System

Abstract

To gain a bird's eye view of information collected from multiple news media.SOLUTION: A system according to an embodiment comprises a collection unit, generation unit, and display unit. The collection unit collects news articles. The generation unit generates summaries of the articles collected by the collection unit using a large-scale language model. The display unit displays a list of the summaries generated by the generation unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional technology had the problem that it was difficult to collect information from multiple news media and obtain an overall understanding of the information.

[0005] The system according to the embodiment aims to provide an overview of information collected from multiple news media. [Means for solving the problem]

[0006] A system according to an embodiment includes a collection unit, a generation unit, and a display unit. The collection unit collects news articles. The generation unit generates summaries of the articles collected by the collection unit using a large-scale language model. The display unit displays a list of the summaries generated by the generation unit. Effect of the Invention

[0007] The system according to the embodiment can provide an overview of information collected from multiple news media. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A news summarization system according to an embodiment of the present invention is a system that collects news articles, generates summaries using a generation AI, and displays them in a list. This news summarization system includes a collection unit that collects news articles, a generation unit that generates summaries from the collected articles using a large-scale language model, and a display unit that displays the generated summaries in a list. For example, the collection unit collects news articles using web scraping technology. The collected articles are sent to the generation unit, and summaries are generated using a large-scale language model (generation AI). The summaries are designed to include the titles, lead sentences, and main points of the body of the articles. The generated summaries are sent to the display unit and displayed in a list to the user. The user can filter the summaries using the filter unit, and can also customize the list display using the customization unit. Furthermore, the collection unit estimates the user's emotions and determines the priority of the news articles to be collected based on the estimated emotions. In addition, the collection unit analyzes the user's past browsing history and selects the optimal collection method. It also has a function of filtering news articles based on specific keywords and topics. This allows the user to collect and obtain information that will affect the market at once, allowing them to grasp the information from a bird's-eye view. This allows the news summarization system to consolidate and obtain all the information that will affect the market at once, enabling users to get a bird's-eye view of the information.

[0029] The news summarization system according to the embodiment includes a collection unit, a generation unit, and a display unit. The collection unit collects news articles. The news articles include, for example, online news, newspaper articles, blog articles, and the like, but are not limited to such examples. The collection unit collects news articles, for example, using a web scraping technique. The collection unit can also collect news articles using an RSS feed. Furthermore, the collection unit can also collect news articles using an API. For example, the collection unit uses an API for collecting articles from a specific news site. The generation unit summarizes the articles collected by the collection unit using a generation AI. The summary is designed to include, for example, the title, lead text, and main points of the body of the article, but is not limited to such examples. For example, the generation AI summarizes the article using a text generation AI (for example, LLM). The generation unit can also use the generation AI to extract and summarize important parts of the article. For example, the generation AI picks up particularly important information in the article and summarizes it based on that. The display unit displays a list of summaries generated by the generation unit. The display unit displays the summary on, for example, a web browser. The display unit can also display the summary on a mobile application. Furthermore, the display unit can display the summary on a desktop application. For example, the display unit displays the summary in a card format. In this way, the news summarization system according to the embodiment collects news articles, generates summaries, and displays them in a list, allowing information to be grasped at a bird's-eye view.

[0030] The collection unit collects news articles. Examples of news articles include, but are not limited to, online news, newspaper articles, blog articles, and the like. The collection unit collects news articles using, for example, web scraping technology. Web scraping technology is a technology for automatically extracting data from a specific website, and can use libraries such as Python's BeautifulSoup and Scrapy. This allows the collection unit to analyze the HTML structure of a specific news site and extract information such as the title, text, and date of an article. The collection unit can also collect news articles using an RSS feed. An RSS feed distributes update information provided by a website in XML format, and by using this, the latest news articles can be efficiently collected. Furthermore, the collection unit can also collect news articles using an API. For example, by using an API provided by a specific news site or news service, article data can be obtained in JSON format and efficiently collected. By using the API, the collection unit can filter articles based on specific keywords or categories and collect only necessary information. This enables the collection unit to efficiently collect news articles from a variety of sources, improving the information gathering capabilities of the entire system.

[0031] The generation unit uses the generation AI to summarize the articles collected by the collection unit. The summary is designed to include, for example, the title and lead sentence of the article, and the main points of the body of the article, but is not limited to such examples. The generation AI summarizes the article using a text generation AI (for example, LLM). Specifically, the generation AI uses natural language processing technology to analyze the content of the article and extract important information. For example, the generation AI identifies keywords and phrases that appear frequently in the article and generates a summary based on them. The generation AI can also understand the context of the article and extract important parts to summarize it. For example, the generation AI focuses on the opening and conclusion parts of the article and generates a summary based on them. Furthermore, the generation AI can compress the content of the article and provide a summary in short sentences. This allows the generation unit to quickly and accurately summarize the collected articles and provide important information to the user. The generation AI can continuously learn and improve the accuracy of the summary. For example, based on user feedback, the generation AI can improve the quality of the summary and provide a more appropriate summary. This enables the generation unit to always generate high-quality summaries using the latest technology, thereby assisting the user in understanding information.

[0032] The display unit displays a list of summaries generated by the generation unit. The display unit displays the summaries on a web browser, for example. The display on the web browser is performed in a visually easy-to-read format using HTML and CSS. For example, the summaries are displayed in a card format, and each card includes information such as the article title, summary text, and publication date. The display unit can also display the summaries on a mobile application. In the mobile application, the user interface is optimized for touch operation, and the summaries can be easily viewed by swiping or tapping. Furthermore, the display unit can also display the summaries on a desktop application. In the desktop application, many summaries can be displayed at once by utilizing a large screen, and the user can efficiently grasp information. The display unit can customize the display format according to the user's preferences. For example, the user can set the number and order of summaries to be displayed, or filter based on a specific category or keyword. As a result, the display unit can provide the user with a flexible and intuitive interface and facilitate browsing of information. Furthermore, the display unit can update the summaries in real time and always provide the latest news articles. As a result, the display unit can always allow the user to grasp the latest information, and improve the efficiency of information collection.

[0033] The generation unit can include the title or lead sentence of the article, and the main points of the body text in the summary. The generation unit, for example, includes the title of the article in the summary. For example, the generation unit includes the title of the article as it is in the summary. The generation unit can also include the lead sentence of the article in the summary. For example, the generation unit includes the lead sentence of the article as it is in the summary. The generation unit can also include the main points of the body text of the article in the summary. For example, the generation unit extracts the main points from the body text of the article and includes them in the summary. In this way, the generation unit can efficiently grasp important information by generating a summary including the main points of the article. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the title, lead sentence, and main points of the body text of the article and outputs a summary.

[0034] The information processing apparatus includes a filter unit for filtering a summary by a user. The filter unit can filter a summary by a user. The filter unit performs, for example, keyword filtering. For example, the filter unit filters a summary based on a keyword specified by a user. The filter unit can also perform category filtering. For example, the filter unit filters a summary based on a news category. The filter unit can also perform topic filtering. For example, the filter unit filters summaries related to a specific topic. This allows the filter unit to efficiently obtain required information by filtering a summary by a user. A part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs a keyword specified by a user and outputs a filtered summary.

[0035] The present invention includes a customization unit that allows a user to customize the display of the list of summaries. The customization unit allows the user to customize the display of the list of summaries. The customization unit, for example, changes the display order. For example, the customization unit displays the summaries based on an order specified by the user. The customization unit can also select display items. For example, the customization unit displays the summaries based on items selected by the user. The customization unit can also change the display format. For example, the customization unit provides different display formats such as a list format or a card format. As a result, the customization unit customizes the display of the list of summaries, thereby improving the visibility of information. A part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the display order and display items specified by the user and outputs a customized summary.

[0036] The collection unit can analyze the user's past browsing history and select the optimal collection method. The collection unit, for example, analyzes the user's past browsing history. For example, the collection unit analyzes the news sites and types of articles that the user has viewed in the past. The collection unit can also analyze topics in which the user has shown interest in the past. For example, the collection unit preferentially collects articles from news sites that the user has frequently viewed in the past. The collection unit can also preferentially collect articles related to topics in which the user has shown interest in the past. Furthermore, the collection unit can preferentially collect articles that tend to be viewed in a specific time period from the user's past browsing history. For example, the collection unit analyzes articles that the user has viewed in a specific time period in the past and preferentially collects articles related to that time period. In this way, the collection unit can collect optimal news articles by analyzing the user's past browsing history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can select a collection method using an AI model that inputs the user's past browsing history and outputs an optimal collection method.

[0037] The collection unit can filter news articles based on specific keywords or topics when collecting the news articles. The collection unit, for example, filters news articles based on specific keywords. For example, the collection unit preferentially collects related articles based on keywords specified by the user. The collection unit can also filter news articles based on specific topics. For example, the collection unit filters and collects related articles based on topics in which the user is interested. The collection unit can also specify keywords that the user wants to avoid and filter articles based on the keywords. For example, the collection unit can perform filtering using an AI model that inputs keywords specified by the user and outputs filtered articles. This allows the collection unit to collect highly relevant news articles by filtering based on specific keywords or topics.

[0038] The collection unit can dynamically change the collection target based on the user's current field of interest when collecting news articles. The collection unit, for example, collects news articles based on the user's current field of interest. For example, the collection unit preferentially collects related articles based on topics that the user has frequently searched for recently. The collection unit can also dynamically collect related articles based on the content of articles recently viewed by the user. For example, the collection unit analyzes the content of articles recently viewed by the user and preferentially collects articles related to the content. The collection unit can also change the collection target in real time based on the field in which the user is currently interested. For example, the collection unit dynamically changes the collection target based on the topic in which the user is currently interested. As a result, the collection unit can provide information according to the latest interest by dynamically changing the collection target based on the user's current field of interest. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the user's current field of interest and dynamically changes the collection target.

[0039] When collecting news articles, the collection unit can preferentially collect highly relevant articles by referring to the user's past search history. The collection unit, for example, collects news articles by referring to the user's past search history. For example, the collection unit preferentially collects related articles based on keywords searched by the user in the past. The collection unit can also filter and collect related articles based on topics searched by the user in the past. For example, the collection unit preferentially collects articles related to topics searched by the user in the past. The collection unit can also preferentially collect articles related to a specific theme from the user's past search history. For example, the collection unit preferentially collects articles related to themes searched by the user in the past. Thereby, the collection unit can preferentially collect highly relevant news articles by referring to the user's past search history. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the user's past search history and outputs highly relevant articles.

[0040] When collecting news articles, the collection unit can preferentially collect highly relevant articles taking into account the geographical location information of the user. The collection unit, for example, collects news articles taking into account the geographical location information of the user. For example, the collection unit preferentially collects local news related to the user's current location. In addition, when the user is traveling, the collection unit can also preferentially collect news related to the travel destination. For example, the collection unit collects news related to the travel destination while the user is traveling. In addition, the collection unit can also preferentially collect articles related to local events and occurrences based on the geographical location information of the user. For example, the collection unit collects articles related to local events and occurrences related to the user's current location. In this way, the collection unit can provide highly relevant local news by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0041] The collection unit can analyze the social media activity of the user and collect related articles when collecting news articles. The collection unit, for example, collects news articles by analyzing the social media activity of the user. For example, the collection unit collects related news based on articles shared by the user on social media. The collection unit can also collect related news based on the posted content of an account followed by the user on social media. For example, the collection unit analyzes the posted content of an account followed by the user and collects news related to the content. The collection unit can also collect related news based on an article that the user has "liked" or commented on on social media. For example, the collection unit analyzes an article that the user has "liked" or commented on and collects news related to the content. In this way, the collection unit can collect highly relevant news articles by analyzing the social media activity of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the social media activity of the user and outputs related articles.

[0042] When collecting news articles, the collection unit can select the optimal collection method by considering the device information of the user. The collection unit, for example, collects news articles by considering the device information of the user. For example, when the user is using a smartphone, the collection unit collects articles from a news site optimized for mobile. In addition, when the user is using a tablet, the collection unit can also collect articles from a news site optimized for a large screen. For example, when the user is using a tablet, the collection unit collects articles from a news site optimized for the device. In addition, when the user is using a desktop, the collection unit can also collect articles from a news site that provides detailed information. For example, when the user is using a desktop, the collection unit collects articles from a news site optimized for the device. This allows the collection unit to select the optimal collection method by considering the device information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the device information of the user and outputs the optimal collection method.

[0043] When collecting news articles, the collection unit can preferentially collect highly relevant articles by referring to the user's past purchase history. The collection unit, for example, collects news articles by referring to the user's past purchase history. For example, the collection unit preferentially collects news related to products purchased by the user in the past. The collection unit can also collect news related to topics that the user is likely to be interested in from the user's purchase history. For example, the collection unit collects news related to products purchased by the user in the past. The collection unit can also preferentially collect reviews and evaluation articles related to products purchased by the user in the past. For example, the collection unit collects reviews and evaluation articles related to products purchased by the user in the past. Thereby, the collection unit can preferentially collect highly relevant news articles by referring to the user's past purchase history. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0044] The generation unit can adjust the level of detail of the summary based on the importance of the article when generating the summary. The generation unit adjusts the level of detail of the summary based on, for example, the importance of the article. For example, the generation unit generates a detailed summary for an article with high importance. The generation unit can also generate a concise summary for an article with low importance. For example, the generation unit adjusts the length of the summary according to the importance. As a result, the generation unit can efficiently grasp important information by adjusting the level of detail of the summary based on the importance of the article. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the importance of the article as input and adjusts the level of detail of the summary.

[0045] The generation unit can apply different summarization algorithms depending on the article category when generating a summary. The generation unit applies a summarization algorithm depending on the article category, for example. For example, the generation unit applies a detailed summarization algorithm to a political article. The generation unit can also apply a concise summarization algorithm to an entertainment article. For example, the generation unit applies a concise summarization algorithm to an entertainment article. The generation unit can also apply a summarization algorithm including technical terms to a scientific article. For example, the generation unit applies a summarization algorithm including technical terms to a scientific article. In this way, the generation unit can provide a summary appropriate for the category by applying different summarization algorithms depending on the article category. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the article category as input and applies a summary algorithm.

[0046] The generation unit can evaluate the reliability of an article when generating a summary, and can include highly reliable information in the summary with priority. The generation unit, for example, evaluates the reliability of an article. For example, the generation unit prioritizes including information from a highly reliable news source in the summary. The generation unit can also not include information from a less reliable news source in the summary. For example, the generation unit does not include information from a less reliable news source in the summary. The generation unit can also evaluate the reliability of an article and reflect highly reliable information in the summary. For example, the generation unit evaluates the reliability of an article and reflects highly reliable information in the summary. In this way, the generation unit can provide highly reliable information by evaluating the reliability of an article. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the reliability of an article and includes highly reliable information in the summary.

[0047] The generation unit can determine the priority of the summaries based on the submission time of the articles when generating the summaries. The generation unit determines the priority of the summaries based on, for example, the submission time of the articles. For example, the generation unit prioritizes summarizing the latest articles. The generation unit can also lower the priority of the summaries of articles submitted earlier. For example, the generation unit lowers the priority of the summaries of articles submitted earlier. The generation unit can also adjust the order of the summaries according to the submission time. For example, the generation unit adjusts the order of the summaries according to the submission time. In this way, the generation unit can provide the latest information preferentially by determining the priority of the summaries based on the submission time of the articles. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate summaries using a generation AI model that uses the submission time of the articles as input and determines the priority of the summaries.

[0048] The generation unit can adjust the order of summaries based on the relevance of the articles when generating summaries. The generation unit adjusts the order of summaries based on the relevance of the articles, for example. For example, the generation unit prioritizes summarizing highly relevant articles. The generation unit can also postpone the order of summaries for less relevant articles. For example, the generation unit postpones the order of summaries for less relevant articles. The generation unit can also adjust the order of summaries according to the relevance of the articles. For example, the generation unit adjusts the order of summaries according to the relevance of the articles. As a result, the generation unit can provide highly relevant information preferentially by adjusting the order of summaries based on the relevance of the articles. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the relevance of the articles as input and adjusts the order of summaries.

[0049] The generation unit can apply different summary algorithms depending on the language and region of the article when generating a summary. The generation unit applies a summary algorithm depending on, for example, the language and region of the article. For example, the generation unit applies a summary algorithm for English to an English article. The generation unit can also apply a summary algorithm for Japanese to an article in Japanese. For example, the generation unit applies a summary algorithm for Japanese to an article in Japanese. The generation unit can also apply different summary algorithms for each region. For example, the generation unit applies different summary algorithms for each region. In this way, the generation unit can provide an appropriate summary by applying different summary algorithms depending on the language and region of the article. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the language and region of the article as input and applies a summary algorithm.

[0050] The generation unit can evaluate the reliability of the summary by considering the author information of the article when generating a summary. The generation unit, for example, evaluates the reliability of the summary by considering the author information of the article. For example, if the author is reliable, the generation unit prioritizes summarizing the article. In addition, the generation unit can postpone summarizing the article if the author is unreliable. For example, if the author is unreliable, the generation unit postpones summarizing the article. In addition, the generation unit can analyze the author's past writing history, evaluate the reliability, and reflect the evaluation in the summary. For example, the generation unit analyzes the author's past writing history, evaluates the reliability, and reflects the evaluation in the summary. In this way, the generation unit can provide a reliable summary by considering the author information of the article. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the author information of the article as input and evaluates the reliability of the summary.

[0051] The display unit can select the optimal display method by referring to the user's past browsing history at the time of display. The display unit, for example, selects the display method by referring to the user's past browsing history. For example, the display unit preferentially provides a display format that the user has preferred in the past. The display unit can also select the optimal display layout from the user's past browsing history. For example, the display unit selects the optimal display layout from the user's past browsing history. The display unit can also provide the optimal display method by referring to a display method of an article that the user has previously viewed. For example, the display unit provides the optimal display method by referring to a display method of an article that the user has previously viewed. Thereby, the display unit can provide the optimal display method by referring to the user's past browsing history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the user's past browsing history and outputs the optimal display method.

[0052] The display unit can determine the display priority based on the importance of the article at the time of display. The display unit, for example, determines the display priority based on the importance of the article. For example, the display unit preferentially displays articles with high importance. The display unit can also lower the display priority of articles with low importance. For example, the display unit lowers the display priority of articles with low importance. The display unit can also adjust the display order according to the importance of the article. For example, the display unit adjusts the display order according to the importance of the article. As a result, the display unit can display important information preferentially by determining the display priority based on the importance of the article. A part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that uses the importance of the article as an input and determines the display priority.

[0053] The display unit can apply different display formats according to the category of the article at the time of display. The display unit applies the display format according to the category of the article, for example. For example, the display unit applies a detailed display format to a political article. The display unit can also apply a concise display format to an entertainment article. For example, the display unit applies a concise display format to an entertainment article. The display unit can also apply a display format including technical terms to a scientific article. For example, the display unit applies a display format including technical terms to a scientific article. In this way, the display unit can provide a display suitable for the category by applying different display formats according to the category of the article. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the category of the article and applies the display format.

[0054] The display unit can evaluate the reliability of an article at the time of display and preferentially display highly reliable information. The display unit, for example, evaluates the reliability of an article. For example, the display unit preferentially displays information from a highly reliable news source. The display unit can also lower the display priority of information from a less reliable news source. For example, the display unit lowers the display priority of information from a less reliable news source. The display unit can also evaluate the reliability of an article and reflect the highly reliable information in the display. For example, the display unit evaluates the reliability of an article and reflects the highly reliable information in the display. Thereby, the display unit can provide highly reliable information by evaluating the reliability of the article. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display using an AI model that uses the reliability of an article as an input and displays highly reliable information.

[0055] The display unit can display highly relevant articles preferentially in consideration of the geographical location information of the user at the time of display. The display unit, for example, displays news articles in consideration of the geographical location information of the user. For example, the display unit preferentially displays local news related to the user's current location. In addition, when the user is traveling, the display unit can also display news related to the travel destination preferentially. For example, the display unit displays news related to the travel destination while the user is traveling. In addition, the display unit can also display articles related to local events and occurrences preferentially based on the geographical location information of the user. For example, the display unit displays articles related to local events and occurrences related to the user's current location. In this way, the display unit can provide highly relevant local news by considering the geographical location information of the user. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0056] The display unit can select the optimal display method in consideration of the device information of the user at the time of display. The display unit, for example, displays a news article in consideration of the device information of the user. For example, when the user is using a smartphone, the display unit provides a display method optimized for mobile. In addition, when the user is using a tablet, the display unit can also provide a display method optimized for a large screen. For example, when the user is using a tablet, the display unit provides a display method optimized for the device. In addition, when the user is using a desktop, the display unit can also provide a display method that provides detailed information. For example, when the user is using a desktop, the display unit provides a display method optimized for the device. Thereby, the display unit can provide the optimal display method by considering the device information of the user. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the device information of the user and outputs the optimal display method.

[0057] The display unit can analyze the user's social media activity and display related articles at the time of display. The display unit, for example, analyzes the user's social media activity to display news articles. For example, the display unit displays related news based on articles shared by the user on social media. The display unit can also display related news based on the posted content of an account the user follows on social media. For example, the display unit analyzes the posted content of an account the user follows and displays news related to the content. The display unit can also display related news based on an article that the user "liked" or commented on on social media. For example, the display unit analyzes an article that the user "liked" or commented on and displays news related to the content. In this way, the display unit can provide highly relevant news articles by analyzing the user's social media activity. Part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the user's social media activity and outputs related articles.

[0058] The display unit can display highly relevant articles preferentially by referring to the user's past purchase history at the time of display. The display unit, for example, displays news articles by referring to the user's past purchase history. For example, the display unit preferentially displays news related to products purchased by the user in the past. The display unit can also display news related to topics that the user is likely to be interested in from the user's purchase history. For example, the display unit displays news related to products purchased by the user in the past. The display unit can also preferentially display reviews and evaluation articles related to products purchased by the user in the past. For example, the display unit displays reviews and evaluation articles related to products purchased by the user in the past. In this way, the display unit can provide highly relevant news articles by referring to the user's past purchase history. A part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can display using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0059] The filter unit can select an optimal filtering method by referring to the user's past browsing history at the time of filtering. The filter unit, for example, selects a filtering method by referring to the user's past browsing history. For example, the filter unit preferentially provides a display format that the user has preferred in the past. The filter unit can also select an optimal display layout from the user's past browsing history. For example, the filter unit selects an optimal display layout from the user's past browsing history. The filter unit can also provide an optimal display method by referring to a display method of an article that the user has previously viewed. For example, the filter unit provides an optimal display method by referring to a display method of an article that the user has previously viewed. Thereby, the filter unit can provide an optimal filtering method by referring to the user's past browsing history. A part or all of the above-mentioned processing in the filter unit may be performed, for example, using AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the user's past browsing history and outputs an optimal filtering method.

[0060] The filter unit can determine the priority of filtering based on the importance of the article when filtering. The filter unit determines the priority of filtering based on, for example, the importance of the article. For example, the filter unit preferentially displays articles with high importance. The filter unit can also lower the display priority of articles with low importance. For example, the filter unit lowers the display priority of articles with low importance. The filter unit can also adjust the display order according to the importance of the article. For example, the filter unit adjusts the display order according to the importance of the article. As a result, the filter unit can provide important information preferentially by determining the priority of filtering based on the importance of the article. A part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the importance of the article and determines the priority of filtering.

[0061] The filter unit can apply different filtering algorithms depending on the category of the article when filtering. The filter unit applies a filtering algorithm depending on, for example, the category of the article. For example, the filter unit applies a detailed display format to a political article. The filter unit can also apply a concise display format to an entertainment article. For example, the filter unit applies a concise display format to an entertainment article. The filter unit can also apply a display format including technical terms to a scientific article. For example, the filter unit applies a display format including technical terms to a scientific article. In this way, the filter unit can provide information suitable for the category by applying different filtering algorithms depending on the category of the article. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the category of the article and applies a filtering algorithm.

[0062] The filter unit can evaluate the reliability of an article during filtering and preferentially filter highly reliable information. The filter unit, for example, evaluates the reliability of an article. For example, the filter unit preferentially displays information from a highly reliable news source. The filter unit can also lower the display priority of information from a less reliable news source. For example, the filter unit lowers the display priority of information from a less reliable news source. The filter unit can also evaluate the reliability of an article and reflect the highly reliable information in the display. For example, the filter unit evaluates the reliability of an article and reflects the highly reliable information in the display. In this way, the filter unit can provide highly reliable information by evaluating the reliability of the article. Part or all of the above-mentioned processing in the filter unit may be performed, for example, using AI or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that uses the reliability of an article as an input and filters highly reliable information.

[0063] The filter unit can preferentially filter highly relevant articles in consideration of the geographical location information of the user during filtering. The filter unit, for example, filters news articles in consideration of the geographical location information of the user. For example, the filter unit preferentially displays local news related to the user's current location. In addition, when the user is traveling, the filter unit can also preferentially display news related to the travel destination. For example, the filter unit displays news related to the travel destination while the user is traveling. In addition, the filter unit can also preferentially display articles related to local events and occurrences based on the geographical location information of the user. For example, the filter unit displays articles related to local events and occurrences related to the user's current location. In this way, the filter unit can provide highly relevant local news by considering the geographical location information of the user. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0064] The filter unit can select an optimal filtering method in consideration of the device information of the user at the time of filtering. The filter unit, for example, filters news articles in consideration of the device information of the user. For example, when the user is using a smartphone, the filter unit provides a display method optimized for mobile. In addition, when the user is using a tablet, the filter unit can also provide a display method optimized for a large screen. For example, when the user is using a tablet, the filter unit provides a display method optimized for the device. In addition, when the user is using a desktop, the filter unit can also provide a display method that provides detailed information. For example, when the user is using a desktop, the filter unit provides a display method optimized for the device. In this way, the filter unit can provide an optimal filtering method by considering the device information of the user. Part or all of the above-mentioned processing in the filter unit may be performed, for example, using AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the device information of the user and outputs the optimal filtering method.

[0065] The filter unit can analyze the social media activity of the user and filter related articles at the time of filtering. The filter unit, for example, analyzes the social media activity of the user to filter news articles. For example, the filter unit filters related news based on articles shared by the user on social media. The filter unit can also filter related news based on the posted content of an account followed by the user on social media. For example, the filter unit analyzes the posted content of an account followed by the user and filters news related to the content. The filter unit can also filter related news based on an article that the user has "liked" or commented on on social media. For example, the filter unit analyzes an article that the user has "liked" or commented on and filters news related to the content. In this way, the filter unit can provide highly relevant news articles by analyzing the social media activity of the user. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the social media activity of the user and outputs related articles.

[0066] The filter unit can filter highly relevant articles preferentially by referring to the user's past purchase history during filtering. The filter unit, for example, filters news articles by referring to the user's past purchase history. For example, the filter unit preferentially filters news related to products purchased by the user in the past. The filter unit can also filter news related to topics that the user is likely to be interested in from the user's purchase history. For example, the filter unit filters news related to products purchased by the user in the past. The filter unit can also preferentially filter reviews and evaluation articles related to products purchased by the user in the past. For example, the filter unit filters reviews and evaluation articles related to products purchased by the user in the past. In this way, the filter unit can provide highly relevant news articles by referring to the user's past purchase history. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0067] The customization unit can select an optimal customization method by referring to the user's past browsing history at the time of customization. The customization unit, for example, selects a customization method by referring to the user's past browsing history. For example, the customization unit preferentially provides a display format that the user has preferred in the past. The customization unit can also select an optimal display layout from the user's past browsing history. For example, the customization unit selects an optimal display layout from the user's past browsing history. The customization unit can also provide an optimal display method by referring to a display method of an article that the user has previously viewed. For example, the customization unit provides an optimal display method by referring to a display method of an article that the user has previously viewed. Thereby, the customization unit can provide an optimal customization method by referring to the user's past browsing history. A part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the user's past browsing history and outputs an optimal customization method.

[0068] The customization unit can determine the priority of customization based on the importance of the article at the time of customization. The customization unit determines the priority of customization based on, for example, the importance of the article. For example, the customization unit preferentially displays articles with high importance. The customization unit can also lower the display priority of articles with low importance. For example, the customization unit lowers the display priority of articles with low importance. The customization unit can also adjust the display order according to the importance of the article. For example, the customization unit adjusts the display order according to the importance of the article. As a result, the customization unit can provide important information preferentially by determining the priority of customization based on the importance of the article. A part or all of the above-mentioned processing in the customization unit may be performed using, for example, AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the importance of the article and determines the priority of customization.

[0069] The customization unit can apply different customization algorithms depending on the category of the article during customization. The customization unit applies the customization algorithm, for example, depending on the category of the article. For example, the customization unit applies a detailed display format to a political article. The customization unit can also apply a concise display format to an entertainment article. For example, the customization unit applies a concise display format to an entertainment article. The customization unit can also apply a display format including technical terms to a scientific article. For example, the customization unit applies a display format including technical terms to a scientific article. In this way, the customization unit can provide information suitable for the category by applying different customization algorithms depending on the category of the article. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the category of the article and applies the customization algorithm.

[0070] The customization unit can evaluate the reliability of an article at the time of customization, and customize highly reliable information with priority. The customization unit, for example, evaluates the reliability of an article. For example, the customization unit preferentially displays information from a highly reliable news source. The customization unit can also lower the display priority of information from a less reliable news source. For example, the customization unit can lower the display priority of information from a less reliable news source. The customization unit can also evaluate the reliability of an article and reflect the highly reliable information in the display. For example, the customization unit evaluates the reliability of an article and reflects the highly reliable information in the display. In this way, the customization unit can provide highly reliable information by evaluating the reliability of the article. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that uses the reliability of an article as an input and customizes highly reliable information.

[0071] During customization, the customization unit can prioritize customizing highly relevant articles in consideration of the geographical location information of the user. The customization unit customizes news articles in consideration of, for example, the geographical location information of the user. For example, the customization unit prioritizes displaying local news related to the user's current location. In addition, when the user is traveling, the customization unit can also prioritize displaying news related to the travel destination. For example, the customization unit displays news related to the travel destination while the user is traveling. In addition, the customization unit can also prioritize displaying articles related to local events and occurrences based on the geographical location information of the user. For example, the customization unit displays articles related to local events and occurrences related to the user's current location. In this way, the customization unit can provide highly relevant local news by considering the geographical location information of the user. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0072] The customization unit can select the optimal customization method in consideration of the device information of the user at the time of customization. The customization unit customizes the news article in consideration of, for example, the device information of the user. For example, when the user is using a smartphone, the customization unit provides a display method optimized for mobile. In addition, when the user is using a tablet, the customization unit can also provide a display method optimized for a large screen. For example, when the user is using a tablet, the customization unit provides a display method optimized for the device. In addition, when the user is using a desktop, the customization unit can also provide a display method that provides detailed information. For example, when the user is using a desktop, the customization unit provides a display method optimized for the device. In this way, the customization unit can provide the optimal customization method by considering the device information of the user. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the device information of the user and outputs the optimal customization method.

[0073] The customization unit can analyze the user's social media activity and customize related articles at the time of customization. The customization unit, for example, customizes news articles by analyzing the user's social media activity. For example, the customization unit displays related news based on articles shared by the user on social media. The customization unit can also display related news based on the posted content of an account followed by the user on social media. For example, the customization unit analyzes the posted content of an account followed by the user and displays news related to the content. The customization unit can also display related news based on articles that the user has "liked" or commented on on social media. For example, the customization unit analyzes articles that the user has "liked" or commented on and displays news related to the content. In this way, the customization unit can provide highly relevant news articles by analyzing the user's social media activity. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the user's social media activity and outputs related articles.

[0074] During customization, the customization unit can refer to the user's past purchase history and preferentially customize highly relevant articles. The customization unit, for example, refers to the user's past purchase history to customize news articles. For example, the customization unit preferentially displays news related to products purchased by the user in the past. The customization unit can also display news related to topics that the user is likely to be interested in from the user's purchase history. For example, the customization unit displays news related to products purchased by the user in the past. The customization unit can also preferentially display reviews and evaluation articles related to products purchased by the user in the past. For example, the customization unit displays reviews and evaluation articles related to products purchased by the user in the past. In this way, the customization unit can provide highly relevant news articles by referring to the user's past purchase history. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0075] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0076] The news summarization system may further include an interest evaluation unit that evaluates the user's interest in real time. The interest evaluation unit analyzes the scroll speed and stay time when the user browses a news article, and evaluates the user's interest. For example, if the user stays on a particular article for a long time, it is determined that the user has a high interest in that article. The interest evaluation unit may also evaluate the interest based on the frequency with which the user shares or comments on an article. This allows the interest evaluation unit to adjust the display order of news articles based on the user's interest. Furthermore, the interest evaluation unit may preferentially collect related news articles based on the user's interest. This allows the user to efficiently browse news articles that match his or her interests.

[0077] The generation unit may include a reliability evaluation unit that evaluates the reliability of an article when generating a summary. The reliability evaluation unit evaluates reliability based on the reliability of the news source and the past track record of the article's writer. For example, information from a reliable news source is preferentially included in the summary. The reliability evaluation unit can also check whether the content of the article is consistent with other reliable sources. This allows the generation unit to generate a summary including reliable information. Furthermore, the reliability evaluation unit can display the reliability evaluation result to the user. This allows the user to make a decision based on reliable information.

[0078] The news summarization system may further include a geographic information collection unit that collects news articles taking into consideration the geographic location information of the user. The geographic information collection unit preferentially collects local news related to the user's current location. For example, if the user is in a particular city, the geographic information collection unit collects news articles related to the city. In addition, if the user is traveling, the geographic information collection unit may also collect news articles related to the travel destination. Furthermore, the geographic information collection unit may collect articles about local events and happenings based on the user's geographic location information. This allows the user to obtain the latest information related to his or her current location.

[0079] The news summarization system may further include a social media analysis unit that analyzes the user's social media activities to collect news articles. The social media analysis unit collects related news articles based on articles shared by the user on social media. For example, if the user shares an article on a specific topic, news articles related to the topic are collected. The social media analysis unit may also collect related news articles based on the content posted by accounts the user follows. Furthermore, the social media analysis unit may also collect related news articles based on articles that the user has "liked" or commented on. This allows the user to efficiently obtain news articles that match their interests.

[0080] The news summarization system may further include a device information collection unit that collects news articles taking into account device information of the user. When the user is using a smartphone, the device information collection unit collects articles from a news site optimized for mobile devices. For example, articles in a display format optimized for smartphones are collected. When the user is using a tablet, the device information collection unit may also collect articles from a news site optimized for a large screen. Furthermore, when the user is using a desktop, the device information collection unit may also collect articles from a news site that provides detailed information. This allows the user to efficiently obtain news articles optimized for his or her device.

[0081] The news summarization system may further include a purchase history analysis unit that collects news articles by referring to the user's past purchase history. The purchase history analysis unit collects news articles related to products that the user has purchased in the past. For example, when the user has purchased a specific product, news articles related to the product are collected. The purchase history analysis unit may also collect news articles related to topics that the user may be interested in from the user's purchase history. Furthermore, the purchase history analysis unit may collect reviews and evaluation articles related to products that the user has purchased in the past. This allows the user to obtain the latest information related to his or her purchase history.

[0082] The news summarization system may further include a search history analysis unit that collects news articles by referring to the user's past search history. The search history analysis unit collects related news articles based on keywords previously searched by the user. For example, when a user searches for a keyword related to a specific topic, news articles related to the topic are collected. The search history analysis unit may also collect related news articles based on topics previously searched by the user. Furthermore, the search history analysis unit may collect news articles related to a specific theme from the user's past search history. This allows the user to obtain the latest information related to his or her search history.

[0083] The process flow of the first embodiment will be briefly described below.

[0084] Step 1: The collection unit collects news articles. The news articles include online news, newspaper articles, blog articles, etc. The collection unit collects news articles using web scraping technology, RSS feeds, and APIs. For example, the collection unit uses an API to collect articles from a specific news site. Step 2: The generator uses a generative AI to summarize the articles collected by the collector. The summary is designed to include the article title, lead text, and main points of the text. The generator uses a text generation AI (e.g., LLM) to summarize the article and extract the important parts of the article to create a summary. Step 3: The display unit displays a list of the summaries generated by the generation unit. The display unit can display the summaries on a web browser, a mobile application, or a desktop application. For example, the summaries are displayed in a card format.

[0085] (Example 2) A news summarization system according to an embodiment of the present invention is a system that collects news articles, generates summaries using a generation AI, and displays them in a list. This news summarization system includes a collection unit that collects news articles, a generation unit that generates summaries from the collected articles using a large-scale language model, and a display unit that displays the generated summaries in a list. For example, the collection unit collects news articles using web scraping technology. The collected articles are sent to the generation unit, and summaries are generated using a large-scale language model (generation AI). The summaries are designed to include the titles, lead sentences, and main points of the body of the articles. The generated summaries are sent to the display unit and displayed in a list to the user. The user can filter the summaries using the filter unit, and can also customize the list display using the customization unit. Furthermore, the collection unit estimates the user's emotions and determines the priority of the news articles to be collected based on the estimated emotions. In addition, the collection unit analyzes the user's past browsing history and selects the optimal collection method. It also has a function of filtering news articles based on specific keywords and topics. This allows the user to collect and obtain information that will affect the market at once, allowing them to grasp the information from a bird's-eye view. This allows the news summarization system to consolidate and obtain all the information that will affect the market at once, enabling users to get a bird's-eye view of the information.

[0086] The news summarization system according to the embodiment includes a collection unit, a generation unit, and a display unit. The collection unit collects news articles. The news articles include, for example, online news, newspaper articles, blog articles, and the like, but are not limited to such examples. The collection unit collects news articles, for example, using a web scraping technique. The collection unit can also collect news articles using an RSS feed. Furthermore, the collection unit can also collect news articles using an API. For example, the collection unit uses an API for collecting articles from a specific news site. The generation unit summarizes the articles collected by the collection unit using a generation AI. The summary is designed to include, for example, the title, lead text, and main points of the body of the article, but is not limited to such examples. For example, the generation AI summarizes the article using a text generation AI (for example, LLM). The generation unit can also use the generation AI to extract and summarize important parts of the article. For example, the generation AI picks up particularly important information in the article and summarizes it based on that. The display unit displays a list of summaries generated by the generation unit. The display unit displays the summary on, for example, a web browser. The display unit can also display the summary on a mobile application. Furthermore, the display unit can display the summary on a desktop application. For example, the display unit displays the summary in a card format. In this way, the news summarization system according to the embodiment collects news articles, generates summaries, and displays them in a list, allowing information to be grasped at a bird's-eye view.

[0087] The collection unit collects news articles. Examples of news articles include, but are not limited to, online news, newspaper articles, blog articles, and the like. The collection unit collects news articles using, for example, web scraping technology. Web scraping technology is a technology for automatically extracting data from a specific website, and can use libraries such as Python's BeautifulSoup and Scrapy. This allows the collection unit to analyze the HTML structure of a specific news site and extract information such as the title, text, and date of an article. The collection unit can also collect news articles using an RSS feed. An RSS feed distributes update information provided by a website in XML format, and by using this, the latest news articles can be efficiently collected. Furthermore, the collection unit can also collect news articles using an API. For example, by using an API provided by a specific news site or news service, article data can be obtained in JSON format and efficiently collected. By using the API, the collection unit can filter articles based on specific keywords or categories and collect only necessary information. This enables the collection unit to efficiently collect news articles from a variety of sources, improving the information collection capabilities of the entire system.

[0088] The generation unit uses the generation AI to summarize the articles collected by the collection unit. The summary is designed to include, for example, the title and lead sentence of the article, and the main points of the body of the article, but is not limited to such examples. The generation AI summarizes the article using a text generation AI (for example, LLM). Specifically, the generation AI uses natural language processing technology to analyze the content of the article and extract important information. For example, the generation AI identifies keywords and phrases that appear frequently in the article and generates a summary based on them. The generation AI can also understand the context of the article and extract important parts to summarize it. For example, the generation AI focuses on the opening and conclusion parts of the article and generates a summary based on them. Furthermore, the generation AI can compress the content of the article and provide a summary in short sentences. This allows the generation unit to quickly and accurately summarize the collected articles and provide important information to the user. The generation AI can continuously learn and improve the accuracy of the summary. For example, based on user feedback, the generation AI can improve the quality of the summary and provide a more appropriate summary. This enables the generation unit to always generate high-quality summaries using the latest technology, thereby assisting the user in understanding information.

[0089] The display unit displays a list of summaries generated by the generation unit. The display unit displays the summaries on a web browser, for example. The display on the web browser is performed in a visually easy-to-read format using HTML and CSS. For example, the summaries are displayed in a card format, and each card includes information such as the article title, summary text, and publication date. The display unit can also display the summaries on a mobile application. In the mobile application, the user interface is optimized for touch operation, and the summaries can be easily viewed by swiping or tapping. Furthermore, the display unit can also display the summaries on a desktop application. In the desktop application, many summaries can be displayed at once by utilizing a large screen, and the user can efficiently grasp information. The display unit can customize the display format according to the user's preferences. For example, the user can set the number and order of summaries to be displayed, or filter based on a specific category or keyword. As a result, the display unit can provide the user with a flexible and intuitive interface and facilitate browsing of information. Furthermore, the display unit can update the summaries in real time and always provide the latest news articles. As a result, the display unit can always allow the user to grasp the latest information, and improve the efficiency of information collection.

[0090] The generation unit can include the title or lead sentence of the article, and the main points of the body text in the summary. The generation unit, for example, includes the title of the article in the summary. For example, the generation unit includes the title of the article as it is in the summary. The generation unit can also include the lead sentence of the article in the summary. For example, the generation unit includes the lead sentence of the article as it is in the summary. The generation unit can also include the main points of the body text of the article in the summary. For example, the generation unit extracts the main points from the body text of the article and includes them in the summary. In this way, the generation unit can efficiently grasp important information by generating a summary including the main points of the article. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the title, lead sentence, and main points of the body text of the article and outputs a summary.

[0091] The information processing apparatus includes a filter unit for filtering a summary by a user. The filter unit can filter a summary by a user. The filter unit performs, for example, keyword filtering. For example, the filter unit filters a summary based on a keyword specified by a user. The filter unit can also perform category filtering. For example, the filter unit filters a summary based on a news category. The filter unit can also perform topic filtering. For example, the filter unit filters summaries related to a specific topic. This allows the filter unit to efficiently obtain required information by filtering a summary by a user. A part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs a keyword specified by a user and outputs a filtered summary.

[0092] The present invention includes a customization unit that allows a user to customize the display of the list of summaries. The customization unit allows the user to customize the display of the list of summaries. The customization unit, for example, changes the display order. For example, the customization unit displays the summaries based on an order specified by the user. The customization unit can also select display items. For example, the customization unit displays the summaries based on items selected by the user. The customization unit can also change the display format. For example, the customization unit provides different display formats such as a list format or a card format. As a result, the customization unit customizes the display of the list of summaries, thereby improving the visibility of information. A part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the display order and display items specified by the user and outputs a customized summary.

[0093] The collection unit can estimate the user's emotion and determine the priority of the news articles to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion. For example, the collection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The collection unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the collection unit analyzes the tone and speed of the voice and calculates an emotion score. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on the fluctuation of the heart rate. As a result, the collection unit can provide information suitable for the user by determining the priority of the news articles based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0094] The collection unit can analyze the user's past browsing history and select the optimal collection method. The collection unit, for example, analyzes the user's past browsing history. For example, the collection unit analyzes the news sites and types of articles that the user has viewed in the past. The collection unit can also analyze topics in which the user has shown interest in the past. For example, the collection unit preferentially collects articles from news sites that the user has frequently viewed in the past. The collection unit can also preferentially collect articles related to topics in which the user has shown interest in the past. Furthermore, the collection unit can preferentially collect articles that tend to be viewed in a specific time period from the user's past browsing history. For example, the collection unit analyzes articles that the user has viewed in a specific time period in the past and preferentially collects articles related to that time period. In this way, the collection unit can collect optimal news articles by analyzing the user's past browsing history. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can select a collection method using an AI model that inputs the user's past browsing history and outputs an optimal collection method.

[0095] The collection unit can filter news articles based on specific keywords or topics when collecting the news articles. The collection unit, for example, filters news articles based on specific keywords. For example, the collection unit preferentially collects related articles based on keywords specified by the user. The collection unit can also filter news articles based on specific topics. For example, the collection unit filters and collects related articles based on topics in which the user is interested. The collection unit can also specify keywords that the user wants to avoid and filter articles based on the keywords. For example, the collection unit can perform filtering using an AI model that inputs keywords specified by the user and outputs filtered articles. This allows the collection unit to collect highly relevant news articles by filtering based on specific keywords or topics.

[0096] The collection unit can dynamically change the collection target based on the user's current field of interest when collecting news articles. The collection unit, for example, collects news articles based on the user's current field of interest. For example, the collection unit preferentially collects related articles based on topics that the user has frequently searched for recently. The collection unit can also dynamically collect related articles based on the content of articles recently viewed by the user. For example, the collection unit analyzes the content of articles recently viewed by the user and preferentially collects articles related to the content. The collection unit can also change the collection target in real time based on the field in which the user is currently interested. For example, the collection unit dynamically changes the collection target based on the topic in which the user is currently interested. As a result, the collection unit can provide information according to the latest interest by dynamically changing the collection target based on the user's current field of interest. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the user's current field of interest and dynamically changes the collection target.

[0097] When collecting news articles, the collection unit can preferentially collect highly relevant articles by referring to the user's past search history. The collection unit, for example, collects news articles by referring to the user's past search history. For example, the collection unit preferentially collects related articles based on keywords searched by the user in the past. The collection unit can also filter and collect related articles based on topics searched by the user in the past. For example, the collection unit preferentially collects articles related to topics searched by the user in the past. The collection unit can also preferentially collect articles related to a specific theme from the user's past search history. For example, the collection unit preferentially collects articles related to themes searched by the user in the past. Thereby, the collection unit can preferentially collect highly relevant news articles by referring to the user's past search history. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the user's past search history and outputs highly relevant articles.

[0098] The collection unit can estimate the user's emotion and select a news site to be collected based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion. For example, the collection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The collection unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the collection unit analyzes the tone and speed of the voice and calculates an emotion score. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on the fluctuation of the heart rate. As a result, the collection unit can provide a news article suitable for the user by selecting a news site based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0099] When collecting news articles, the collection unit can preferentially collect highly relevant articles taking into account the geographical location information of the user. The collection unit, for example, collects news articles taking into account the geographical location information of the user. For example, the collection unit preferentially collects local news related to the user's current location. In addition, when the user is traveling, the collection unit can also preferentially collect news related to the travel destination. For example, the collection unit collects news related to the travel destination while the user is traveling. In addition, the collection unit can also preferentially collect articles related to local events and occurrences based on the geographical location information of the user. For example, the collection unit collects articles related to local events and occurrences related to the user's current location. In this way, the collection unit can provide highly relevant local news by taking into account the geographical location information of the user. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0100] The collection unit can analyze the social media activity of the user and collect related articles when collecting news articles. The collection unit, for example, collects news articles by analyzing the social media activity of the user. For example, the collection unit collects related news based on articles shared by the user on social media. The collection unit can also collect related news based on the posted content of an account followed by the user on social media. For example, the collection unit analyzes the posted content of an account followed by the user and collects news related to the content. The collection unit can also collect related news based on an article that the user has "liked" or commented on on social media. For example, the collection unit analyzes an article that the user has "liked" or commented on and collects news related to the content. In this way, the collection unit can collect highly relevant news articles by analyzing the social media activity of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the social media activity of the user and outputs related articles.

[0101] When collecting news articles, the collection unit can select the optimal collection method by considering the device information of the user. The collection unit, for example, collects news articles by considering the device information of the user. For example, when the user is using a smartphone, the collection unit collects articles from a news site optimized for mobile. In addition, when the user is using a tablet, the collection unit can also collect articles from a news site optimized for a large screen. For example, when the user is using a tablet, the collection unit collects articles from a news site optimized for the device. In addition, when the user is using a desktop, the collection unit can also collect articles from a news site that provides detailed information. For example, when the user is using a desktop, the collection unit collects articles from a news site optimized for the device. This allows the collection unit to select the optimal collection method by considering the device information of the user. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the device information of the user and outputs the optimal collection method.

[0102] When collecting news articles, the collection unit can preferentially collect highly relevant articles by referring to the user's past purchase history. The collection unit, for example, collects news articles by referring to the user's past purchase history. For example, the collection unit preferentially collects news related to products purchased by the user in the past. The collection unit can also collect news related to topics that the user is likely to be interested in from the user's purchase history. For example, the collection unit collects news related to products purchased by the user in the past. The collection unit can also preferentially collect reviews and evaluation articles related to products purchased by the user in the past. For example, the collection unit collects reviews and evaluation articles related to products purchased by the user in the past. Thereby, the collection unit can preferentially collect highly relevant news articles by referring to the user's past purchase history. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can perform collection using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0103] The generation unit can estimate the user's emotion and adjust the expression method of the summary based on the estimated user's emotion. The generation unit, for example, estimates the user's emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The generation unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the generation unit analyzes the tone and speed of the voice and calculates an emotion score. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on the fluctuation of the heart rate. As a result, the generation unit can provide a summary suitable for the user by adjusting the expression method of the summary based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0104] The generation unit can adjust the level of detail of the summary based on the importance of the article when generating the summary. The generation unit adjusts the level of detail of the summary based on, for example, the importance of the article. For example, the generation unit generates a detailed summary for an article with high importance. The generation unit can also generate a concise summary for an article with low importance. For example, the generation unit adjusts the length of the summary according to the importance. As a result, the generation unit can efficiently grasp important information by adjusting the level of detail of the summary based on the importance of the article. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the importance of the article as input and adjusts the level of detail of the summary.

[0105] The generation unit can apply different summarization algorithms depending on the article category when generating a summary. The generation unit applies a summarization algorithm depending on the article category, for example. For example, the generation unit applies a detailed summarization algorithm to a political article. The generation unit can also apply a concise summarization algorithm to an entertainment article. For example, the generation unit applies a concise summarization algorithm to an entertainment article. The generation unit can also apply a summarization algorithm including technical terms to a scientific article. For example, the generation unit applies a summarization algorithm including technical terms to a scientific article. In this way, the generation unit can provide a summary appropriate for the category by applying different summarization algorithms depending on the article category. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the article category as input and applies a summary algorithm.

[0106] The generation unit can evaluate the reliability of an article when generating a summary, and can include highly reliable information in the summary with priority. The generation unit, for example, evaluates the reliability of an article. For example, the generation unit prioritizes including information from a highly reliable news source in the summary. The generation unit can also not include information from a less reliable news source in the summary. For example, the generation unit does not include information from a less reliable news source in the summary. The generation unit can also evaluate the reliability of an article and reflect highly reliable information in the summary. For example, the generation unit evaluates the reliability of an article and reflects highly reliable information in the summary. In this way, the generation unit can provide highly reliable information by evaluating the reliability of an article. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that inputs the reliability of an article and includes highly reliable information in the summary.

[0107] The generation unit can determine the priority of the summaries based on the submission time of the articles when generating the summaries. The generation unit determines the priority of the summaries based on, for example, the submission time of the articles. For example, the generation unit prioritizes summarizing the latest articles. The generation unit can also lower the priority of the summaries of articles submitted earlier. For example, the generation unit lowers the priority of the summaries of articles submitted earlier. The generation unit can also adjust the order of the summaries according to the submission time. For example, the generation unit adjusts the order of the summaries according to the submission time. In this way, the generation unit can provide the latest information preferentially by determining the priority of the summaries based on the submission time of the articles. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate summaries using a generation AI model that uses the submission time of the articles as input and determines the priority of the summaries.

[0108] The generation unit can adjust the order of summaries based on the relevance of the articles when generating summaries. The generation unit adjusts the order of summaries based on the relevance of the articles, for example. For example, the generation unit prioritizes summarizing highly relevant articles. The generation unit can also postpone the order of summaries for less relevant articles. For example, the generation unit postpones the order of summaries for less relevant articles. The generation unit can also adjust the order of summaries according to the relevance of the articles. For example, the generation unit adjusts the order of summaries according to the relevance of the articles. As a result, the generation unit can provide highly relevant information preferentially by adjusting the order of summaries based on the relevance of the articles. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the relevance of the articles as input and adjusts the order of summaries.

[0109] The generation unit can apply different summary algorithms depending on the language and region of the article when generating a summary. The generation unit applies a summary algorithm depending on, for example, the language and region of the article. For example, the generation unit applies a summary algorithm for English to an English article. The generation unit can also apply a summary algorithm for Japanese to an article in Japanese. For example, the generation unit applies a summary algorithm for Japanese to an article in Japanese. The generation unit can also apply different summary algorithms for each region. For example, the generation unit applies different summary algorithms for each region. In this way, the generation unit can provide an appropriate summary by applying different summary algorithms depending on the language and region of the article. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the language and region of the article as input and applies a summary algorithm.

[0110] The generation unit can evaluate the reliability of the summary by considering the author information of the article when generating a summary. The generation unit, for example, evaluates the reliability of the summary by considering the author information of the article. For example, if the author is reliable, the generation unit prioritizes summarizing the article. In addition, the generation unit can postpone summarizing the article if the author is unreliable. For example, if the author is unreliable, the generation unit postpones summarizing the article. In addition, the generation unit can analyze the author's past writing history, evaluate the reliability, and reflect the evaluation in the summary. For example, the generation unit analyzes the author's past writing history, evaluates the reliability, and reflects the evaluation in the summary. In this way, the generation unit can provide a reliable summary by considering the author information of the article. Part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can generate a summary using a generation AI model that uses the author information of the article as input and evaluates the reliability of the summary.

[0111] The display unit can estimate the user's emotion and adjust the display method based on the estimated user's emotion. The display unit, for example, estimates the user's emotion. For example, the display unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The display unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the display unit analyzes the tone and speed of the voice and calculates an emotion score. The display unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the display unit calculates an emotion score based on the fluctuation of the heart rate. As a result, the display unit can provide a display suitable for the user by adjusting the display method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input image data of the user captured by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0112] The display unit can select the optimal display method by referring to the user's past browsing history at the time of display. The display unit, for example, selects the display method by referring to the user's past browsing history. For example, the display unit preferentially provides a display format that the user has preferred in the past. The display unit can also select the optimal display layout from the user's past browsing history. For example, the display unit selects the optimal display layout from the user's past browsing history. The display unit can also provide the optimal display method by referring to a display method of an article that the user has previously viewed. For example, the display unit provides the optimal display method by referring to a display method of an article that the user has previously viewed. Thereby, the display unit can provide the optimal display method by referring to the user's past browsing history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the user's past browsing history and outputs the optimal display method.

[0113] The display unit can determine the display priority based on the importance of the article at the time of display. The display unit, for example, determines the display priority based on the importance of the article. For example, the display unit preferentially displays articles with high importance. The display unit can also lower the display priority of articles with low importance. For example, the display unit lowers the display priority of articles with low importance. The display unit can also adjust the display order according to the importance of the article. For example, the display unit adjusts the display order according to the importance of the article. As a result, the display unit can display important information preferentially by determining the display priority based on the importance of the article. A part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that uses the importance of the article as an input and determines the display priority.

[0114] The display unit can apply different display formats according to the category of the article at the time of display. The display unit applies the display format according to the category of the article, for example. For example, the display unit applies a detailed display format to a political article. The display unit can also apply a concise display format to an entertainment article. For example, the display unit applies a concise display format to an entertainment article. The display unit can also apply a display format including technical terms to a scientific article. For example, the display unit applies a display format including technical terms to a scientific article. In this way, the display unit can provide a display suitable for the category by applying different display formats according to the category of the article. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the category of the article and applies the display format.

[0115] The display unit can evaluate the reliability of an article at the time of display and preferentially display highly reliable information. The display unit, for example, evaluates the reliability of an article. For example, the display unit preferentially displays information from a highly reliable news source. The display unit can also lower the display priority of information from a less reliable news source. For example, the display unit lowers the display priority of information from a less reliable news source. The display unit can also evaluate the reliability of an article and reflect the highly reliable information in the display. For example, the display unit evaluates the reliability of an article and reflects the highly reliable information in the display. Thereby, the display unit can provide highly reliable information by evaluating the reliability of the article. A part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can display using an AI model that uses the reliability of an article as an input and displays highly reliable information.

[0116] The display unit can estimate the user's emotion and adjust the display order based on the estimated user's emotion. The display unit, for example, estimates the user's emotion. For example, the display unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The display unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the display unit analyzes the tone and speed of the voice and calculates an emotion score. The display unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the display unit calculates an emotion score based on the heart rate fluctuation. As a result, the display unit can provide information suitable for the user by adjusting the display order based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can input image data of the user captured by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0117] The display unit can display highly relevant articles preferentially in consideration of the geographical location information of the user at the time of display. The display unit, for example, displays news articles in consideration of the geographical location information of the user. For example, the display unit preferentially displays local news related to the user's current location. In addition, when the user is traveling, the display unit can also display news related to the travel destination preferentially. For example, the display unit displays news related to the travel destination while the user is traveling. In addition, the display unit can also display articles related to local events and occurrences preferentially based on the geographical location information of the user. For example, the display unit displays articles related to local events and occurrences related to the user's current location. In this way, the display unit can provide highly relevant local news by considering the geographical location information of the user. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0118] The display unit can select the optimal display method in consideration of the device information of the user at the time of display. The display unit, for example, displays a news article in consideration of the device information of the user. For example, when the user is using a smartphone, the display unit provides a display method optimized for mobile. In addition, when the user is using a tablet, the display unit can also provide a display method optimized for a large screen. For example, when the user is using a tablet, the display unit provides a display method optimized for the device. In addition, when the user is using a desktop, the display unit can also provide a display method that provides detailed information. For example, when the user is using a desktop, the display unit provides a display method optimized for the device. Thereby, the display unit can provide the optimal display method by considering the device information of the user. Part or all of the above-mentioned processing in the display unit may be performed, for example, using AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the device information of the user and outputs the optimal display method.

[0119] The display unit can analyze the user's social media activity and display related articles at the time of display. The display unit, for example, analyzes the user's social media activity to display news articles. For example, the display unit displays related news based on articles shared by the user on social media. The display unit can also display related news based on the posted content of an account the user follows on social media. For example, the display unit analyzes the posted content of an account the user follows and displays news related to the content. The display unit can also display related news based on an article that the user "liked" or commented on on social media. For example, the display unit analyzes an article that the user "liked" or commented on and displays news related to the content. In this way, the display unit can provide highly relevant news articles by analyzing the user's social media activity. Part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can perform display using an AI model that inputs the user's social media activity and outputs related articles.

[0120] The display unit can display highly relevant articles preferentially by referring to the user's past purchase history at the time of display. The display unit, for example, displays news articles by referring to the user's past purchase history. For example, the display unit preferentially displays news related to products purchased by the user in the past. The display unit can also display news related to topics that the user is likely to be interested in from the user's purchase history. For example, the display unit displays news related to products purchased by the user in the past. The display unit can also preferentially display reviews and evaluation articles related to products purchased by the user in the past. For example, the display unit displays reviews and evaluation articles related to products purchased by the user in the past. In this way, the display unit can provide highly relevant news articles by referring to the user's past purchase history. A part or all of the above-mentioned processing in the display unit may be performed using, for example, AI, or may be performed without using AI. For example, the display unit can display using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0121] The filter unit can estimate the user's emotion and adjust the filtering criteria based on the estimated user's emotion. The filter unit, for example, estimates the user's emotion. For example, the filter unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The filter unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the filter unit analyzes the tone and speed of the voice and calculates an emotion score. The filter unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the filter unit calculates an emotion score based on the heart rate fluctuation. As a result, the filter unit can provide information suitable for the user by adjusting the filtering criteria based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit may input image data of a user captured by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0122] The filter unit can select an optimal filtering method by referring to the user's past browsing history at the time of filtering. The filter unit, for example, selects a filtering method by referring to the user's past browsing history. For example, the filter unit preferentially provides a display format that the user has preferred in the past. The filter unit can also select an optimal display layout from the user's past browsing history. For example, the filter unit selects an optimal display layout from the user's past browsing history. The filter unit can also provide an optimal display method by referring to a display method of an article that the user has previously viewed. For example, the filter unit provides an optimal display method by referring to a display method of an article that the user has previously viewed. Thereby, the filter unit can provide an optimal filtering method by referring to the user's past browsing history. A part or all of the above-mentioned processing in the filter unit may be performed, for example, using AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the user's past browsing history and outputs an optimal filtering method.

[0123] The filter unit can determine the priority of filtering based on the importance of the article when filtering. The filter unit determines the priority of filtering based on, for example, the importance of the article. For example, the filter unit preferentially displays articles with high importance. The filter unit can also lower the display priority of articles with low importance. For example, the filter unit lowers the display priority of articles with low importance. The filter unit can also adjust the display order according to the importance of the article. For example, the filter unit adjusts the display order according to the importance of the article. As a result, the filter unit can provide important information preferentially by determining the priority of filtering based on the importance of the article. A part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the importance of the article and determines the priority of filtering.

[0124] The filter unit can apply different filtering algorithms depending on the category of the article when filtering. The filter unit applies a filtering algorithm depending on, for example, the category of the article. For example, the filter unit applies a detailed display format to a political article. The filter unit can also apply a concise display format to an entertainment article. For example, the filter unit applies a concise display format to an entertainment article. The filter unit can also apply a display format including technical terms to a scientific article. For example, the filter unit applies a display format including technical terms to a scientific article. In this way, the filter unit can provide information suitable for the category by applying different filtering algorithms depending on the category of the article. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the category of the article and applies a filtering algorithm.

[0125] The filter unit can evaluate the reliability of an article during filtering and preferentially filter highly reliable information. The filter unit, for example, evaluates the reliability of an article. For example, the filter unit preferentially displays information from a highly reliable news source. The filter unit can also lower the display priority of information from a less reliable news source. For example, the filter unit lowers the display priority of information from a less reliable news source. The filter unit can also evaluate the reliability of an article and reflect the highly reliable information in the display. For example, the filter unit evaluates the reliability of an article and reflects the highly reliable information in the display. In this way, the filter unit can provide highly reliable information by evaluating the reliability of the article. Part or all of the above-mentioned processing in the filter unit may be performed, for example, using AI or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that uses the reliability of an article as an input and filters highly reliable information.

[0126] The filter unit can preferentially filter highly relevant articles in consideration of the geographical location information of the user during filtering. The filter unit, for example, filters news articles in consideration of the geographical location information of the user. For example, the filter unit preferentially displays local news related to the user's current location. In addition, when the user is traveling, the filter unit can also preferentially display news related to the travel destination. For example, the filter unit displays news related to the travel destination while the user is traveling. In addition, the filter unit can also preferentially display articles related to local events and occurrences based on the geographical location information of the user. For example, the filter unit displays articles related to local events and occurrences related to the user's current location. In this way, the filter unit can provide highly relevant local news by considering the geographical location information of the user. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0127] The filter unit can select an optimal filtering method in consideration of the device information of the user at the time of filtering. The filter unit, for example, filters news articles in consideration of the device information of the user. For example, when the user is using a smartphone, the filter unit provides a display method optimized for mobile. In addition, when the user is using a tablet, the filter unit can also provide a display method optimized for a large screen. For example, when the user is using a tablet, the filter unit provides a display method optimized for the device. In addition, when the user is using a desktop, the filter unit can also provide a display method that provides detailed information. For example, when the user is using a desktop, the filter unit provides a display method optimized for the device. In this way, the filter unit can provide an optimal filtering method by considering the device information of the user. Part or all of the above-mentioned processing in the filter unit may be performed, for example, using AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the device information of the user and outputs the optimal filtering method.

[0128] The filter unit can analyze the social media activity of the user and filter related articles at the time of filtering. The filter unit, for example, analyzes the social media activity of the user to filter news articles. For example, the filter unit filters related news based on articles shared by the user on social media. The filter unit can also filter related news based on the posted content of an account followed by the user on social media. For example, the filter unit analyzes the posted content of an account followed by the user and filters news related to the content. The filter unit can also filter related news based on an article that the user has "liked" or commented on on social media. For example, the filter unit analyzes an article that the user has "liked" or commented on and filters news related to the content. In this way, the filter unit can provide highly relevant news articles by analyzing the social media activity of the user. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the social media activity of the user and outputs related articles.

[0129] The filter unit can filter highly relevant articles preferentially by referring to the user's past purchase history during filtering. The filter unit, for example, filters news articles by referring to the user's past purchase history. For example, the filter unit preferentially filters news related to products purchased by the user in the past. The filter unit can also filter news related to topics that the user is likely to be interested in from the user's purchase history. For example, the filter unit filters news related to products purchased by the user in the past. The filter unit can also preferentially filter reviews and evaluation articles related to products purchased by the user in the past. For example, the filter unit filters reviews and evaluation articles related to products purchased by the user in the past. In this way, the filter unit can provide highly relevant news articles by referring to the user's past purchase history. Part or all of the above-mentioned processing in the filter unit may be performed using, for example, AI, or may be performed without using AI. For example, the filter unit can perform filtering using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0130] The customization unit can estimate the user's emotion and adjust the customization method based on the estimated user's emotion. The customization unit, for example, estimates the user's emotion. For example, the customization unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The customization unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the customization unit analyzes the tone and speed of the voice and calculates an emotion score. The customization unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the customization unit calculates an emotion score based on the heart rate fluctuation. Thereby, the customization unit can provide a display suitable for the user by adjusting the customization method based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the customization unit may be performed using, for example, AI, or may be performed without using AI. For example, the customization unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0131] The customization unit can select an optimal customization method by referring to the user's past browsing history at the time of customization. The customization unit, for example, selects a customization method by referring to the user's past browsing history. For example, the customization unit preferentially provides a display format that the user has preferred in the past. The customization unit can also select an optimal display layout from the user's past browsing history. For example, the customization unit selects an optimal display layout from the user's past browsing history. The customization unit can also provide an optimal display method by referring to a display method of an article that the user has previously viewed. For example, the customization unit provides an optimal display method by referring to a display method of an article that the user has previously viewed. Thereby, the customization unit can provide an optimal customization method by referring to the user's past browsing history. A part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the user's past browsing history and outputs an optimal customization method.

[0132] The customization unit can determine the priority of customization based on the importance of the article at the time of customization. The customization unit determines the priority of customization based on, for example, the importance of the article. For example, the customization unit preferentially displays articles with high importance. The customization unit can also lower the display priority of articles with low importance. For example, the customization unit lowers the display priority of articles with low importance. The customization unit can also adjust the display order according to the importance of the article. For example, the customization unit adjusts the display order according to the importance of the article. As a result, the customization unit can provide important information preferentially by determining the priority of customization based on the importance of the article. A part or all of the above-mentioned processing in the customization unit may be performed using, for example, AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the importance of the article and determines the priority of customization.

[0133] The customization unit can apply different customization algorithms depending on the category of the article during customization. The customization unit applies the customization algorithm, for example, depending on the category of the article. For example, the customization unit applies a detailed display format to a political article. The customization unit can also apply a concise display format to an entertainment article. For example, the customization unit applies a concise display format to an entertainment article. The customization unit can also apply a display format including technical terms to a scientific article. For example, the customization unit applies a display format including technical terms to a scientific article. In this way, the customization unit can provide information suitable for the category by applying different customization algorithms depending on the category of the article. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the category of the article and applies the customization algorithm.

[0134] The customization unit can evaluate the reliability of an article at the time of customization, and customize highly reliable information with priority. The customization unit, for example, evaluates the reliability of an article. For example, the customization unit preferentially displays information from a highly reliable news source. The customization unit can also lower the display priority of information from a less reliable news source. For example, the customization unit can lower the display priority of information from a less reliable news source. The customization unit can also evaluate the reliability of an article and reflect the highly reliable information in the display. For example, the customization unit evaluates the reliability of an article and reflects the highly reliable information in the display. In this way, the customization unit can provide highly reliable information by evaluating the reliability of the article. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that uses the reliability of an article as an input and customizes highly reliable information.

[0135] The customization unit can estimate the user's emotion during customization and adjust the order of customization based on the estimated user's emotion. The customization unit, for example, estimates the user's emotion. For example, the customization unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The customization unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the customization unit analyzes the tone and speed of the voice and calculates an emotion score. The customization unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the customization unit calculates an emotion score based on the heart rate fluctuation. Thereby, the customization unit can provide information suitable for the user by adjusting the order of customization based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the customization unit may be performed using, for example, AI, or may be performed without using AI. For example, the customization unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0136] During customization, the customization unit can prioritize customizing highly relevant articles in consideration of the geographical location information of the user. The customization unit customizes news articles in consideration of, for example, the geographical location information of the user. For example, the customization unit prioritizes displaying local news related to the user's current location. In addition, when the user is traveling, the customization unit can also prioritize displaying news related to the travel destination. For example, the customization unit displays news related to the travel destination while the user is traveling. In addition, the customization unit can also prioritize displaying articles related to local events and occurrences based on the geographical location information of the user. For example, the customization unit displays articles related to local events and occurrences related to the user's current location. In this way, the customization unit can provide highly relevant local news by considering the geographical location information of the user. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the geographical location information of the user and outputs highly relevant articles.

[0137] The customization unit can select the optimal customization method in consideration of the device information of the user at the time of customization. The customization unit customizes the news article in consideration of, for example, the device information of the user. For example, when the user is using a smartphone, the customization unit provides a display method optimized for mobile. In addition, when the user is using a tablet, the customization unit can also provide a display method optimized for a large screen. For example, when the user is using a tablet, the customization unit provides a display method optimized for the device. In addition, when the user is using a desktop, the customization unit can also provide a display method that provides detailed information. For example, when the user is using a desktop, the customization unit provides a display method optimized for the device. In this way, the customization unit can provide the optimal customization method by considering the device information of the user. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the device information of the user and outputs the optimal customization method.

[0138] The customization unit can analyze the user's social media activity and customize related articles at the time of customization. The customization unit, for example, customizes news articles by analyzing the user's social media activity. For example, the customization unit displays related news based on articles shared by the user on social media. The customization unit can also display related news based on the posted content of an account followed by the user on social media. For example, the customization unit analyzes the posted content of an account followed by the user and displays news related to the content. The customization unit can also display related news based on articles that the user has "liked" or commented on on social media. For example, the customization unit analyzes articles that the user has "liked" or commented on and displays news related to the content. In this way, the customization unit can provide highly relevant news articles by analyzing the user's social media activity. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the user's social media activity and outputs related articles.

[0139] During customization, the customization unit can refer to the user's past purchase history and preferentially customize highly relevant articles. The customization unit, for example, refers to the user's past purchase history to customize news articles. For example, the customization unit preferentially displays news related to products purchased by the user in the past. The customization unit can also display news related to topics that the user is likely to be interested in from the user's purchase history. For example, the customization unit displays news related to products purchased by the user in the past. The customization unit can also preferentially display reviews and evaluation articles related to products purchased by the user in the past. For example, the customization unit displays reviews and evaluation articles related to products purchased by the user in the past. In this way, the customization unit can provide highly relevant news articles by referring to the user's past purchase history. Part or all of the above-mentioned processing in the customization unit may be performed, for example, using AI, or may be performed without using AI. For example, the customization unit can perform customization using an AI model that inputs the user's past purchase history and outputs highly relevant articles.

[0140] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0141] The news summarization system may further include an interest evaluation unit that evaluates the user's interest in real time. The interest evaluation unit analyzes the scroll speed and stay time when the user browses a news article, and evaluates the user's interest. For example, if the user stays on a particular article for a long time, it is determined that the user has a high interest in that article. The interest evaluation unit may also evaluate the interest based on the frequency with which the user shares or comments on an article. This allows the interest evaluation unit to adjust the display order of news articles based on the user's interest. Furthermore, the interest evaluation unit may preferentially collect related news articles based on the user's interest. This allows the user to efficiently browse news articles that match his or her interests.

[0142] The generation unit may include a reliability evaluation unit that evaluates the reliability of an article when generating a summary. The reliability evaluation unit evaluates reliability based on the reliability of the news source and the past track record of the article's writer. For example, information from a reliable news source is preferentially included in the summary. The reliability evaluation unit can also check whether the content of the article is consistent with other reliable sources. This allows the generation unit to generate a summary including reliable information. Furthermore, the reliability evaluation unit can display the reliability evaluation result to the user. This allows the user to make a decision based on reliable information.

[0143] The filter unit can estimate the user's emotions and adjust the filtering criteria based on the estimated emotions. For example, if the user is feeling stressed, the filter unit can preferentially display articles with relaxing content. Also, if the user is excited, the filter unit can preferentially display articles with a high entertainment value. Furthermore, the filter unit can filter articles related to a specific topic based on the user's emotions. For example, if the user is sad, the filter unit can preferentially display articles with positive content. In this way, the filter unit can provide information according to the user's emotions.

[0144] The customization unit can estimate the user's emotion and adjust the customization method based on the estimated emotion. For example, when the user is tired, the customization unit provides a simple and easy-to-read display format. Also, when the user is excited, the customization unit can provide a colorful and interactive display format. Furthermore, the customization unit can adjust the order of articles to be displayed based on the user's emotion. For example, when the user is relaxed, the customization unit preferentially displays articles with relaxing content. In this way, the customization unit can provide an optimal display method according to the user's emotion.

[0145] The collection unit can estimate the user's emotions and select news sites to be collected based on the estimated emotions. For example, if the user is feeling stressed, the collection unit can preferentially collect news sites that provide articles with relaxing content. Also, if the user is excited, the collection unit can preferentially collect news sites with a high entertainment value. Furthermore, the collection unit can select news sites related to a specific topic based on the user's emotions. For example, if the user is sad, the collection unit preferentially collects news sites that provide articles with positive content. This allows the collection unit to select the optimal news site according to the user's emotions.

[0146] The news summarization system may further include a geographic information collection unit that collects news articles taking into consideration the geographic location information of the user. The geographic information collection unit preferentially collects local news related to the user's current location. For example, if the user is in a particular city, the geographic information collection unit collects news articles related to the city. In addition, if the user is traveling, the geographic information collection unit may also collect news articles related to the travel destination. Furthermore, the geographic information collection unit may collect articles about local events and happenings based on the user's geographic location information. This allows the user to obtain the latest information related to his or her current location.

[0147] The news summarization system may further include a social media analysis unit that analyzes the user's social media activities to collect news articles. The social media analysis unit collects related news articles based on articles shared by the user on social media. For example, if the user shares an article on a specific topic, news articles related to the topic are collected. The social media analysis unit may also collect related news articles based on the content posted by accounts the user follows. Furthermore, the social media analysis unit may also collect related news articles based on articles that the user has "liked" or commented on. This allows the user to efficiently obtain news articles that match their interests.

[0148] The news summarization system may further include a device information collection unit that collects news articles taking into account device information of the user. When the user is using a smartphone, the device information collection unit collects articles from a news site optimized for mobile devices. For example, articles in a display format optimized for smartphones are collected. When the user is using a tablet, the device information collection unit may also collect articles from a news site optimized for a large screen. Furthermore, when the user is using a desktop, the device information collection unit may also collect articles from a news site that provides detailed information. This allows the user to efficiently obtain news articles optimized for his or her device.

[0149] The news summarization system may further include a purchase history analysis unit that collects news articles by referring to the user's past purchase history. The purchase history analysis unit collects news articles related to products that the user has purchased in the past. For example, when the user has purchased a specific product, news articles related to the product are collected. The purchase history analysis unit may also collect news articles related to topics that the user may be interested in from the user's purchase history. Furthermore, the purchase history analysis unit may collect reviews and evaluation articles related to products that the user has purchased in the past. This allows the user to obtain the latest information related to his or her purchase history.

[0150] The news summarization system may further include a search history analysis unit that collects news articles by referring to the user's past search history. The search history analysis unit collects related news articles based on keywords previously searched by the user. For example, when a user searches for a keyword related to a specific topic, news articles related to the topic are collected. The search history analysis unit may also collect related news articles based on topics previously searched by the user. Furthermore, the search history analysis unit may collect news articles related to a specific theme from the user's past search history. This allows the user to obtain the latest information related to his or her search history.

[0151] The process flow of the second embodiment will be briefly described below.

[0152] Step 1: The collection unit collects news articles. The news articles include online news, newspaper articles, blog articles, etc. The collection unit collects news articles using web scraping technology, RSS feeds, and APIs. For example, the collection unit uses an API to collect articles from a specific news site. Step 2: The generator uses a generative AI to summarize the articles collected by the collector. The summary is designed to include the article title, lead text, and main points of the text. The generator uses a text generation AI (e.g., LLM) to summarize the article and extract the important parts of the article to create a summary. Step 3: The display unit displays a list of the summaries generated by the generation unit. The display unit can display the summaries on a web browser, a mobile application, or a desktop application. For example, the summaries are displayed in a card format.

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0154] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0155] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0156] For example, the collection unit collects news articles using the camera 42 and microphone 38B of the smart device 14, and processes the collected articles by the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates summaries using a generation AI. The display unit displays summaries in a list by the display 40A of the smart device 14, for example. The filter unit is realized, for example, by the control unit 46A of the smart device 14, and filters the summaries based on keywords specified by the user. The customization unit is realized, for example, by the control unit 46A of the smart device 14, and customizes the summaries based on the display order and display items specified by the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0157] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0158] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0164] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0165] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0167] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0171] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0172] For example, the collection unit collects news articles using the camera 42 and microphone 238 of the smart glasses 214, and processes the collected articles by the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates summaries using a generation AI. The display unit displays summaries in a list by the display of the smart glasses 214, for example. The filter unit is realized, for example, by the control unit 46A of the smart glasses 214, and filters the summaries based on keywords specified by the user. The customization unit is realized, for example, by the control unit 46A of the smart glasses 214, and customizes the summaries based on the display order and display items specified by the user. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0173] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0174] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0175] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0176] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0177] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0179] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0180] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0181] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0182] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0183] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0184] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0185] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0186] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0187] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0188] For example, the collection unit collects news articles using the camera 42 and microphone 238 of the headset type terminal 314, and processes the collected articles by the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates summaries using a generation AI. The display unit displays summaries in a list by the display 343 of the headset type terminal 314, for example. The filter unit is realized, for example, by the control unit 46A of the headset type terminal 314, and filters the summaries based on keywords specified by the user. The customization unit is realized, for example, by the control unit 46A of the headset type terminal 314, and customizes the summaries based on the display order and display items specified by the user. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0189] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0190] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0191] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0192] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0193] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0194] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0195] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0196] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0197] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0198] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0199] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0200] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0201] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0202] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0203] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0204] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0205] For example, the collection unit collects news articles using the camera 42 and microphone 238 of the robot 414, and processes the collected articles by the specific processing unit 290 of the data processing device 12. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates summaries using a generation AI. The display unit displays summaries in a list on the display of the robot 414, for example. The filter unit is realized, for example, by the control unit 46A of the robot 414, and filters the summaries based on keywords specified by the user. The customization unit is realized, for example, by the control unit 46A of the robot 414, and customizes the summaries based on the display order and display items specified by the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0206] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0207] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0208] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0209] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0210] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0211] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0212] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0213] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0214] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0215] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0216] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0217] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0218] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0219] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0220] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0221] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0222] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0223] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0224] (Appendix 1) a collection department for collecting news articles; a generation unit that generates summaries of the articles collected by the collection unit using a large-scale language model; a display unit that displays a list of the summaries generated by the generation unit; A system characterized by: (Appendix 2) The generation unit is Include the article title or lead sentence, and the main points of the text in the summary 2. The system of claim 1, (Appendix 3) A filter section is provided for allowing the user to filter the summary. 2. The system of claim 1, (Appendix 4) It has a customization section that allows users to customize the summary list display. 2. The system of claim 1, (Appendix 5) The collecting unit includes: Estimate user sentiment and prioritize news articles based on the estimated user sentiment 2. The system of claim 1, (Appendix 6) The collecting unit includes: Analyze users' past browsing history and select the appropriate collection method 2. The system of claim 1, (Appendix 7) The collecting unit includes: When collecting news articles, filter them based on specific keywords or topics 2. The system of claim 1, (Appendix 8) The collecting unit includes: Dynamically change news article collection based on the user's current interests 2. The system of claim 1, (Appendix 9) The collecting unit includes: When collecting news articles, the system refers to the user's past search history and prioritizes collecting articles that are highly relevant. 2. The system of claim 1, (Appendix 10) The collecting unit includes: Estimate user sentiment and select news sites to collect based on the estimated user sentiment. 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting news articles, the system prioritizes collecting articles that are highly relevant to the user by taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 12) The collecting unit includes: When collecting news articles, analyze users' social media activity and collect related articles. 2. The system of claim 1, (Appendix 13) The collecting unit includes: When collecting news articles, the optimal collection method is selected taking into account the user's device information. 2. The system of claim 1, (Appendix 14) The collecting unit includes: When collecting news articles, prioritize collecting articles that are highly relevant by referring to the user's past purchase history. 2. The system of claim 1, (Appendix 15) The generation unit is Estimate the user's emotions and adjust the way summaries are presented based on the estimated user emotions. 2. The system of claim 1, (Appendix 16) The generation unit is When generating summaries, adjust the level of detail in the summary based on the importance of the article. 2. The system of claim 1, (Appendix 17) The generation unit is When generating summaries, different summarization algorithms are applied depending on the article category. 2. The system of claim 1, (Appendix 18) The generation unit is When generating summaries, the article's credibility is evaluated and the most credible information is prioritized for inclusion in the summary. 2. The system of claim 1, (Appendix 19) The generation unit is During abstract generation, prioritize abstracts based on the age of the article 2. The system of claim 1, (Appendix 20) The generation unit is When generating summaries, adjust the order of summaries based on article relevance 2. The system of claim 1, (Appendix 21) The generation unit is When generating summaries, different summarization algorithms are applied depending on the article's language and region. 2. The system of claim 1, (Appendix 22) The generation unit is When generating summaries, the author information of the article is taken into account to evaluate the reliability of the summaries. 2. The system of claim 1, (Appendix 23) The display unit is Estimate user's emotions and adjust the display method based on the estimated user's emotions 2. The system of claim 1, (Appendix 24) The display unit is When displaying, the optimal display method is selected by referring to the user's past browsing history. 2. The system of claim 1, (Appendix 25) The display unit is When displaying, determine display priority based on article importance 2. The system of claim 1, (Appendix 26) The display unit is Apply different display formats depending on the article category when viewing 2. The system of claim 1, (Appendix 27) The display unit is When displayed, the article's credibility is evaluated and the most reliable information is displayed first. 2. The system of claim 1, (Appendix 28) The display unit is Infer user emotion and adjust display order based on the estimated user emotion 2. The system of claim 1, (Appendix 29) The display unit is At display time, the site takes into account the user's geographic location to prioritize relevant articles. 2. The system of claim 1, (Appendix 30) The display unit is When displaying, the optimal display method is selected taking into account the user's device information. 2. The system of claim 1, (Appendix 31) The display unit is At the time of viewing, analyze the user's social media activity and display relevant articles 2. The system of claim 1, (Appendix 32) The display unit is When displayed, articles with high relevance are displayed preferentially by referring to the user's past purchase history. 2. The system of claim 1, (Appendix 33) The filter unit includes: Inferring a user's emotions and adjusting filtering criteria based on the estimated user's emotions 2. The system of claim 1, (Appendix 34) The filter unit includes: When filtering, the optimal filtering method is selected by referring to the user's past browsing history. 2. The system of claim 1, (Appendix 35) The filter unit includes: When filtering, determine filtering priority based on article importance 2. The system of claim 1, (Appendix 36) The filter unit includes: When filtering, apply different filtering algorithms depending on the article category 2. The system of claim 1, (Appendix 37) The filter unit includes: When filtering, the reliability of articles is evaluated and the most reliable information is given priority. 2. The system of claim 1, (Appendix 38) The filter unit includes: When filtering, the geographic location of the user is taken into consideration to prioritize relevant articles. 2. The system of claim 1, (Appendix 39) The filter unit includes: When filtering, the optimal filtering method is selected taking into account the user's device information. 2. The system of claim 1, (Appendix 40) The filter unit includes: When filtering, analyze the user's social media activity and filter relevant articles. 2. The system of claim 1, (Appendix 41) The filter unit includes: When filtering, prioritize filtering to articles with high relevance by referring to the user's past purchase history. 2. The system of claim 1, (Appendix 42) The customization unit includes: Inferring a user's emotions and adjusting the customization method based on the inferred user's emotions 2. The system of claim 1, (Appendix 43) The customization unit includes: When customizing, the optimal customization method is selected by referring to the user's past browsing history. 2. The system of claim 1, (Appendix 44) The customization unit includes: During customization, prioritize customizations based on the importance of the article 2. The system of claim 1, (Appendix 45) The customization unit includes: During customization, apply different customization algorithms depending on the article category 2. The system of claim 1, (Appendix 46) The customization unit includes: When customizing, evaluate the reliability of articles and prioritize the most reliable information. 2. The system of claim 1, (Appendix 47) The customization unit includes: During customization, the user's emotion is estimated and the customization order is adjusted based on the estimated user's emotion. 2. The system of claim 1, (Appendix 48) The customization unit includes: During customization, take into account the user's geographic location information and prioritize relevant articles. 2. The system of claim 1, (Appendix 49) The customization unit includes: When customizing, select the optimal customization method taking into account the user's device information 2. The system of claim 1, (Appendix 50) The customization unit includes: During customization, analyze users' social media activity and customize relevant articles 2. The system of claim 1, (Appendix 51) The customization unit includes: When customizing, prioritize articles that are highly relevant to the user by referring to the user's past purchase history 2. The system of claim 1, [Explanation of symbols]

[0225] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection department for collecting news articles; a generation unit that generates summaries of the articles collected by the collection unit using a large-scale language model; a display unit that displays a list of the summaries generated by the generation unit; A system characterized by:

2. The generation unit is Include the article title or lead sentence, and the main points of the text in the summary 2. The system of claim 1 .

3. A filter section is provided for allowing the user to filter the summary.

2. The system of claim 1 .

4. It has a customization section that allows users to customize the summary list display.

2. The system of claim 1 .

5. The collecting unit includes: Estimate user sentiment and prioritize news articles based on the estimated user sentiment 2. The system of claim 1 .

6. The collecting unit includes: Analyze users' past browsing history and select the appropriate collection method 2. The system of claim 1 .

7. The collecting unit includes: When collecting news articles, filter them based on specific keywords or topics 2. The system of claim 1 .

8. The collecting unit includes: Dynamically change news article collection based on the user's current interests 2. The system of claim 1 .

9. The collecting unit includes: When collecting news articles, the system refers to the user's past search history and prioritizes collecting articles that are highly relevant.

2. The system of claim 1 .

10. The collecting unit includes: Estimate user sentiment and select news sites to collect based on the estimated user sentiment.

2. The system of claim 1 .

Images