System

Abstract

To provide a system which can extract important points from a large volume of information of news and can provide a user with the points in an appropriate manner.SOLUTION: A system according to an embodiment includes a collection unit, a specification unit, a generation unit, a classification unit, and a response unit. The collection unit collects data of news. The specification unit analyzes data of news collected by the collection unit and specifies an important point of news. The generation unit generates a summary of news on the basis of the important point specified by the specification unit. The classification unit categorizes the summary generated by the generation unit according to each topic. The responding unit provides information according to a user on the basis of the summary categorized by the classification 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] With conventional technology, it was difficult to efficiently extract important points from the vast amount of news information and provide it to users in an appropriate format.

[0005] The system according to the embodiment aims to extract important points from a vast amount of news information and provide them to users in an appropriate format. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an identification unit, a generation unit, a classification unit, and a response unit. The collection unit collects news data. The identification unit analyzes the news data collected by the collection unit and identifies important points of the news. The generation unit generates a news summary based on the important points identified by the identification unit. The classification unit categorizes the summary generated by the generation unit based on each topic. The response unit provides information according to the user based on the summary categorized by the classification unit. Effect of the Invention

[0007] The system according to the embodiment can extract important points from a vast amount of news information and provide them to the user in an appropriate format. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The AI ​​assistant for combining news article summaries and a question-answering system according to an embodiment of the present invention is a system that automatically collects news data, analyzes it to identify important points, and generates a summary of the news data. The system categorizes the generated summary based on each topic and provides information according to the user. The system also has a function to collect news data from multiple different sources and determine trends and changes. For example, news data is collected, analyzed to identify important points, and a summary is generated. The generated summary is categorized based on each topic and information according to the user is provided. The system also has a function to collect news data from multiple different sources and determine trends and changes. Based on the user's past browsing history and feedback, information according to the user's interests is suggested and visually provided. The system also has a function to evaluate the historical background and reliability of the source related to the news summary and filter the information based on the user's settings. The system also has a function to notify the latest news, so that the user can efficiently obtain the information he or she needs without getting lost in the sea of ​​information. As a result, the AI ​​assistant for combining news article summaries and a question-answering system can efficiently obtain the information he or she needs without getting lost in the sea of ​​information.

[0029] The combined AI assistant of the news article summary and question answering system according to the embodiment includes a collection unit, a specification unit, a generation unit, a classification unit, and a response unit. The collection unit collects news data. The news data includes, for example, text data, image data, video data, etc., but is not limited to such examples. The collection unit can collect news data from, for example, news sites, SNS, blogs, etc. The specification unit analyzes the news data collected by the collection unit and specifies important points of the news. The important points are specified, for example, based on a summary of the content of the news, extraction of keywords, etc., but is not limited to such examples. The specification unit can analyze the content of the news using, for example, natural language processing technology, and specify important points. The generation unit generates a news summary based on the important points specified by the specification unit. The summary is generated, for example, based on the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. The generation unit can generate a news summary using, for example, a generation AI. The generation AI can generate a news summary using a text generation AI (for example, LLM). The classification unit categorizes the summary generated by the generation unit based on each topic. The categorization is performed, for example, based on the classification criteria of the topic or the algorithm used, but is not limited to such examples. The classification unit can categorize the summary using, for example, AI. The response unit provides information according to the user based on the summary categorized by the classification unit. The information is provided, for example, based on the user's interests and concerns, but is not limited to such examples. The response unit can provide information according to the user using, for example, AI. As a result, the combination AI assistant of the news article summary and question answering system according to the embodiment can efficiently collect, analyze, summarize, categorize, and provide news data.

[0030] The collection unit collects news data. The news data includes, but is not limited to, for example, text data, image data, video data, and the like. The collection unit can collect news data from, for example, news sites, SNS, blogs, and the like. Specifically, the collection unit uses web scraping technology and API to automatically collect news data from various information sources on the Internet. When using web scraping technology, the collection unit analyzes the HTML structure of a specific webpage and extracts necessary data. When using API, the collection unit obtains the latest news data through the API published by the news provider. Furthermore, the collection unit has a database for centrally managing the collected data, and the collected news data is stored in this database. The database has an index function for efficiently managing data in different formats such as text data, image data, and video data, enabling rapid data search and access. In addition, the collection unit also has a function for evaluating the quality of the collected data, deleting duplicate data, and filtering noise data. This allows the collection unit to efficiently collect reliable news data and improve the performance of the entire system.

[0031] The identification unit analyzes the news data collected by the collection unit and identifies important points of the news. The important points are identified, for example, based on a summary of the news content, extraction of keywords, etc., but are not limited to such examples. The identification unit can analyze the content of the news using, for example, natural language processing technology and identify important points. Specifically, the identification unit breaks down the news text using morphological analysis and dependency structure analysis to understand the meaning of each word and phrase. Furthermore, the identification unit extracts important keywords in the news text using TF-IDF (Term Frequency-Inverse Document Frequency) and word embedding technology. This makes it possible to obtain basic information for efficiently summarizing the content of the news. In addition, the identification unit can use topic modeling technology (for example, LDA: Latent Dirichlet Allocation) to understand the context and topic of the news. This makes it possible to identify the main theme or topic of the news and improve the accuracy of summary generation. Furthermore, the identification unit also has a filtering function that selects important news based on specific conditions from the collected news data. For example, it is possible to extract only news related to a specific region or category. This enables the identification unit to quickly and accurately identify important points in the news and provide them as input data to the subsequent generation unit.

[0032] The generating unit generates a news summary based on the important points identified by the identifying unit. The summary is generated based on, for example, the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. The generating unit can generate a news summary using, for example, a generating AI. The generating AI can generate a news summary using a text generating AI (e.g., LLM). Specifically, the generating unit uses a generating AI model trained on a large news dataset in advance, receives important points provided by the identifying unit as input, and generates a summary in a natural sentence format. The generating AI generates a summary sentence based on input keywords and phrases while taking into account the context. For example, the generating AI concisely summarizes the main events and background information of the news so that readers can understand it in a short time. In addition, the generating unit checks the accuracy and consistency of the summary using an evaluation index (e.g., ROUGE score) for evaluating the quality of the generated summary sentence. In addition, the generating unit also has a function of adjusting the length and detail of the summary according to the user's request. For example, if a short summary is required, a concise summary including only the main points is generated, and if a detailed summary is required, a summary including more information is generated. This enables the generation unit to provide a high-quality news summary that meets the needs of the user.

[0033] The classification unit categorizes the summaries generated by the generation unit based on each topic. The categorization is performed, for example, based on the topic classification criteria and the algorithm used, but is not limited to such examples. The classification unit can categorize the summaries using, for example, AI. Specifically, the classification unit classifies the generated summaries into appropriate categories based on predefined topic categories (for example, politics, economy, sports, entertainment, etc.). The classification unit extracts features of the summary sentences using a machine learning algorithm (for example, support vector machine, random forest, neural network, etc.) and builds a classification model for each topic category. Furthermore, the classification unit can analyze the topic distribution of the summary sentences using a topic modeling technique (for example, LDA) and classify them into the most relevant category. The classification unit also has a function of classifying the summary sentences into personalized categories based on the user's interests and concerns. For example, the classification unit identifies topics in which the user is interested based on the user's past browsing history and feedback, and provides summary sentences related to those topics preferentially. This allows the categorization unit to efficiently and accurately categorize the generated summaries and provide highly relevant information to the user.

[0034] The response unit provides information according to the user based on the summaries categorized by the classification unit. The information is provided based on, for example, the user's interests and concerns, but is not limited to such examples. The response unit can provide information according to the user using, for example, AI. Specifically, the response unit selects a news summary that the user is interested in based on the user's profile information and past behavior history, and provides it in an appropriate format. For example, if the user is using a smartphone, the response unit provides the news summary through a push notification or an in-app notification. Also, if the user is using a desktop, the response unit can provide the news summary through a web browser notification or email. Furthermore, the response unit also has a function of generating an appropriate answer to a question from the user. For example, if the user inputs a question requesting detailed information about a specific news item, the response unit generates an appropriate answer using a generation AI based on the data obtained from the collection unit and the identification unit, and provides it to the user. The response unit can collect user feedback and continuously improve the accuracy and relevance of the information provided. For example, by the user rating the provided news summary, the response unit can adjust the summary generation and information provision algorithms based on the rating, and provide higher quality information. This enables the response unit to provide the user with prompt and appropriate information, thereby improving user satisfaction.

[0035] The collection unit can collect news data from a plurality of different information sources. The collection unit can collect news data from a plurality of different information sources, such as news sites, SNS, blogs, etc. This improves the diversity of information by collecting news from a plurality of information sources. Some 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 cause AI to collect data from news sites.

[0036] The classification unit may include a determination unit that determines trends and changes. The classification unit may include a determination unit that analyzes, for example, news data and determines trends and changes. Trends and changes are determined based on, for example, changes over time, changes in frequency, and the like, but are not limited to such examples. In this way, by determining trends and changes, the latest information can be provided. A part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit may have AI analyze news data and determine trends and changes.

[0037] The determination unit may include a providing unit that provides a determination result. The determination unit may include, for example, a providing unit that provides a determination result of a trend and a change. The determination result is provided based on, for example, an overview of the trend, details of the change, and the like, but is not limited to such an example. In this way, by providing the determination result, useful information can be provided to the user. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit may cause AI to provide the determination result of the trend and the change.

[0038] The response unit can suggest information according to the user's interest based on the user's past browsing history and feedback. The user's past browsing history and feedback are collected based on, for example, a browsing history saving method, a feedback collecting method, and the like, but are not limited to such examples. This improves the user's satisfaction by suggesting information according to the user's interest. A part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can have AI analyze the user's past browsing history and feedback to suggest information according to the user's interest.

[0039] The response unit may include a visualization unit that visually provides news summaries and related information. The visual presentation method may be based on, for example, graphs, charts, infographics, etc., but is not limited to such examples. This provides information visually, thereby deepening the user's understanding. Some or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to execute the visualization unit that visually provides news summaries and related information.

[0040] The response unit may include a historical background providing unit that provides a historical background related to the news summary. The historical background is provided based on, for example, past events, related historical facts, and the like, but is not limited to such examples. By providing the historical background, understanding of the news is deepened. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to provide the historical background related to the news summary.

[0041] The response unit may include a reliability evaluation unit that evaluates the reliability of the news source. The reliability is evaluated based on, for example, the reliability score of the information source, past reliability evaluation, etc., but is not limited to such examples. In this way, by evaluating the reliability of the news, it is possible to provide the user with reliable information. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to evaluate the reliability of the news source.

[0042] The response unit may include a filtering unit that filters information based on a user's settings. The user's settings are based on, for example, topics of interest, frequency of notifications, etc., but are not limited to such examples. By filtering information based on the user's settings, optimal information can be provided to the user. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to execute the filtering unit that filters information based on the user's settings.

[0043] The response unit can have a notification function for notifying the latest news. The notification function is provided, for example, based on push notification, email notification, etc., but is not limited to such examples. By notifying the latest news, the user can obtain the latest information without missing it. Some or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can cause AI to execute the notification function for notifying the latest news.

[0044] The generation unit can perform different summaries for each user attribute. The user attributes are collected based on, for example, age, sex, occupation, etc., but are not limited to such examples. This makes it possible to provide individualized information by performing summaries according to the user attributes. 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 may use a generation AI that generates different summaries based on the user attributes.

[0045] The collection unit can analyze the user's past news browsing history and select the optimal collection method. The optimal collection method is selected based on, for example, the frequency of collection, the selection criteria for the collection target, etc., but is not limited to such examples. For example, news categories that the user has frequently browsed in the past are collected with priority. In addition, if the user has a tendency to browse during a specific time period, news can be collected according to that time period. Furthermore, news sources that the user has highly rated in the past can be collected with priority. In this way, the optimal collection method can be selected by analyzing the user's past news 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 have AI analyze the user's past news browsing history and select the optimal collection method.

[0046] The collection unit can perform filtering based on the user's current field of interest when collecting news. The current field of interest is identified based on, for example, a recent browsing history, a search history, etc., but is not limited to such examples. For example, news related to a topic in which the user is currently interested is preferentially collected. In addition, if the user is interested in a specific event, news related to the event can also be collected. Furthermore, if the user is interested in a specific region, news related to the region can also be collected. In this way, by filtering news based on the user's current field of interest, it is possible to provide highly relevant news. 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 cause AI to execute a process of filtering news based on the user's current field of interest.

[0047] When collecting news, the collection unit can preferentially collect highly relevant news by considering the geographical location information of the user. The geographical location information is collected based on, for example, GPS data, IP address, etc., but is not limited to such examples. For example, news related to the area where the user is currently located is preferentially collected. In addition, when the user is traveling, news related to the travel destination can also be collected. Furthermore, when the user is interested in a specific area, news related to the area can also be preferentially collected. In this way, highly relevant news can be provided by considering the geographical location 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 cause AI to analyze the geographical location information of the user and preferentially collect highly relevant news.

[0048] The collection unit can analyze the user's social media activity and collect related news when collecting news. The social media activity is analyzed based on, for example, the content of the post, the number of likes, etc., but is not limited to such examples. For example, articles related to news shared by the user on social media are collected. News shared by accounts followed by the user can also be collected. Furthermore, articles related to news that the user "liked" on social media can also be collected. In this way, highly relevant news can be provided by analyzing the user's social media activity. 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 have AI analyze the user's social media activity and collect related news.

[0049] The identification unit can adjust the specific level of detail based on the importance of the news when identifying the news. The importance of the news is evaluated based on, for example, the influence of the news, the interest of readers, etc., but is not limited to such examples. For example, in the case of important news, detailed points are identified. In addition, in the case of general news, points that grasp the main points can also be identified. Furthermore, in the case of entertainment news, visually stimulating points can also be identified. As a result, important information can be provided preferentially by adjusting the specific level of detail based on the importance of the news. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can have AI evaluate the importance of the news and adjust the specific level of detail.

[0050] When identifying news, the identification unit can apply different identification algorithms depending on the news category. The news categories are classified based on, for example, politics, economy, sports, etc., but are not limited to such examples. For example, in the case of political news, a highly reliable source is preferentially identified. In addition, in the case of sports news, the game results and the performance of the players can also be identified. Furthermore, in the case of entertainment news, visually stimulating points can also be identified. In this way, by applying the identification algorithm depending on the news category, appropriate information according to the category can be provided. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can apply different identification algorithms to AI depending on the news category.

[0051] The identification unit can determine a specific priority based on the time of submission of the news when identifying the news. The time of submission of the news is evaluated based on, for example, the submission date and time, the latest information, etc., but is not limited to such examples. For example, the latest news is prioritized and identified. Also, past news can be used as a reference for identification. Furthermore, news submitted earlier can be identified with a lower priority. In this way, by determining a specific priority based on the time of submission of the news, the latest information can be provided preferentially. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can have AI evaluate the time of submission of the news and determine a specific priority.

[0052] The identification unit can adjust the specific order based on the relevance of the news when identifying the news. The relevance of the news is evaluated based on, for example, the degree of matching of the topic, related keywords, etc., but is not limited to such examples. For example, highly relevant news is preferentially identified. Also, less relevant news can be postponed. Furthermore, highly relevant news can be identified first, and then less relevant news can be identified. In this way, by adjusting the specific order based on the relevance of the news, highly relevant information can be provided preferentially. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can have AI evaluate the relevance of the news and adjust the specific order.

[0053] The generation unit can adjust the level of detail of the summary based on the importance of the news when generating the summary. The level of detail of the summary is adjusted based on, for example, the comprehensiveness of the information, detailed explanation, etc., but is not limited to such examples. For example, in the case of important news, a detailed summary can be generated. In addition, in the case of general news, a concise summary can also be generated. Furthermore, in the case of entertainment news, a visually stimulating summary can also be generated. In this way, by adjusting the level of detail of the summary based on the importance of the news, important information can be provided preferentially. 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 have the generation AI evaluate the importance of the news and adjust the level of detail of the summary.

[0054] The generating unit can apply different summarization algorithms depending on the news category when generating a summary. The summarization algorithm is applied based on, for example, abstractive summarization, extractive summarization, etc., but is not limited to such examples. For example, in the case of political news, a highly reliable source is given priority for summarization. In addition, in the case of sports news, game results and player performances can also be summarized. Furthermore, in the case of entertainment news, a visually stimulating summary can also be generated. In this way, by applying a summarization algorithm depending on the news category, an appropriate summary depending on the category can be provided. Part or all of the above-mentioned processing in the generating unit may be performed, for example, using a generating AI, or may be performed without using a generating AI. For example, the generating unit can apply different summarization algorithms to the generating AI depending on the news category.

[0055] The generation unit can determine the priority of summaries based on the submission time of news when generating summaries. The priority of summaries is determined based on, for example, the importance of news, the submission time, etc., but is not limited to such examples. For example, the latest news is given priority for summarization. Also, past news can be used as a reference for summarization. Furthermore, news submitted earlier can be summarized with a lower priority. In this way, by determining the priority of summaries based on the submission time of news, the latest information can be provided preferentially. 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 have the generation AI evaluate the submission time of news and determine the priority of summaries.

[0056] The generation unit can adjust the order of summaries based on the relevance of news when generating summaries. The order of summaries is adjusted based on, for example, the order of relevance or the order of importance, but is not limited to such examples. For example, highly relevant news is summarized with priority. Also, less relevant news can be postponed. Furthermore, highly relevant news can be summarized first, and then less relevant news can be summarized. In this way, by adjusting the order of summaries based on the relevance of news, highly relevant information can be provided with priority. 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 cause the generation AI to evaluate the relevance of news and adjust the order of summaries.

[0057] The classification unit can improve the accuracy of categorization by considering the interrelationships of news during categorization. The interrelationships of news are evaluated based on, for example, links of related news, common keywords, etc., but are not limited to such examples. For example, related news is grouped and categorized. In addition, the interrelationships of news can be analyzed and highly related news can be classified into the same category. Furthermore, the accuracy of categorization can be improved by considering the interrelationships of news. As a result, the accuracy of categorization is improved by considering the interrelationships of news. Part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit can improve the accuracy of categorization by having AI evaluate the interrelationships of news.

[0058] The classification unit can perform categorization taking into consideration the attribute information of the news submitter at the time of categorization. The attribute information of the submitter is collected based on, for example, the submitter's occupation, field of expertise, etc., but is not limited to such examples. For example, if the submitter of the news is an expert, it is classified into a specialized category. Also, if the submitter of the news is a general user, it can be classified into a general category. Furthermore, it can be classified into an appropriate category based on the attribute information of the news submitter. In this way, by taking into consideration the attribute information of the news submitter, more appropriate categorization can be provided. Part or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can have AI evaluate the attribute information of the news submitter and perform categorization.

[0059] The classification unit can perform categorization taking into account the geographical distribution of news at the time of categorization. The geographical distribution is evaluated, for example, based on news by region, news by country, etc., but is not limited to such examples. For example, categorization is performed based on the place of origin of the news. Categorization can also be performed based on the range of influence of the news. Furthermore, classification into an appropriate category can be performed taking into account the geographical distribution of the news. In this way, more appropriate categorization can be provided by taking into account the geographical distribution of the news. Part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit can have AI evaluate the geographical distribution of the news and perform categorization.

[0060] The classification unit can improve the accuracy of categorization by referring to related literature of the news at the time of categorization. The related literature is referenced based on, for example, academic papers, related news articles, etc., but is not limited to such examples. For example, the related literature is referenced to complement background information of the news. Also, the news category can be scrutinized based on the related literature. Furthermore, the accuracy of categorization can be improved by referring to the related literature. As a result, the accuracy of categorization is improved by referring to the related literature of the news. Part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit can improve the accuracy of categorization by having AI refer to the related literature of the news.

[0061] The response unit can provide optimal information by referring to the user's past browsing history when providing information. The optimal information is selected based on, for example, information based on the user's interest, the latest information, etc., but is not limited to such examples. For example, information related to news viewed by the user in the past can be provided. Information that is likely to be of interest to the user can also be provided based on the user's past browsing history. Furthermore, the optimal information can be provided by analyzing the user's past browsing history. As a result, optimal information can be provided by referring to the user's past browsing history. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can cause AI to refer to the user's past browsing history and provide optimal information.

[0062] The response unit can customize information based on the user's current field of interest when providing information. The current field of interest is identified based on, for example, a recent browsing history, a search history, etc., but is not limited to such examples. For example, information related to a topic in which the user is currently interested can be provided. In addition, if the user is interested in a specific event, information related to the event can be provided. Furthermore, if the user is interested in a specific region, information related to the region can be provided. In this way, by customizing information based on the user's current field of interest, more appropriate information can be provided. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can cause AI to execute processing to customize information based on the user's current field of interest.

[0063] The response unit can provide optimal information by considering the geographical location information of the user when providing information. The geographical location information is collected based on, for example, GPS data, IP address, etc., but is not limited to such examples. For example, information related to the area where the user is currently located is provided. In addition, if the user is traveling, information related to the travel destination can also be provided. Furthermore, if the user is interested in a specific area, information related to the area can also be provided. In this way, more appropriate information can be provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can have AI analyze the geographical location information of the user to provide optimal information.

[0064] The response unit can analyze the user's social media activity and suggest a means of providing information when providing information. The social media activity is analyzed based on, for example, the content of the post, the number of likes, etc., but is not limited to such examples. For example, information related to news shared by the user on social media can be provided. Information related to news shared by an account followed by the user can also be provided. Furthermore, information related to news that the user "liked" on social media can also be provided. In this way, by analyzing the user's social media activity, a more appropriate means of providing information can be suggested. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can have AI analyze the user's social media activity and suggest a means of providing information.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The collection unit can preferentially collect news related to a region by taking into account the geographical location information of the user. For example, if the user is staying in a specific region, news related to the region is preferentially collected. In addition, if the user is traveling, news related to the travel destination can also be collected. Furthermore, if the user is interested in a specific region, news related to the region can also be collected. In this way, highly relevant news can be provided by taking into account the geographical location information of the user.

[0067] The identification unit can adjust the specific level of detail based on the importance of the news. For example, in the case of important news, the identification unit can identify detailed points. In addition, in the case of general news, the identification unit can identify points that highlight the main points. Furthermore, in the case of entertainment news, the identification unit can identify visually stimulating points. In this way, important information can be provided preferentially by adjusting the specific level of detail based on the importance of the news.

[0068] The generator can apply different summarization algorithms depending on the news category. For example, in the case of political news, it prioritizes and summarizes reliable sources. In addition, in the case of sports news, it can also summarize game results and player performances. Furthermore, in the case of entertainment news, it can generate visually stimulating summaries. In this way, by applying summarization algorithms depending on the news category, it is possible to provide appropriate summaries according to the category.

[0069] The classification unit can improve the accuracy of categorization by taking into account the interrelationships between news items. For example, related news items are grouped and categorized. Also, the classification unit can analyze the interrelationships between news items and classify highly related news items into the same category. Furthermore, the classification unit can improve the accuracy of categorization by taking into account the interrelationships between news items. In this way, the accuracy of categorization is improved by taking into account the interrelationships between news items.

[0070] The response unit can analyze the user's social media activity and collect related news. For example, articles related to news shared by the user on social media can be collected. News shared by accounts the user follows can also be collected. Furthermore, articles related to news that the user "liked" on social media can also be collected. This makes it possible to provide highly relevant news by analyzing the user's social media activity.

[0071] The process flow of the first embodiment will be briefly described below.

[0072] Step 1: The collection unit collects news data. News data includes, but is not limited to, text data, image data, video data, and the like. The collection unit can collect news data from, for example, news sites, SNS, blogs, and the like. Step 2: The identification unit analyzes the news data collected by the collection unit and identifies important points of the news. The important points are identified, for example, based on a summary of the news content, extraction of keywords, etc., but are not limited to such examples. The identification unit can analyze the news content using, for example, natural language processing technology, and identify important points. Step 3: The generator generates a news summary based on the important points identified by the identifier. The summary is generated based on, for example, the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. The generator can generate the news summary using, for example, a generation AI. The generation AI can generate the news summary using a text generation AI (e.g., LLM). Step 4: The classifier categorizes the summaries generated by the generator based on each topic. The categorization is performed based on, for example, a topic classification criterion or an algorithm to be used, but is not limited to such examples. The classifier can categorize the summaries using, for example, AI. Step 5: The response unit provides information appropriate to the user based on the summary categorized by the classification unit. The information is provided based on, for example, the user's interests and concerns, but is not limited to such an example. The response unit can provide information appropriate to the user using, for example, AI.

[0073] (Example 2) The AI ​​assistant for combining news article summaries and a question-answering system according to an embodiment of the present invention is a system that automatically collects news data, analyzes it to identify important points, and generates a summary of the news data. The system categorizes the generated summary based on each topic and provides information according to the user. The system also has a function to collect news data from multiple different sources and determine trends and changes. For example, news data is collected, analyzed to identify important points, and a summary is generated. The generated summary is categorized based on each topic and information according to the user is provided. The system also has a function to collect news data from multiple different sources and determine trends and changes. Based on the user's past browsing history and feedback, information according to the user's interests is suggested and visually provided. The system also has a function to evaluate the historical background and reliability of the source related to the news summary and filter the information based on the user's settings. The system also has a function to notify the latest news, so that the user can efficiently obtain the information he or she needs without getting lost in the sea of ​​information. As a result, the AI ​​assistant for combining news article summaries and a question-answering system can efficiently obtain the information he or she needs without getting lost in the sea of ​​information.

[0074] The combined AI assistant of the news article summary and question answering system according to the embodiment includes a collection unit, a specification unit, a generation unit, a classification unit, and a response unit. The collection unit collects news data. The news data includes, for example, text data, image data, video data, etc., but is not limited to such examples. The collection unit can collect news data from, for example, news sites, SNS, blogs, etc. The specification unit analyzes the news data collected by the collection unit and specifies important points of the news. The important points are specified, for example, based on a summary of the content of the news, extraction of keywords, etc., but is not limited to such examples. The specification unit can analyze the content of the news using, for example, natural language processing technology, and specify important points. The generation unit generates a news summary based on the important points specified by the specification unit. The summary is generated, for example, based on the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. The generation unit can generate a news summary using, for example, a generation AI. The generation AI can generate a news summary using a text generation AI (for example, LLM). The classification unit categorizes the summary generated by the generation unit based on each topic. The categorization is performed, for example, based on the classification criteria of the topic or the algorithm used, but is not limited to such examples. The classification unit can categorize the summary using, for example, AI. The response unit provides information according to the user based on the summary categorized by the classification unit. The information is provided, for example, based on the user's interests and concerns, but is not limited to such examples. The response unit can provide information according to the user using, for example, AI. As a result, the combination AI assistant of the news article summary and question answering system according to the embodiment can efficiently collect, analyze, summarize, categorize, and provide news data.

[0075] The collection unit collects news data. The news data includes, but is not limited to, for example, text data, image data, video data, and the like. The collection unit can collect news data from, for example, news sites, SNS, blogs, and the like. Specifically, the collection unit uses web scraping technology and API to automatically collect news data from various information sources on the Internet. When using web scraping technology, the collection unit analyzes the HTML structure of a specific webpage and extracts necessary data. When using API, the collection unit obtains the latest news data through the API published by the news provider. Furthermore, the collection unit has a database for centrally managing the collected data, and the collected news data is stored in this database. The database has an index function for efficiently managing data in different formats such as text data, image data, and video data, enabling rapid data search and access. In addition, the collection unit also has a function for evaluating the quality of the collected data, deleting duplicate data, and filtering noise data. This allows the collection unit to efficiently collect reliable news data and improve the performance of the entire system.

[0076] The identification unit analyzes the news data collected by the collection unit and identifies important points of the news. The important points are identified, for example, based on a summary of the news content, extraction of keywords, etc., but are not limited to such examples. The identification unit can analyze the content of the news using, for example, natural language processing technology and identify important points. Specifically, the identification unit breaks down the news text using morphological analysis and dependency structure analysis to understand the meaning of each word and phrase. Furthermore, the identification unit extracts important keywords in the news text using TF-IDF (Term Frequency-Inverse Document Frequency) and word embedding technology. This makes it possible to obtain basic information for efficiently summarizing the content of the news. In addition, the identification unit can use topic modeling technology (for example, LDA: Latent Dirichlet Allocation) to understand the context and topic of the news. This makes it possible to identify the main theme or topic of the news and improve the accuracy of summary generation. Furthermore, the identification unit also has a filtering function that selects important news based on specific conditions from the collected news data. For example, it is possible to extract only news related to a specific region or category. This enables the identification unit to quickly and accurately identify important points in the news and provide them as input data to the subsequent generation unit.

[0077] The generating unit generates a news summary based on the important points identified by the identifying unit. The summary is generated based on, for example, the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. The generating unit can generate a news summary using, for example, a generating AI. The generating AI can generate a news summary using a text generating AI (e.g., LLM). Specifically, the generating unit uses a generating AI model trained on a large news dataset in advance, receives important points provided by the identifying unit as input, and generates a summary in a natural sentence format. The generating AI generates a summary sentence based on input keywords and phrases while taking into account the context. For example, the generating AI concisely summarizes the main events and background information of the news so that readers can understand it in a short time. In addition, the generating unit checks the accuracy and consistency of the summary using an evaluation index (e.g., ROUGE score) for evaluating the quality of the generated summary sentence. In addition, the generating unit also has a function of adjusting the length and detail of the summary according to the user's request. For example, if a short summary is required, a concise summary including only the main points is generated, and if a detailed summary is required, a summary including more information is generated. This enables the generation unit to provide a high-quality news summary that meets the needs of the user.

[0078] The classification unit categorizes the summaries generated by the generation unit based on each topic. The categorization is performed, for example, based on the topic classification criteria and the algorithm used, but is not limited to such examples. The classification unit can categorize the summaries using, for example, AI. Specifically, the classification unit classifies the generated summaries into appropriate categories based on predefined topic categories (for example, politics, economy, sports, entertainment, etc.). The classification unit uses a machine learning algorithm (for example, support vector machine, random forest, neural network, etc.) to extract features of the summary sentences and build a classification model for each topic category. Furthermore, the classification unit can analyze the topic distribution of the summary sentences using a topic modeling technique (for example, LDA) and classify them into the most relevant category. The classification unit also has a function of classifying the summary sentences into personalized categories based on the user's interests and concerns. For example, the classification unit identifies topics in which the user is interested based on the user's past browsing history and feedback, and provides summary sentences related to the topics preferentially. This allows the categorization unit to efficiently and accurately categorize the generated summaries and provide highly relevant information to the user.

[0079] The response unit provides information according to the user based on the summaries categorized by the classification unit. The information is provided based on, for example, the user's interests and concerns, but is not limited to such examples. The response unit can provide information according to the user using, for example, AI. Specifically, the response unit selects a news summary that the user is interested in based on the user's profile information and past behavior history, and provides it in an appropriate format. For example, if the user is using a smartphone, the response unit provides the news summary through a push notification or an in-app notification. Also, if the user is using a desktop, the response unit can provide the news summary through a web browser notification or email. Furthermore, the response unit also has a function of generating an appropriate answer to a question from the user. For example, if the user inputs a question requesting detailed information about a specific news item, the response unit generates an appropriate answer using a generation AI based on the data obtained from the collection unit and the identification unit, and provides it to the user. The response unit can collect user feedback and continuously improve the accuracy and relevance of the information provided. For example, by the user rating the provided news summary, the response unit can adjust the summary generation and information provision algorithms based on the rating, and provide higher quality information. This enables the response unit to provide the user with prompt and appropriate information, thereby improving user satisfaction.

[0080] The collection unit can collect news data from a plurality of different information sources. The collection unit can collect news data from a plurality of different information sources, such as news sites, SNS, blogs, etc. This improves the diversity of information by collecting news from a plurality of information sources. Some 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 cause AI to collect data from news sites.

[0081] The classification unit may include a determination unit that determines trends and changes. The classification unit may include a determination unit that analyzes, for example, news data and determines trends and changes. Trends and changes are determined based on, for example, changes over time, changes in frequency, and the like, but are not limited to such examples. In this way, by determining trends and changes, the latest information can be provided. A part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit may have AI analyze news data and determine trends and changes.

[0082] The determination unit may include a providing unit that provides a determination result. The determination unit may include, for example, a providing unit that provides a determination result of a trend and a change. The determination result is provided based on, for example, an overview of the trend, details of the change, and the like, but is not limited to such an example. In this way, by providing the determination result, useful information can be provided to the user. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI, or may be performed without using AI. For example, the determination unit may cause AI to provide the determination result of the trend and the change.

[0083] The response unit can suggest information according to the user's interest based on the user's past browsing history and feedback. The user's past browsing history and feedback are collected based on, for example, a browsing history saving method, a feedback collecting method, and the like, but are not limited to such examples. This improves the user's satisfaction by suggesting information according to the user's interest. A part or all of the above-mentioned processing in the response unit may be performed using, for example, AI, or may be performed without using AI. For example, the response unit can have AI analyze the user's past browsing history and feedback to suggest information according to the user's interest.

[0084] The response unit may include a visualization unit that visually provides news summaries and related information. The visual presentation method may be based on, for example, graphs, charts, infographics, etc., but is not limited to such examples. This provides information visually, thereby deepening the user's understanding. Some or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to execute the visualization unit that visually provides news summaries and related information.

[0085] The response unit may include a historical background providing unit that provides a historical background related to the news summary. The historical background is provided based on, for example, past events, related historical facts, and the like, but is not limited to such examples. By providing the historical background, understanding of the news is deepened. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to provide the historical background related to the news summary.

[0086] The response unit may include a reliability evaluation unit that evaluates the reliability of the news source. The reliability is evaluated based on, for example, the reliability score of the information source, past reliability evaluation, etc., but is not limited to such examples. In this way, by evaluating the reliability of the news, it is possible to provide the user with reliable information. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to evaluate the reliability of the news source.

[0087] The response unit may include a filtering unit that filters information based on a user's settings. The user's settings are based on, for example, topics of interest, frequency of notifications, etc., but are not limited to such examples. By filtering information based on the user's settings, optimal information can be provided to the user. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit may cause AI to execute the filtering unit that filters information based on the user's settings.

[0088] The response unit can have a notification function for notifying the latest news. The notification function is provided, for example, based on push notification, email notification, etc., but is not limited to such examples. By notifying the latest news, the user can obtain the latest information without missing it. Some or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can cause AI to execute the notification function for notifying the latest news.

[0089] The generation unit can perform different summaries for each user attribute. The user attributes are collected based on, for example, age, sex, occupation, etc., but are not limited to such examples. This makes it possible to provide individualized information by performing summaries according to the user attributes. 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 may use a generation AI that generates different summaries based on the user attributes.

[0090] The collection unit can estimate the user's emotion and adjust the timing of news collection based on the estimated user's emotion. The user's emotion is estimated based on, for example, an emotion analysis algorithm, a method of using emotion data, and the like, but is not limited to such examples. For example, when the user is stressed, news is collected during a time period when the user can relax. In addition, when the user is excited, the latest news can be collected immediately. Furthermore, when the user is tired, news can be collected after the user rests. In this way, by adjusting the timing of news collection according to the user's emotion, news can be provided at a more appropriate timing. 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, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the timing of news collection.

[0091] The collection unit can analyze the user's past news browsing history and select the optimal collection method. The optimal collection method is selected based on, for example, the frequency of collection, the selection criteria for the collection target, etc., but is not limited to such examples. For example, news categories that the user has frequently browsed in the past are collected with priority. In addition, if the user has a tendency to browse during a specific time period, news can be collected according to that time period. Furthermore, news sources that the user has highly rated in the past can be collected with priority. In this way, the optimal collection method can be selected by analyzing the user's past news 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 have AI analyze the user's past news browsing history and select the optimal collection method.

[0092] The collection unit can perform filtering based on the user's current field of interest when collecting news. The current field of interest is identified based on, for example, a recent browsing history, a search history, etc., but is not limited to such examples. For example, news related to a topic in which the user is currently interested is preferentially collected. In addition, if the user is interested in a specific event, news related to the event can also be collected. Furthermore, if the user is interested in a specific region, news related to the region can also be collected. In this way, by filtering news based on the user's current field of interest, it is possible to provide highly relevant news. 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 cause AI to execute a process of filtering news based on the user's current field of interest.

[0093] The collection unit can estimate the user's emotion and determine the priority of news to be collected based on the estimated user's emotion. The priority of news is determined based on, for example, the importance of the news, the user's interest, etc., but is not limited to such examples. For example, when the user is relaxed, interesting news is collected with priority. Also, when the user is in a hurry, important news can be collected with priority. Furthermore, when the user is excited, entertainment news can be collected with priority. In this way, more appropriate news can be provided by determining the priority of news according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of news.

[0094] When collecting news, the collection unit can preferentially collect highly relevant news by considering the geographical location information of the user. The geographical location information is collected based on, for example, GPS data, IP address, etc., but is not limited to such examples. For example, news related to the area where the user is currently located is preferentially collected. In addition, when the user is traveling, news related to the travel destination can also be collected. Furthermore, when the user is interested in a specific area, news related to the area can also be preferentially collected. In this way, highly relevant news can be provided by considering the geographical location 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 cause AI to analyze the geographical location information of the user and preferentially collect highly relevant news.

[0095] The collection unit can analyze the user's social media activity and collect related news when collecting news. The social media activity is analyzed based on, for example, the content of the post, the number of likes, etc., but is not limited to such examples. For example, articles related to news shared by the user on social media are collected. News shared by accounts followed by the user can also be collected. Furthermore, articles related to news that the user "liked" on social media can also be collected. In this way, highly relevant news can be provided by analyzing the user's social media activity. 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 have AI analyze the user's social media activity and collect related news.

[0096] The identification unit can estimate the user's emotion and adjust the method of identifying important points based on the estimated user's emotion. The method of identifying important points is adjusted based on, for example, a keyword extraction method, an importance evaluation criterion, and the like, but is not limited to such examples. For example, when the user is relaxed, detailed points are identified. Also, when the user is in a hurry, a point that covers the main points can be identified. Furthermore, when the user is excited, a visually stimulating point can be identified. In this way, by adjusting the method of identifying important points according to the user's emotion, more appropriate information can be provided. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the method of identifying important points.

[0097] The identification unit can adjust the specific level of detail based on the importance of the news when identifying the news. The importance of the news is evaluated based on, for example, the influence of the news, the interest of readers, etc., but is not limited to such examples. For example, in the case of important news, detailed points are identified. In addition, in the case of general news, points that grasp the main points can also be identified. Furthermore, in the case of entertainment news, visually stimulating points can also be identified. As a result, important information can be provided preferentially by adjusting the specific level of detail based on the importance of the news. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can have AI evaluate the importance of the news and adjust the specific level of detail.

[0098] When identifying news, the identification unit can apply different identification algorithms depending on the news category. The news categories are classified based on, for example, politics, economy, sports, etc., but are not limited to such examples. For example, in the case of political news, a highly reliable source is preferentially identified. In addition, in the case of sports news, the game results and the performance of the players can also be identified. Furthermore, in the case of entertainment news, visually stimulating points can also be identified. In this way, by applying the identification algorithm depending on the news category, appropriate information according to the category can be provided. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can apply different identification algorithms to AI depending on the news category.

[0099] The identification unit can estimate the user's emotion and determine the priority of the points to be identified based on the estimated user's emotion. The priority of the points is determined based on, for example, importance, relevance, etc., but is not limited to such examples. For example, when the user is relaxed, interesting points are preferentially identified. Also, when the user is in a hurry, important points can be preferentially identified. Furthermore, when the user is excited, visually stimulating points can be preferentially identified. In this way, by determining the priority of the points to be identified according to the user's emotion, more appropriate information can be provided. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the identification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the identification unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of the points.

[0100] The identification unit can determine a specific priority based on the time of submission of the news when identifying the news. The time of submission of the news is evaluated based on, for example, the submission date and time, the latest information, etc., but is not limited to such examples. For example, the latest news is prioritized and identified. Also, past news can be used as a reference for identification. Furthermore, news submitted earlier can be identified with a lower priority. In this way, by determining a specific priority based on the time of submission of the news, the latest information can be provided preferentially. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can have AI evaluate the time of submission of the news and determine a specific priority.

[0101] The identification unit can adjust the specific order based on the relevance of the news when identifying the news. The relevance of the news is evaluated based on, for example, the degree of matching of the topic, related keywords, etc., but is not limited to such examples. For example, highly relevant news is preferentially identified. Also, less relevant news can be postponed. Furthermore, highly relevant news can be identified first, and then less relevant news can be identified. In this way, by adjusting the specific order based on the relevance of the news, highly relevant information can be provided preferentially. Part or all of the above-mentioned processing in the identification unit may be performed, for example, using AI, or may be performed without using AI. For example, the identification unit can have AI evaluate the relevance of the news and adjust the specific order.

[0102] 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 expression method of the summary is adjusted based on, for example, the tone of the sentence, the conciseness of the expression, etc., but is not limited to such examples. For example, when the user is relaxed, a detailed summary is generated. Also, when the user is in a hurry, a concise summary can be generated. Furthermore, when the user is excited, a visually stimulating summary can be generated. In this way, by adjusting the expression method of the summary according to the user's emotion, a more appropriate summary can be provided. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the expression method of the summary.

[0103] The generation unit can adjust the level of detail of the summary based on the importance of the news when generating the summary. The level of detail of the summary is adjusted based on, for example, the comprehensiveness of the information, detailed explanation, etc., but is not limited to such examples. For example, in the case of important news, a detailed summary can be generated. In addition, in the case of general news, a concise summary can also be generated. Furthermore, in the case of entertainment news, a visually stimulating summary can also be generated. In this way, by adjusting the level of detail of the summary based on the importance of the news, important information can be provided preferentially. 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 have the generation AI evaluate the importance of the news and adjust the level of detail of the summary.

[0104] The generating unit can apply different summarization algorithms depending on the news category when generating a summary. The summarization algorithm is applied based on, for example, abstractive summarization, extractive summarization, etc., but is not limited to such examples. For example, in the case of political news, a highly reliable source is given priority for summarization. In addition, in the case of sports news, game results and player performances can also be summarized. Furthermore, in the case of entertainment news, a visually stimulating summary can also be generated. In this way, by applying a summarization algorithm depending on the news category, an appropriate summary depending on the category can be provided. Part or all of the above-mentioned processing in the generating unit may be performed, for example, using a generating AI, or may be performed without using a generating AI. For example, the generating unit can apply different summarization algorithms to the generating AI depending on the news category.

[0105] The generation unit can estimate the user's emotion and adjust the length of the summary based on the estimated user's emotion. The length of the summary is adjusted based on, for example, the number of characters in a sentence, the number of paragraphs, etc., but is not limited to such examples. For example, when the user is in a hurry, a short summary that covers the main points is generated. Also, when the user is relaxed, a longer summary including detailed explanations can be generated. Furthermore, when the user is excited, a visually stimulating summary can be generated. In this way, a more appropriate summary can be provided by adjusting the length of the summary according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the generation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the summary.

[0106] The generation unit can determine the priority of summaries based on the submission time of news when generating summaries. The priority of summaries is determined based on, for example, the importance of news, the submission time, etc., but is not limited to such examples. For example, the latest news is given priority for summarization. Also, past news can be used as a reference for summarization. Furthermore, news submitted earlier can be summarized with a lower priority. In this way, by determining the priority of summaries based on the submission time of news, the latest information can be provided preferentially. 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 have the generation AI evaluate the submission time of news and determine the priority of summaries.

[0107] The generation unit can adjust the order of summaries based on the relevance of news when generating summaries. The order of summaries is adjusted based on, for example, the order of relevance or the order of importance, but is not limited to such examples. For example, highly relevant news is summarized with priority. Also, less relevant news can be postponed. Furthermore, highly relevant news can be summarized first, and then less relevant news can be summarized. In this way, by adjusting the order of summaries based on the relevance of news, highly relevant information can be provided with priority. 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 cause the generation AI to evaluate the relevance of news and adjust the order of summaries.

[0108] The classification unit can estimate the user's emotion and adjust the categorization criteria based on the estimated user's emotion. The categorization criteria are adjusted based on, for example, the topic classification criteria, the user's interests, etc., but are not limited to such examples. For example, when the user is relaxed, detailed categorization is performed. Also, when the user is in a hurry, concise categorization can be performed. Furthermore, when the user is excited, visually stimulating categorization can be performed. In this way, by adjusting the categorization criteria according to the user's emotion, more appropriate categorization can be provided. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the classification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the classification unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the categorization criteria.

[0109] The classification unit can improve the accuracy of categorization by considering the interrelationships of news during categorization. The interrelationships of news are evaluated based on, for example, links of related news, common keywords, etc., but are not limited to such examples. For example, related news is grouped and categorized. In addition, the interrelationships of news can be analyzed and highly related news can be classified into the same category. Furthermore, the accuracy of categorization can be improved by considering the interrelationships of news. As a result, the accuracy of categorization is improved by considering the interrelationships of news. Part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit can improve the accuracy of categorization by having AI evaluate the interrelationships of news.

[0110] The classification unit can perform categorization taking into consideration the attribute information of the news submitter at the time of categorization. The attribute information of the submitter is collected based on, for example, the submitter's occupation, field of expertise, etc., but is not limited to such examples. For example, if the submitter of the news is an expert, it is classified into a specialized category. Also, if the submitter of the news is a general user, it can be classified into a general category. Furthermore, it can be classified into an appropriate category based on the attribute information of the news submitter. In this way, by taking into consideration the attribute information of the news submitter, more appropriate categorization can be provided. Part or all of the above-mentioned processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit can have AI evaluate the attribute information of the news submitter and perform categorization.

[0111] The classification unit can estimate the user's emotion and adjust the order of displaying the categorization results based on the estimated user's emotion. The display order is adjusted based on, for example, high order of importance, high order of relevance, etc., but is not limited to such examples. For example, when the user is relaxed, detailed categorization results are displayed. Also, when the user is in a hurry, concise categorization results can be displayed. Furthermore, when the user is excited, visually stimulating categorization results can be displayed. In this way, by adjusting the order of displaying the categorization results according to the user's emotion, more appropriate information can be provided. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the classification unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the classification unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order.

[0112] The classification unit can perform categorization taking into account the geographical distribution of news at the time of categorization. The geographical distribution is evaluated, for example, based on news by region, news by country, etc., but is not limited to such examples. For example, categorization is performed based on the place of origin of the news. Categorization can also be performed based on the range of influence of the news. Furthermore, classification into an appropriate category can be performed taking into account the geographical distribution of the news. In this way, more appropriate categorization can be provided by taking into account the geographical distribution of the news. Part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit can have AI evaluate the geographical distribution of the news and perform categorization.

[0113] The classification unit can improve the accuracy of categorization by referring to related literature of the news at the time of categorization. The related literature is referenced based on, for example, academic papers, related news articles, etc., but is not limited to such examples. For example, the related literature is referenced to complement background information of the news. Also, the news category can be scrutinized based on the related literature. Furthermore, the accuracy of categorization can be improved by referring to the related literature. As a result, the accuracy of categorization is improved by referring to the related literature of the news. Part or all of the above-mentioned processing in the classification unit may be performed, for example, using AI, or may be performed without using AI. For example, the classification unit can improve the accuracy of categorization by having AI refer to the related literature of the news.

[0114] The response unit can estimate the user's emotion and adjust the method of providing information based on the estimated user's emotion. The method of providing information is adjusted based on, for example, text, image, video, etc., but is not limited to such examples. For example, when the user is relaxed, detailed information is provided. Also, when the user is in a hurry, concise information can be provided. Furthermore, when the user is excited, visually stimulating information can be provided. In this way, by adjusting the method of providing information according to the user's emotion, more appropriate information can be provided. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the response unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the method of providing information.

[0115] The response unit can provide optimal information by referring to the user's past browsing history when providing information. The optimal information is selected based on, for example, information based on the user's interest, the latest information, etc., but is not limited to such examples. For example, information related to news viewed by the user in the past can be provided. Information that is likely to be of interest to the user can also be provided based on the user's past browsing history. Furthermore, the optimal information can be provided by analyzing the user's past browsing history. As a result, optimal information can be provided by referring to the user's past browsing history. A part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can cause AI to refer to the user's past browsing history and provide optimal information.

[0116] The response unit can customize information based on the user's current field of interest when providing information. The current field of interest is identified based on, for example, a recent browsing history, a search history, etc., but is not limited to such examples. For example, information related to a topic in which the user is currently interested can be provided. In addition, if the user is interested in a specific event, information related to the event can be provided. Furthermore, if the user is interested in a specific region, information related to the region can be provided. In this way, by customizing information based on the user's current field of interest, more appropriate information can be provided. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can cause AI to execute processing to customize information based on the user's current field of interest.

[0117] The response unit can estimate the user's emotion and determine the priority of information provision based on the estimated user's emotion. The priority of information provision is determined based on, for example, importance, relevance, etc., but is not limited to such examples. For example, when the user is relaxed, interesting information is provided with priority. Also, when the user is in a hurry, important information can be provided with priority. Furthermore, when the user is excited, visually stimulating information can be provided with priority. In this way, by determining the priority of information provision according to the user's emotion, more appropriate information can be provided. 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 response unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the response unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of information provision.

[0118] The response unit can provide optimal information by considering the geographical location information of the user when providing information. The geographical location information is collected based on, for example, GPS data, IP address, etc., but is not limited to such examples. For example, information related to the area where the user is currently located is provided. In addition, if the user is traveling, information related to the travel destination can also be provided. Furthermore, if the user is interested in a specific area, information related to the area can also be provided. In this way, more appropriate information can be provided by considering the geographical location information of the user. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can have AI analyze the geographical location information of the user to provide optimal information.

[0119] The response unit can analyze the user's social media activity and suggest a means of providing information when providing information. The social media activity is analyzed based on, for example, the content of the post, the number of likes, etc., but is not limited to such examples. For example, information related to news shared by the user on social media can be provided. Information related to news shared by an account followed by the user can also be provided. Furthermore, information related to news that the user "liked" on social media can also be provided. In this way, by analyzing the user's social media activity, a more appropriate means of providing information can be suggested. Part or all of the above-mentioned processing in the response unit may be performed, for example, using AI, or may be performed without using AI. For example, the response unit can have AI analyze the user's social media activity and suggest a means of providing information.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The collection unit can preferentially collect news related to a region by taking into account the geographical location information of the user. For example, if the user is staying in a specific region, news related to the region is preferentially collected. In addition, if the user is traveling, news related to the travel destination can also be collected. Furthermore, if the user is interested in a specific region, news related to the region can also be collected. In this way, highly relevant news can be provided by taking into account the geographical location information of the user.

[0122] The identification unit can adjust the specific level of detail based on the importance of the news. For example, in the case of important news, the identification unit can identify detailed points. In addition, in the case of general news, the identification unit can identify points that highlight the main points. Furthermore, in the case of entertainment news, the identification unit can identify visually stimulating points. In this way, important information can be provided preferentially by adjusting the specific level of detail based on the importance of the news.

[0123] The generator can apply different summarization algorithms depending on the news category. For example, in the case of political news, it prioritizes and summarizes reliable sources. In addition, in the case of sports news, it can also summarize game results and player performances. Furthermore, in the case of entertainment news, it can generate visually stimulating summaries. In this way, by applying summarization algorithms depending on the news category, it is possible to provide appropriate summaries according to the category.

[0124] The classification unit can improve the accuracy of categorization by taking into account the interrelationships between news items. For example, related news items are grouped and categorized. Also, the classification unit can analyze the interrelationships between news items and classify highly related news items into the same category. Furthermore, the classification unit can improve the accuracy of categorization by taking into account the interrelationships between news items. In this way, the accuracy of categorization is improved by taking into account the interrelationships between news items.

[0125] The response unit can analyze the user's social media activity and collect related news. For example, articles related to news shared by the user on social media can be collected. News shared by accounts the user follows can also be collected. Furthermore, articles related to news that the user "liked" on social media can also be collected. This makes it possible to provide highly relevant news by analyzing the user's social media activity.

[0126] The collection unit can estimate the user's emotions and adjust the timing of news collection based on the estimated user's emotions. For example, if the user is feeling stressed, news is collected during a time period when the user can relax. Also, if the user is excited, the latest news can be collected immediately. Furthermore, if the user is tired, news can be collected after the user has rested. In this way, by adjusting the timing of news collection according to the user's emotions, news can be provided at a more appropriate timing.

[0127] The identification unit can estimate the user's emotion and adjust the method of identifying important points based on the estimated user's emotion. For example, when the user is relaxed, detailed points can be identified. When the user is in a hurry, points that focus on the main points can be identified. Furthermore, when the user is excited, visually stimulating points can be identified. In this way, by adjusting the method of identifying important points according to the user's emotion, more appropriate information can be provided.

[0128] The generation unit can estimate the user's emotion and adjust the way the summary is expressed based on the estimated user's emotion. For example, if the user is relaxed, a detailed summary can be generated. Also, if the user is in a hurry, a concise summary can be generated. Furthermore, if the user is excited, a visually stimulating summary can be generated. In this way, a more appropriate summary can be provided by adjusting the way the summary is expressed depending on the user's emotion.

[0129] The classification unit can estimate the user's emotion and adjust the categorization criteria based on the estimated user's emotion. For example, if the user is relaxed, detailed categorization can be performed. If the user is in a hurry, brief categorization can be performed. Furthermore, if the user is excited, visually stimulating categorization can be performed. In this way, by adjusting the categorization criteria according to the user's emotion, more appropriate categorization can be provided.

[0130] The response unit can estimate the user's emotion and adjust the method of providing information based on the estimated user's emotion. For example, when the user is relaxed, detailed information can be provided. When the user is in a hurry, brief information can be provided. Furthermore, when the user is excited, visually stimulating information can be provided. In this way, by adjusting the method of providing information according to the user's emotion, more appropriate information can be provided.

[0131] The process flow of the second embodiment will be briefly described below.

[0132] Step 1: The collection unit collects news data. News data includes, but is not limited to, text data, image data, video data, and the like. The collection unit can collect news data from, for example, news sites, SNS, blogs, and the like. Step 2: The identification unit analyzes the news data collected by the collection unit and identifies important points of the news. The important points are identified, for example, based on a summary of the news content, extraction of keywords, etc., but are not limited to such examples. The identification unit can analyze the news content using, for example, natural language processing technology, and identify important points. Step 3: The generator generates a news summary based on the important points identified by the identifier. The summary is generated based on, for example, the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. The generator can generate the news summary using, for example, a generation AI. The generation AI can generate the news summary using a text generation AI (e.g., LLM). Step 4: The classifier categorizes the summaries generated by the generator based on each topic. The categorization is performed based on, for example, a topic classification criterion or an algorithm to be used, but is not limited to such examples. The classifier can categorize the summaries using, for example, AI. Step 5: The response unit provides information appropriate to the user based on the summary categorized by the classification unit. The information is provided based on, for example, the user's interests and concerns, but is not limited to such an example. The response unit can provide information appropriate to the user using, for example, AI.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] For example, the collection unit can collect news data using the camera 42 and the communication I / F 44 of the smart device 14. The identification unit is realized by the identification processing unit 290 of the data processing device 12, and analyzes the collected news data and identifies important points. The generation unit is realized by the identification processing unit 290 of the data processing device 12, and generates a news summary based on the identified important points. The classification unit is realized by the identification processing unit 290 of the data processing device 12, and categorizes the generated summary based on each topic. The response unit is realized by the control unit 46A of the smart device 14, and provides information according to the user based on the categorized summary. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 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.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0140] 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.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0142] 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).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0144] 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.

[0145] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate 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.

[0147] 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.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0151] 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.

[0152] For example, the collection unit can collect news data using the camera 42 and the communication I / F 44 of the smart glasses 214. The identification unit is realized by the identification processing unit 290 of the data processing device 12, and analyzes the collected news data and identifies important points. The generation unit is realized by the identification processing unit 290 of the data processing device 12, and generates a news summary based on the identified important points. The classification unit is realized by the identification processing unit 290 of the data processing device 12, and categorizes the generated summary based on each topic. The response unit is realized by the control unit 46A of the smart glasses 214, and provides information according to the user based on the categorized summary. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 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.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0156] 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.

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

[0158] 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).

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

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] For example, the collection unit can collect news data using the camera 42 and the communication I / F 44 of the headset type terminal 314. The identification unit is realized by the identification processing unit 290 of the data processing device 12, and analyzes the collected news data and identifies important points. The generation unit is realized by the identification processing unit 290 of the data processing device 12, and generates a news summary based on the identified important points. The classification unit is realized by the identification processing unit 290 of the data processing device 12, and categorizes the generated summary based on each topic. The response unit is realized by the control unit 46A of the headset type terminal 314, and provides information according to the user based on the categorized summary. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] For example, the collection unit can collect news data using the camera 42 and the communication I / F 44 of the robot 414. The identification unit is realized by the identification processing unit 290 of the data processing device 12, and analyzes the collected news data and identifies important points. The generation unit is realized by the identification processing unit 290 of the data processing device 12, and generates a news summary based on the identified important points. The classification unit is realized by the identification processing unit 290 of the data processing device 12, and categorizes the generated summary based on each topic. The response unit is realized by the control unit 46A of the robot 414, and provides information according to the user based on the categorized summary. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0186] 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.

[0187] 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.

[0188] These emotions are distributed in the three 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.

[0189] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] (Appendix 1) a collection department for collecting news data; an identification unit that analyzes the news data collected by the collection unit and identifies important points of the news; a generating unit that generates a summary of the news based on the important points identified by the identifying unit; a classification unit that categorizes the summaries generated by the generation unit based on each topic; A response unit that provides information according to a user based on the summary categorized by the classification unit. A system characterized by: (Appendix 2) The collecting unit includes: Collect news data from multiple different sources 2. The system of claim 1, (Appendix 3) The classification unit includes: Equipped with a judgment unit that judges trends and changes 2. The system of claim 1, (Appendix 4) The determination unit is A providing unit that provides the determination result is provided. 4. The system of claim 3. (Appendix 5) The response unit: Suggest information based on your interests based on your past browsing history and feedback 2. The system of claim 1, (Appendix 6) The response unit: It has a visualization section that visually presents news summaries and related information. 2. The system of claim 1, (Appendix 7) The response unit: A historical context section provides historical background related to news summaries. 2. The system of claim 1, (Appendix 8) The response unit: Equipped with a reliability evaluation unit that evaluates the reliability of news sources 2. The system of claim 1, (Appendix 9) The response unit: A filtering unit is provided to filter information based on user settings. 2. The system of claim 1, (Appendix 10) The response unit: Equipped with a notification function that notifies you of the latest news 2. The system of claim 1, (Appendix 11) The generation unit is Perform different summaries for each user attribute 2. The system of claim 1, (Appendix 12) The collecting unit includes: Estimate user emotions and adjust news gathering timing based on the estimated user emotions 2. The system of claim 1, (Appendix 13) The collecting unit includes: Analyze the user's past news browsing history and select the optimal collection method 2. The system of claim 1, (Appendix 14) The collecting unit includes: When gathering news, filter it based on the user's current areas of interest 2. The system of claim 1, (Appendix 15) The collecting unit includes: Estimate user sentiment and prioritize news items based on the estimated user sentiment 2. The system of claim 1, (Appendix 16) The collecting unit includes: When collecting news, the system prioritizes collecting relevant news by taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 17) The collecting unit includes: When collecting news, analyze users' social media activity and collect related news. 2. The system of claim 1, (Appendix 18) The identification unit is Infer user sentiment and adjust how key points are identified based on the inferred user sentiment 2. The system of claim 1, (Appendix 19) The identification unit is When identifying news, adjust the level of specific detail based on the importance of the news 2. The system of claim 1, (Appendix 20) The identification unit is When identifying news, different identification algorithms are applied depending on the news category. 2. The system of claim 1, (Appendix 21) The identification unit is A user's emotion is estimated, and a priority order of points to be identified is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 22) The identification unit is When identifying news, determine specific priorities based on when the news was submitted 2. The system of claim 1, (Appendix 23) The identification unit is During news identification, adjust the specific order based on the relevance of the news 2. The system of claim 1, (Appendix 24) 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 25) The generation unit is When generating summaries, adjust the level of detail in the summary based on the importance of the news. 2. The system of claim 1, (Appendix 26) The generation unit is When generating summaries, different summarization algorithms are applied depending on the news category. 2. The system of claim 1, (Appendix 27) The generation unit is Estimating user sentiment and adjusting the length of a summary based on the estimated user sentiment 2. The system of claim 1, (Appendix 28) The generation unit is During summary generation, prioritize summaries based on when news was submitted 2. The system of claim 1, (Appendix 29) The generation unit is Adjust the order of summaries based on news relevance during summary generation 2. The system of claim 1, (Appendix 30) The classification unit includes: Infer user sentiment and adjust categorization criteria based on the inferred user sentiment 2. The system of claim 1, (Appendix 31) The classification unit includes: When categorizing news, the accuracy of categorization is improved by taking into account the interrelationships between news. 2. The system of claim 1, (Appendix 32) The classification unit includes: When categorizing news, the attribute information of the news submitter is taken into consideration. 2. The system of claim 1, (Appendix 33) The classification unit includes: Infer user sentiment and adjust the order in which categorization results are displayed based on the estimated user sentiment 2. The system of claim 1, (Appendix 34) The classification unit includes: When categorizing news, the geographical distribution of the news is taken into account. 2. The system of claim 1, (Appendix 35) The classification unit includes: When categorizing news, refer to related literature to improve categorization accuracy. 2. The system of claim 1, (Appendix 36) The response unit: Estimate the user's emotions and adjust the way information is provided based on the estimated user's emotions. 2. The system of claim 1, (Appendix 37) The response unit: When providing information, the most appropriate information is provided by referring to the user's past browsing history. 2. The system of claim 1, (Appendix 38) The response unit: Customize information based on your current interests when you provide it to us 2. The system of claim 1, (Appendix 39) The response unit: Estimate the user's emotions and determine the priority of information provision based on the estimated user's emotions. 2. The system of claim 1, (Appendix 40) The response unit: When providing information, provide optimal information by taking into account the user's geographic location information 2. The system of claim 1, (Appendix 41) The response unit: When providing information, the system analyzes the user's social media activity to suggest ways to provide the information. 2. The system of claim 1, [Explanation of symbols]

[0205] 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 data; an identification unit that analyzes the news data collected by the collection unit and identifies important points of the news; a generating unit that generates a summary of the news based on the important points identified by the identifying unit; a classification unit that categorizes the summaries generated by the generation unit based on each topic; A response unit that provides information according to a user based on the summary categorized by the classification unit. A system characterized by:

2. The collecting unit includes: Collecting data for said news from multiple different sources 2. The system of claim 1 .

3. The classification unit includes: Equipped with a judgment unit that judges trends and changes 2. The system of claim 1 .

4. The determination unit is A providing unit that provides the determination result is provided.

4. The system of claim 3.

5. The response unit: Suggest information based on your interests based on your past browsing history and feedback 2. The system of claim 1 .

6. The response unit: A visualization unit is provided to visually present a summary of the news and related information.

2. The system of claim 1 .

7. The response unit: A historical background providing unit provides historical background related to the news summary.

2. The system of claim 1 .

8. The response unit: A reliability evaluation unit that evaluates the reliability of the news source is provided.

2. The system of claim 1 .

9. The response unit: A filtering unit is provided to filter information based on user settings.

2. The system of claim 1 .

10. The response unit: Equipped with a notification function that notifies you of the latest news 2. The system of claim 1 .

Images