. Step 3: The analysis unit analyzes trends based on the articles summarized by the summarization unit. For example, the analysis unit analyzes currently trending topics and news, compiles particularly important news as "Top Stories," and displays them preferentially to users. The analysis unit can identify trends by extracting frequently occurring keywords and analyzing changes over time. Step 4: The countermeasures team detects clickbait based on trends analyzed by the analysis team. For example, the countermeasures team flags clickbait-like articles as users flag them, and the AI ​​detects and rewrites them into reliable information. The countermeasures team can identify clickbait by analyzing the frequency of occurrence of specific keywords and user response patterns.

[0059] (Example of form 2) An information provision system according to an embodiment of the present invention is a system that allows users to easily grasp the latest AI information without specialized knowledge by providing personalized feeds and summarization functions. Based on the user's interests and browsing history, the AI ​​selects the most suitable news articles for each individual and provides a personalized feed. Next, the AI ​​automatically summarizes long articles and presents the important points as "Key Takeaways." This allows the user to grasp the main points of the article in a short time. In addition, the AI ​​analyzes currently trending topics and news, compiles particularly important news as "Top Stories," and displays them preferentially to the user. Furthermore, as a measure against clickbait, the user flags clickbait-like articles, and the AI ​​detects them and rewrites them with reliable information. This allows users to confidently use AI in their daily lives and work and efficiently obtain the latest information in a limited time. For example, the information provision system selects news articles based on the user's interests and browsing history. For example, the information provision system automatically summarizes long articles and presents the important points as "Key Takeaways." For example, the information provision system analyzes currently trending topics and news, compiles particularly important news as "Top Stories," and displays it preferentially to users. For instance, the system allows users to flag clickbait articles, and the AI ​​detects and rewrites them into more reliable information. This enables the information provision system to empower users to confidently utilize AI in their daily lives and work, and to efficiently obtain the latest information within a limited time. In this way, the information provision system can contribute to advancing the world that SoftBank aims for by deepening users' understanding of AI and fostering positive feelings towards it.

[0060] The information provision system according to this embodiment comprises a selection unit, a summarization unit, an analysis unit, and a countermeasure unit. The selection unit selects news articles based on the user's interests and browsing history. The selection unit analyzes, for example, the user's past browsing history, search history, and social media activity to select the most suitable news articles. The selection unit can also filter news articles based on the user's current areas of interest. For example, the selection unit prioritizes selecting articles related to keywords recently searched by the user. The summarization unit automatically summarizes the articles selected by the selection unit. For example, the summarization unit automatically summarizes long articles and presents key points as "Key Takeaways." The summarization unit can extract the main points of an article and summarize them concisely using natural language processing technology and machine learning algorithms. The analysis unit analyzes trends based on the articles summarized by the summarization unit. For example, the analysis unit analyzes currently trending topics and trends, compiles particularly important news as "Top Stories," and displays them preferentially to the user. The analysis unit can identify trends by extracting frequently occurring keywords and analyzing changes over time. The countermeasures unit detects clickbait based on trends analyzed by the analysis unit. For example, the countermeasures unit flags clickbait-like articles as users flag them, and the AI ​​detects them and rewrites them into reliable information. The countermeasures unit can identify clickbait by analyzing the frequency of occurrence of specific keywords and user response patterns. As a result, the information provision system according to this embodiment can provide reliable information by selecting news articles based on the user's interests and browsing history, summarizing them, performing trend analysis, and detecting clickbait.

[0061] The selection unit selects news articles based on the user's interests and browsing history. For example, it analyzes the user's past browsing history, search history, and social media activity to select the most relevant news articles. Specifically, the selection unit analyzes the user's browser history and search engine query logs to identify topics the user has been interested in in the past. It also collects social media activity data and analyzes the content of posts the user has "liked" or "shared" to understand their current areas of interest. Furthermore, the selection unit can utilize location and time-of-day data collected from the user's device to prioritize news articles related to specific regions or time periods. For example, if a user is staying in a particular city, it will prioritize displaying local news related to that city. The selection unit can also learn the user's past behavior patterns and build machine learning models to predict future interests. As a result, the selection unit can comprehensively analyze diverse user data and provide news articles optimized for each individual user.

[0062] The summarization section automatically summarizes articles selected by the selection section. For example, the summarization section can automatically summarize a long article and present the key points as "Key Takeaways." Specifically, the summarization section can extract the main points of an article and summarize them concisely using natural language processing technology and machine learning algorithms. First, the summarization section analyzes the entire article and applies a scoring algorithm to evaluate the importance of each sentence. Next, it selects the most important sentences and combines them to generate a summary. Furthermore, the summarization section can present the summary in a heading or bulleted list format to make the article easier to understand. For example, the summarization section can list the main points of an article as "Key Takeaways" in bullet points, allowing users to grasp the important information in a short time. The summarization section can also convert articles written in different languages ​​into multilingual summaries, enabling it to provide useful information to a global user base. In this way, the summarization section provides support for users to efficiently acquire and understand information.

[0063] The analysis department analyzes trends based on articles summarized by the summarization department. For example, the analysis department analyzes currently trending topics and trends, compiles particularly important news as "Top Stories," and displays it preferentially to users. Specifically, the analysis department analyzes the content of summarized articles and extracts frequently occurring keywords and phrases. This allows it to evaluate how much attention a particular topic is receiving. The analysis department can also analyze changes over time to identify when trends started and when they peaked. For example, it can identify periods when a particular keyword surged and analyze the events and factors behind it. Furthermore, the analysis department can integrate data collected from different sources to conduct comprehensive trend analysis. This allows the analysis department to provide users with the latest trend information and help them avoid missing important news. The analysis department can also build models to predict future trends based on historical data. This allows users to know in advance about topics that are likely to attract attention in the future.

[0064] The countermeasures department detects clickbait based on trends analyzed by the analysis department. For example, users flag clickbait-like articles, and the AI ​​detects and rewrites them with reliable information. Specifically, the countermeasures department can identify clickbait by analyzing the frequency of occurrence of specific keywords and user response patterns. First, the countermeasures department analyzes the title and content of articles and applies natural language processing techniques to detect overly exaggerated expressions and misleading phrases. Next, it analyzes user response data such as click history, time spent on the site, and comments to identify user response patterns to clickbait-like articles. Furthermore, the countermeasures department evaluates the reliability of articles by comparing them with data from reliable sources. For example, it cross-references multiple sources on the same topic to eliminate unreliable information. The countermeasures department can also collect user feedback and continuously improve the accuracy of its clickbait detection algorithm. This allows the countermeasures department to provide users with reliable information and prevent confusion caused by misinformation and clickbait.

[0065] The selection unit can estimate the user's emotions and adjust the criteria for selecting news articles based on the estimated emotions. For example, if the user is stressed, the selection unit will prioritize articles with relaxing content. It can also prioritize articles with stimulating content if the user is excited. Furthermore, if the user is tired, it can prioritize articles with easily understandable content. This allows for the provision of more appropriate articles by adjusting the news article selection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, or not. For example, the selection unit can input user emotion data into a generative AI and have the generative AI adjust the news article selection criteria based on emotions.

[0066] The selection unit can analyze the user's past browsing history and select the most relevant news articles. For example, the selection unit can prioritize articles from categories that the user has frequently viewed in the past. It can also analyze the trends of articles that the user has previously given high ratings to and select similar articles. Furthermore, the selection unit can analyze the characteristics of articles that the user has viewed for extended periods in the past and select articles with similar characteristics. This allows the system to provide more relevant news articles by analyzing the user's past browsing history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's past browsing history data into a generating AI and have the generating AI select the most relevant news articles.

[0067] The selection unit can filter news articles based on the user's current areas of interest. For example, the selection unit can prioritize articles related to keywords the user has recently searched for. It can also select articles related to events the user has recently attended. Furthermore, the selection unit can select articles based on the content of newsletters the user has recently subscribed to. This allows for the provision of more interesting articles by filtering news articles based on the user's current areas of interest. Some or all of the above processing in the selection unit may be performed using AI, for example, or not. For example, the selection unit can input the user's current areas of interest data into a generating AI and have the generating AI perform the filtering of news articles.

[0068] The selection unit can estimate the user's emotions and determine the priority of news articles to select based on the estimated emotions. For example, if the user is relaxed, the selection unit will prioritize displaying articles with relaxing content. If the user is excited, the selection unit can also prioritize displaying articles with stimulating content. Furthermore, if the user is tired, the selection unit can prioritize displaying articles with easy-to-understand content. In this way, by prioritizing news articles according to the user's emotions, more appropriate articles can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input user emotion data into a generative AI and have the generative AI determine the priority of news articles.

[0069] The selection unit can prioritize selecting news articles that are highly relevant, taking into account the user's geographical location. For example, the selection unit can prioritize local news related to the user's current location. Furthermore, if the user is traveling, the selection unit can select news related to their travel destination. In addition, based on the user's geographical location, the selection unit can select articles that include local events and weather information. This allows for the provision of more relevant news articles by considering the user's geographical location. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's geographical location data into a generating AI and have the generating AI select highly relevant news articles.

[0070] The selection unit can analyze a user's social media activity and select relevant articles when choosing news articles. For example, the selection unit can select news related to articles the user has shared on social media. It can also select articles based on the content of posts from accounts the user follows on social media. Furthermore, the selection unit can select articles related to topics in groups the user participates in on social media. This allows for the provision of more relevant news articles by analyzing the user's social media activity. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's social media activity data into a generating AI and have the generating AI perform the selection of relevant news articles.

[0071] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the user is relaxed, the summarization unit can provide a summary in a gentle tone. If the user is in a hurry, the summarization unit can provide a concise and to-the-point summary. Furthermore, if the user is excited, the summarization unit can provide a visually stimulating summary. In this way, by adjusting the way the summary is presented according to the user's emotions, a more appropriate summary can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the way the summary is presented.

[0072] The summarization unit can adjust the level of detail in the summary based on the importance of the article during summary generation. For example, the summarization unit can provide a detailed summary for highly important articles. It can also provide a concise summary for less important articles. Furthermore, it can provide a summary with a moderate level of detail for articles of moderate importance. By adjusting the level of detail in the summary based on the importance of the article, a more appropriate summary can be provided. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input article importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0073] The summarization unit can apply different summarization algorithms depending on the article category when generating summaries. For example, the summarization unit can apply a summarization algorithm that includes technical details to technology articles. It can also apply a summarization algorithm that emphasizes storytelling to entertainment articles. Furthermore, it can apply a summarization algorithm that emphasizes statistical data to business articles. By applying different summarization algorithms depending on the article category, it is possible to provide more appropriate summaries. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input article category data into a generation AI and have the generation AI perform the application of the summarization algorithm.

[0074] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, if the user is in a hurry, the summarization unit can provide a short, concise summary. If the user is relaxed, the summarization unit can provide a longer summary with more detailed explanations. Furthermore, if the user is excited, the summarization unit can provide a visually stimulating summary. By adjusting the length of the summary according to the user's emotions, a more appropriate summary can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the length of the summary.

[0075] The summarization unit can determine the priority of summaries based on the publication date of the articles when generating summaries. For example, the summarization unit will prioritize summaries for the most recent articles. It can also lower the priority of summaries for older articles. Furthermore, the summarization unit can set a priority for articles related to a specific period, according to that period. This allows for the provision of more appropriate summaries by determining the priority of summaries based on the publication date of the articles. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not. For example, the summarization unit can input article publication date data into a generation AI and have the generation AI perform the determination of the summary priority.

[0076] The summarization unit can adjust the order of summaries based on the relevance of the articles during summary generation. For example, the summarization unit can set highly relevant articles higher in the summary order. It can also set less relevant articles lower in the summary order. Furthermore, it can set articles of moderate relevance to an appropriate order. By adjusting the order of summaries based on the relevance of the articles, a more appropriate summary can be provided. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input article relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0077] The analysis unit can estimate the user's emotions and adjust the criteria for trend analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit can provide a trend analysis that includes a wide range of topics. If the user is in a hurry, the analysis unit can also provide a trend analysis that focuses on important topics. Furthermore, if the user is excited, the analysis unit can provide a visually stimulating trend analysis. This allows for the provision of more appropriate trend analysis by adjusting the criteria for trend analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI adjust the criteria for trend analysis.

[0078] The analysis unit can improve the accuracy of trend analysis by considering the interrelationships between articles. For example, the analysis unit can analyze links between related articles to clarify the correlation of trends. It can also analyze the sources cited in articles to identify reliable trends. Furthermore, the analysis unit can analyze common keywords in articles to clarify the themes of trends. This improves the accuracy of trend analysis by considering the interrelationships between articles. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not. For example, the analysis unit can input interrelationship data between articles into a generating AI and have the generating AI perform the task of improving the accuracy of trend analysis.

[0079] The analysis unit can perform trend analysis while considering the attribute information of the article's author. For example, the analysis unit can consider the article's author's field of expertise to identify specialized trends. The analysis unit can also evaluate the reliability of the article's author and identify reliable trends. Furthermore, the analysis unit can analyze the article's author's past posting history to identify consistent trends. This allows for more reliable trend analysis by considering the attribute information of the article's author. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the article's author attribute information data into a generating AI and have the generating AI perform the trend analysis.

[0080] The analysis unit can estimate the user's emotions and adjust the order in which trend analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, the analysis unit can display trend analysis results containing a wide range of topics at the top. If the user is in a hurry, the analysis unit can also display trend analysis results focused on important topics at the top. Furthermore, if the user is excited, the analysis unit can display trend analysis results that are visually stimulating at the top. This allows for the provision of more appropriate trend analysis results by adjusting the order in which trend analysis results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI adjust the display order of trend analysis results.

[0081] The analysis unit can perform trend analysis while considering the geographical distribution of articles. For example, the analysis unit can analyze the origin of articles and identify trends in each region. It can also analyze the geographical distribution of article readers and identify interests in each region. Furthermore, the analysis unit can analyze the geographical scope of articles and identify the impact of trends in each region. By considering the geographical distribution of articles, it is possible to provide more region-specific trend analysis. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input geographical distribution data of articles into a generating AI and have the generating AI perform the trend analysis.

[0082] The analysis unit can improve the accuracy of its analysis by referring to relevant literature for articles during trend analysis. For example, the analysis unit can refer to relevant academic papers to improve the reliability of the trend. It can also refer to relevant news articles to clarify the breadth of the trend. Furthermore, the analysis unit can refer to relevant blog posts to clarify the diversity of the trend. In this way, the accuracy of trend analysis is improved by referring to relevant literature for articles. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input the relevant literature data for articles into a generating AI and have the generating AI perform the task of improving the accuracy of the trend analysis.

[0083] The mitigation unit can estimate the user's emotions and adjust the clickbait detection criteria based on the estimated emotions. For example, if the user is relaxed, the mitigation unit can detect clickbait using broad criteria. If the user is in a hurry, the mitigation unit can also detect clickbait using strict criteria. Furthermore, if the user is excited, the mitigation unit can detect clickbait using visually stimulating criteria. This allows for more appropriate clickbait detection by adjusting the clickbait detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the mitigation unit may be performed using AI or not. For example, the mitigation unit can input user emotion data into a generative AI and have the generative AI adjust the clickbait detection criteria.

[0084] The countermeasures unit can improve the accuracy of clickbait detection by considering the interrelationships between articles. For example, the unit can analyze links between related articles to clarify the correlation between clickbait. The unit can also analyze the sources of citations in articles to identify reliable information. Furthermore, the unit can analyze common keywords in articles to clarify the themes of the clickbait. This improves the accuracy of clickbait detection by considering the interrelationships between articles. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or without AI. For example, the countermeasures unit can input interrelationship data between articles into a generating AI and have the generating AI perform the task of improving the accuracy of clickbait detection.

[0085] The countermeasures unit can perform clickbait detection while considering the attribute information of the article's author. For example, the unit can consider the article's author's field of expertise to identify specialized clickbait. The unit can also evaluate the reliability of the article's author and identify reliable information. Furthermore, the unit can analyze the article's author's past posting history to identify consistent information. By considering the attribute information of the article's author, a more reliable clickbait detection can be provided. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or without AI. For example, the countermeasures unit can input the article's author attribute information data into a generating AI and have the generating AI perform clickbait detection.

[0086] The Response Unit can estimate the user's emotions and adjust the order in which clickbait detection results are displayed based on the estimated user emotions. For example, if the user is relaxed, the Response Unit can display clickbait detection results higher up based on broad criteria. It can also display clickbait detection results higher up based on strict criteria if the user is in a hurry. Furthermore, if the user is excited, the Response Unit can display clickbait detection results higher up based on visually stimulating criteria. This allows for more appropriate clickbait detection results by adjusting the order in which clickbait detection results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the Response Unit may be performed using AI, or not. For example, the Response Unit can input user emotion data into a generative AI and have the generative AI adjust the display order of clickbait detection results.

[0087] The countermeasures unit can perform clickbait detection while considering the geographical distribution of articles. For example, the unit can analyze the origin of articles and identify clickbait for each region. It can also analyze the geographical distribution of article readers and identify interests for each region. Furthermore, the unit can analyze the geographical scope of influence of articles and identify the impact of clickbait for each region. By considering the geographical distribution of articles, it is possible to provide more region-specific clickbait detection. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or without AI. For example, the countermeasures unit can input geographical distribution data of articles into a generating AI and have the generating AI perform clickbait detection.

[0088] The countermeasures unit can improve the accuracy of clickbait detection by referring to related literature for the article. For example, the unit can refer to related academic papers to improve the reliability of the clickbait. The unit can also refer to related news articles to clarify the spread of the clickbait. Furthermore, the unit can refer to related blog posts to clarify the diversity of the clickbait. In this way, the accuracy of clickbait detection is improved by referring to related literature for the article. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or not using AI. For example, the countermeasures unit can input related literature data for the article into a generating AI and have the generating AI perform the task of improving the accuracy of clickbait detection.

[0089] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0090] The selection unit can monitor the user's health status and adjust the criteria for selecting news articles based on that status. For example, if the user is feeling fatigued, the selection unit will prioritize articles with relaxing content. It can also select articles that help reduce stress if the user is feeling stressed. Furthermore, if the user is in good health, the selection unit can select articles on interesting topics. This allows for the provision of more appropriate articles by adjusting the news article selection criteria according to the user's health status. Health status monitoring can be achieved, for example, using sensors in wearable devices or smartphones. Some or all of the above-described processes in the selection unit may be performed using AI, or not. For example, the selection unit can input the user's health data into a generating AI and have the generating AI adjust the news article selection criteria based on the user's health status.

[0091] The selection unit can adjust the criteria for selecting news articles based on the user's musical preferences. For example, if the user prefers classical music, the selection unit will prioritize articles related to culture and history. If the user prefers pop music, the selection unit can also select articles related to entertainment and trends. Furthermore, if the user prefers jazz music, the selection unit can select articles related to creativity and art. This allows for the provision of more interesting articles by adjusting the selection criteria according to the user's musical preferences. Music preference data can be obtained, for example, from music streaming services or the user's playlists. Some or all of the processing described above in the selection unit may be performed using AI, or not. For example, the selection unit can input the user's musical preference data into a generating AI and have the generating AI adjust the news article selection criteria based on musical preferences.

[0092] The summarization unit can estimate the user's reading speed and adjust the length of the summary based on the estimated reading speed. For example, if the user is good at speed reading, the summarization unit can provide a detailed summary. If the user reads slowly, the summarization unit can also provide a concise summary. Furthermore, if the user has a moderate reading speed, the summarization unit can provide a summary of appropriate length. This allows for the provision of more appropriate summaries by adjusting the length of the summary according to the user's reading speed. Estimation of reading speed is achieved, for example, by analyzing the user's past reading history and scrolling speed. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the user's reading speed data into a generating AI and have the generating AI adjust the length of the summary based on the reading speed.

[0093] The summarization unit can estimate the user's emotions and adjust the tone of the summary based on the estimated emotions. For example, if the user is relaxed, the summarization unit can provide a summary in a calm tone. If the user is excited, the summarization unit can provide a summary in a lively tone. Furthermore, if the user is sad, the summarization unit can provide a summary in a comforting tone. By adjusting the tone of the summary according to the user's emotions, a more appropriate summary can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the summary tone.

[0094] The analysis unit can estimate the user's emotions and adjust the format in which the trend analysis results are displayed based on the estimated emotions. For example, if the user is relaxed, the analysis unit can display the trend analysis results in a visually calming format. If the user is excited, the analysis unit can also display the trend analysis results in a visually stimulating format. Furthermore, if the user is in a hurry, the analysis unit can display the trend analysis results in a concise and to-the-point format. By adjusting the format in which the trend analysis results are displayed according to the user's emotions, more appropriate trend analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI adjust the display format of the trend analysis results.

[0095] The countermeasure unit can estimate the user's emotions and adjust the format in which the clickbait detection results are displayed based on the estimated user emotions. For example, if the user is relaxed, the countermeasure unit can display the clickbait detection results in a visually calming format. If the user is excited, the countermeasure unit can also display the clickbait detection results in a visually stimulating format. Furthermore, if the user is in a hurry, the countermeasure unit can display the clickbait detection results in a concise and to-the-point format. In this way, by adjusting the format in which the clickbait detection results are displayed according to the user's emotions, more appropriate clickbait detection results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the countermeasure unit may be performed using AI, for example, or not using AI. For example, the countermeasure unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the display format of the clickbait detection results.

[0096] The selection unit can analyze the user's purchase history and adjust the criteria for selecting news articles based on that history. For example, the selection unit can prioritize articles related to products the user has recently purchased. It can also select articles related to products the user has previously given high ratings to. Furthermore, it can select articles related to products in categories that the user frequently purchases. This allows for the provision of more relevant articles by adjusting the news article selection criteria according to the user's purchase history. Purchase history data can be obtained, for example, from online shopping sites or loyalty card history. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the user's purchase history data into a generating AI and have the generating AI adjust the news article selection criteria based on the purchase history.

[0097] The summarization unit can evaluate the reliability of an article and adjust the level of detail in the summary based on that reliability. For example, the summarization unit can provide a detailed summary for highly reliable articles. It can also provide a concise summary for less reliable articles. Furthermore, it can provide a summary with a moderate level of detail for articles of moderate reliability. This allows for the provision of more appropriate summaries by adjusting the level of detail in the summary based on the article's reliability. Reliability is evaluated, for example, by analyzing the reliability of the article's sources and authors. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input article reliability data into a generating AI and have the generating AI perform the adjustment of the level of detail in the summary based on reliability.

[0098] The analysis unit can adjust the criteria for trend analysis based on the user's occupation. For example, if the user is in a technical profession, the analysis unit can provide a trend analysis that focuses on technical topics. Similarly, if the user is in a marketing profession, the analysis unit can provide a trend analysis that focuses on marketing-related topics. Furthermore, if the user is in an education profession, the analysis unit can provide a trend analysis that focuses on education-related topics. This allows for the provision of more relevant trend analysis by adjusting the criteria according to the user's occupation. Occupational data can be obtained, for example, from the user's profile information or work history. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's occupational data into a generating AI and have the generating AI perform the adjustment of the trend analysis criteria based on occupation.

[0099] The countermeasures unit can evaluate the reliability of news articles and adjust the criteria for clickbait detection based on that reliability. For example, the unit can detect clickbait using lenient criteria for highly reliable articles. It can also detect clickbait using strict criteria for less reliable articles. Furthermore, it can detect clickbait using moderate criteria for articles of moderate reliability. By adjusting the criteria for clickbait detection based on the reliability of news articles, it is possible to provide more appropriate clickbait detection. Reliability evaluation is achieved, for example, by analyzing the reliability of the sources and authors cited in the article. Some or all of the above processing in the countermeasures unit may be performed using AI, for example, or not using AI. For example, the countermeasures unit can input reliability data of news articles into a generating AI and have the generating AI perform adjustments to the clickbait detection criteria based on reliability.

[0100] The following briefly describes the processing flow for example form 2.

[0101] Step 1: The selection unit selects news articles based on the user's interests and browsing history. The selection unit analyzes, for example, the user's past browsing history, search history, and social media activity to select the most relevant news articles. The selection unit can also filter news articles based on the user's current areas of interest. For example, the selection unit prioritizes articles related to keywords the user has recently searched for. Step 2: The summarization section automatically summarizes the articles selected by the selection section. For example, the summarization section can automatically summarize a long article and present the key points as "Key Takeaways." The summarization section can use natural language processing techniques and machine learning algorithms to extract the main points of an article and summarize them concisely. Step 3: The analysis unit analyzes trends based on the articles summarized by the summarization unit. For example, the analysis unit analyzes currently trending topics and news, compiles particularly important news as "Top Stories," and displays them preferentially to users. The analysis unit can identify trends by extracting frequently occurring keywords and analyzing changes over time. Step 4: The countermeasures team detects clickbait based on trends analyzed by the analysis team. For example, the countermeasures team flags clickbait-like articles as users flag them, and the AI ​​detects and rewrites them into reliable information. The countermeasures team can identify clickbait by analyzing the frequency of occurrence of specific keywords and user response patterns.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0104] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0105] Each of the multiple elements described above, including the selection unit, summarization unit, analysis unit, and countermeasure unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the selection unit is implemented by the control unit 46A of the smart device 14 and selects news articles based on the user's interests and browsing history. The summarization unit is implemented by the identification processing unit 290 of the data processing device 12 and automatically summarizes the selected articles and presents the key points as "Key Takeaways". The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes trends based on the summarized articles and compiles particularly important news as "Top Stories". The countermeasure unit is implemented by the control unit 46A of the smart device 14 and detects clickbait articles and rewrites them with more reliable information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0106] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0107] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0112] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0113] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0114] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0115] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0116] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0121] Each of the multiple elements described above, including the selection unit, summarization unit, analysis unit, and countermeasure unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the selection unit is implemented by the control unit 46A of the smart glasses 214 and selects news articles based on the user's interests and browsing history. The summarization unit is implemented by the identification processing unit 290 of the data processing device 12 and automatically summarizes the selected articles and presents the key points as "Key Takeaways". The analysis unit is implemented by the identification processing unit 290 of the data processing device 12 and analyzes trends based on the summarized articles and compiles particularly important news as "Top Stories". The countermeasure unit is implemented by the control unit 46A of the smart glasses 214 and detects clickbait articles and rewrites them with more reliable information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0122] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0123] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0125] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0126] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0128] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0129] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0130] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0131] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0132] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0137] Each of the multiple elements described above, including the selection unit, summarization unit, analysis unit, and countermeasure unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the selection unit is implemented by the control unit 46A of the headset terminal 314 and selects news articles based on the user's interests and browsing history. The summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically summarizes the selected articles and presents the key points as "Key Takeaways". The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes trends based on the summarized articles and compiles particularly important news as "Top Stories". The countermeasure unit is implemented by the control unit 46A of the headset terminal 314 and detects clickbait articles and rewrites them with more reliable information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0138] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0139] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0142] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0144] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0145] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0146] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the selection unit, summarization unit, analysis unit, and countermeasure unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the selection unit is implemented by the control unit 46A of the robot 414 and selects news articles based on the user's interests and browsing history. The summarization unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and automatically summarizes the selected articles and presents the key points as "Key Takeaways". The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes trends based on the summarized articles and compiles particularly important news as "Top Stories". The countermeasure unit is implemented by, for example, the control unit 46A of the robot 414 and detects clickbait articles and rewrites them with more reliable information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0155] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0157] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0158] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0159] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0163] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0164] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0165] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0166] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0167] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0168] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0170] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0171] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0172] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0173] (Note 1) A selection section that selects news articles based on the user's interests and browsing history, A summarization unit that automatically summarizes the articles selected by the selection unit, An analysis unit analyzes trends based on the articles summarized by the aforementioned summary unit, The system includes a countermeasure unit that detects clickbait based on the trend analyzed by the aforementioned analysis unit. A system characterized by the following features. (Note 2) The aforementioned selection unit is We estimate user sentiment and adjust the criteria for selecting news articles based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned selection unit is Analyze the user's past browsing history to select the most relevant news articles. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned selection unit is When selecting news articles, filtering is performed based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned selection unit is It estimates the user's sentiment and determines the priority of news articles to select based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned selection unit is When selecting news articles, the system prioritizes selecting articles that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned selection unit is When selecting news articles, the system analyzes the user's social media activity and selects relevant articles. The system described in Appendix 1, characterized by the features described herein. (Note 8) The summary section above is, It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the article. The system described in Appendix 1, characterized by the features described herein. (Note 10) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the article category. The system described in Appendix 1, characterized by the features described herein. (Note 11) The summary section above is, It estimates the user's sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The summary section above is, When generating summaries, the priority of summaries is determined based on the publication date of the articles. The system described in Appendix 1, characterized by the features described herein. (Note 13) The summary section above is, When generating summaries, the order of the summaries is adjusted based on the relevance of the articles. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is We estimate user sentiment and adjust the criteria for trend analysis based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is When analyzing trends, consider the interrelationships between articles to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is When performing trend analysis, the analysis should take into account the attribute information of the article's author. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is It estimates user sentiment and adjusts the order in which trend analysis results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is When conducting trend analysis, the geographical distribution of articles should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit is When performing trend analysis, referencing related literature in articles improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned countermeasures unit, We estimate user sentiment and adjust clickbait detection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned countermeasures unit, When detecting clickbait, consider the relationships between articles to improve detection accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned countermeasures unit, When detecting clickbait, the system takes into account the attribute information of the article's author. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned countermeasures unit, It estimates the user's sentiment and adjusts the order in which clickbait detection results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned countermeasures unit, When detecting clickbait, the geographical distribution of articles is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned countermeasures unit, When detecting clickbait, we improve the accuracy of the detection by referring to related literature in the article. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A selection section that selects news articles based on the user's interests and browsing history, A summarization unit that automatically summarizes the articles selected by the selection unit, An analysis unit analyzes trends based on the articles summarized by the aforementioned summary unit, The system includes a countermeasure unit that detects clickbait based on the trend analyzed by the aforementioned analysis unit. A system characterized by the following features.

2. The aforementioned selection unit is We estimate user sentiment and adjust the criteria for selecting news articles based on the estimated user sentiment. The system according to feature 1.

3. The aforementioned selection unit is Analyze the user's past browsing history to select the most relevant news articles. The system according to feature 1.

4. The aforementioned selection unit is When selecting news articles, filtering is performed based on the user's current areas of interest. The system according to feature 1.

5. The aforementioned selection unit is It estimates the user's sentiment and determines the priority of news articles to select based on the estimated user sentiment. The system according to feature 1.

6. The aforementioned selection unit is When selecting news articles, the system prioritizes selecting articles that are highly relevant, taking into account the user's geographical location. The system according to feature 1.

7. The aforementioned selection unit is When selecting news articles, the system analyzes the user's social media activity and selects relevant articles. The system according to feature 1.

8. The summary section above is, It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system according to feature 1.

9. The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the article. The system according to feature 1.

Images