system

Abstract

The system according to this embodiment aims to personalize news based on the user's interests and preferences and to provide interactive information. [Solution] The system according to the embodiment comprises a personalization unit, a generation unit, and a response unit. The personalization unit personalizes news based on the user's interests and concerns. The generation unit generates a virtual news caster based on the news selected by the personalization unit. The response unit has the virtual news caster generated by the generation unit respond to the user's questions.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that news personalization is not sufficiently performed and it is difficult to provide information according to the user's interests.

[0005] The system according to the embodiment aims to personalize news based on the user's interests and provide interactive information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a personalization unit, a generation unit, and a response unit. The personalization unit personalizes news based on the user's interests and preferences. The generation unit generates a virtual news caster based on the news selected by the personalization unit. The response unit has the virtual news caster generated by the generation unit respond to the user's questions. [Effects of the Invention]

[0007] The system according to this embodiment can personalize news based on the user's interests and preferences and provide interactive information. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The news delivery system according to an embodiment of the present invention is a system for providing personalized news to users. This news delivery system personalizes news based on the user's interests and concerns. The AI ​​analyzes the user's past browsing history and interests to select the most relevant news. Next, based on the selected news, the AI ​​generates a virtual news caster. This virtual caster can deliver the news in a natural conversational format. Furthermore, when a user asks the virtual caster a question, the AI ​​analyzes the question and generates an appropriate answer. For example, if a user asks, "Tell me more about this news," the AI ​​searches for relevant information, and the virtual caster conveys that information. It is also possible to adjust the content and delivery method of the news in real time based on user feedback. This system allows users to have an experience as if they were conversing with a real news caster. For example, if a user asks, "What's the weather like today?", the virtual caster provides weather information in real time. Also, if a user says, "I want to know more about this news," the virtual caster provides detailed information. This mechanism allows users to have a visually easy-to-understand and interactive news experience. In particular, it is useful as an efficient way to consume news for young people interested in technology, users who prefer visual content, and busy business people. Furthermore, by utilizing 5G networks and cloud computing technology, it achieves high-speed and high-quality streaming and data analysis. This allows users to comfortably view the news. This system utilizes generative AI technologies such as news content generation, dialogue systems using natural language processing, and real-time video generation. This enables the delivery of personalized news to users and realizes an interactive experience.

[0029] The news delivery system according to this embodiment comprises a personalization unit, a generation unit, and a response unit. The personalization unit personalizes news based on the user's interests and preferences. For example, the personalization unit analyzes the user's past browsing history and selects news that is likely to be of interest to the user. The personalization unit can also identify the user's interests based on survey results and social media activity. For example, the personalization unit analyzes the categories of news articles the user has previously viewed and prioritizes providing news from similar categories. The personalization unit can also analyze articles and comments shared by the user on social media and identify topics of interest. The generation unit generates a virtual news caster based on the news selected by the personalization unit. For example, the generation unit generates the appearance of the virtual caster using 3D modeling technology. The generation unit can also generate the voice of the virtual caster using speech synthesis technology. For example, the generation unit can customize the appearance and voice of the virtual caster according to the user's preferences. The generation unit can also generate the movements and facial expressions of the virtual caster using generation AI in order to deliver the news in a natural conversational format. The response unit uses a virtual newscaster generated by the generation unit to respond to user questions. For example, when a user asks the virtual caster a question, the response unit analyzes the question and generates an appropriate answer. The response unit can understand the user's question using natural language processing technology and search for relevant information. For example, if a user asks, "Tell me more about this news," the response unit searches for relevant information, and the virtual caster conveys that information. The response unit can also adjust the content and delivery method of the news in real time based on user feedback. As a result, the news delivery system according to this embodiment can provide personalized news based on the user's interests and preferences, enabling an interactive experience.

[0030] The personalization unit personalizes news based on user interests and preferences. Specifically, it analyzes users' past browsing history and selects news that is likely to be of interest to them. For example, it analyzes the categories of news articles users have previously viewed and prioritizes providing news from similar categories. The personalization unit can also identify user interests based on survey results and social media activity. For example, it analyzes articles and comments users have shared on social media to identify topics of interest. Furthermore, the personalization unit can analyze users' search history and click patterns to gain a detailed understanding of what kind of news users are interested in. This makes it possible to provide the most relevant news to users. The personalization unit uses machine learning algorithms to predict user interests and select news. For example, it combines collaborative filtering and content-based filtering to model user preferences with high accuracy. This allows it to prioritize providing news similar to news that users have shown interest in in the past. The personalization unit also collects user feedback and continuously improves its news selection algorithms. For example, if a user rates a news article as "interesting," the algorithm is adjusted based on that rating to provide more similar news. This allows the personalization section to provide news optimized to the user's interests, thereby improving user satisfaction.

[0031] The generation unit generates a virtual news anchor based on news selected by the personalization unit. Specifically, the generation unit uses 3D modeling technology to generate the appearance of the virtual anchor. For example, the user can customize the virtual anchor's gender, age, clothing, etc., according to their preferences. The generation unit also uses speech synthesis technology to generate the virtual anchor's voice. For example, the user can select their preferred voice tone and accent. Furthermore, the generation unit uses generation AI to generate the virtual anchor's movements and facial expressions in order to deliver the news in a natural conversational format. For example, by having the virtual anchor make appropriate facial expressions and gestures when reading the news, a more realistic experience is provided. The generation AI can automatically adjust the virtual anchor's facial expressions and movements according to the content of the news. For example, when delivering sad news, the virtual anchor can be set to have a sad expression. The generation unit can also change the background and scene of the virtual anchor according to the content of the news. For example, when delivering sports news, a sports stadium background can be used. In this way, the generation unit can provide users with a visually and aurally engaging news experience. Furthermore, the generation unit can continuously improve the appearance, voice, and movements of the virtual anchor based on user feedback. This allows the generation unit to provide the user with the most suitable virtual newscaster, improving the news viewing experience.

[0032] The response unit uses a virtual newscaster generated by the generation unit to answer user questions. Specifically, when a user asks a question to the virtual caster, the unit analyzes the question and generates an appropriate answer. The response unit can understand user questions using natural language processing technology and search for relevant information. For example, if a user asks, "Tell me more about this news," the response unit searches for relevant information, and the virtual caster conveys that information. The response unit can also adjust the content and presentation of the news in real time based on user feedback. For example, if a user requests, "I want to know more," the response unit provides additional information. Furthermore, the response unit can use generative AI to generate appropriate answers to user questions. The generative AI generates answers in a natural conversational format, and the virtual caster conveys those answers. For example, if a user asks, "Tell me the background of this news," the generative AI generates relevant background information, and the virtual caster conveys that information. The response unit can also utilize cloud-based databases to respond to user questions quickly and accurately. This allows the response unit to provide answers based on the latest information. Furthermore, the response unit can analyze the user's question history to understand what questions the user has asked in the past. This allows the response unit to provide more relevant answers based on the user's interests. As a result, the response unit can provide users with an interactive and personalized news experience, improving user satisfaction.

[0033] The adjustment unit can adjust the content and delivery method of news based on user feedback. For example, the adjustment unit can collect user feedback and modify the news content based on that feedback. The adjustment unit can collect user feedback using surveys, click data, comments, etc. For example, the adjustment unit can analyze comments made by users on news articles and adjust the news content based on those comments. The adjustment unit can also analyze the number of times and the time spent clicking on news articles to identify user interests. This allows the adjustment unit to adjust the content and delivery method of news in real time based on user feedback. Some or all of the above processing in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input user feedback data into a generating AI and have the generating AI perform adjustments to the news content and delivery method based on the feedback.

[0034] The generation unit can generate news content. For example, the generation unit can collect the latest information from news sources and generate news articles based on that information. The generation unit can automatically generate news articles using a generation AI. For example, the generation unit inputs information collected from news sources into the generation AI, and the generation AI generates news articles based on that information. The generation unit can also use an algorithm to evaluate the quality of news articles when generating news content. For example, the generation unit evaluates the content of the generated news articles and makes corrections as necessary. In this way, the generation unit can generate news articles that provide users with the latest information. Some or all of the above processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit inputs information collected from news sources into the generation AI, and the generation AI generates news articles based on that information.

[0035] The processing unit can perform natural language processing. For example, the processing unit can analyze user questions and feedback and generate appropriate responses. The processing unit can perform natural language processing using generative AI. For example, the processing unit inputs a user question into the generative AI, which analyzes the question and generates an appropriate response. Furthermore, the processing unit can use techniques such as morphological analysis, grammatical analysis, and semantic analysis in natural language processing. For example, the processing unit performs morphological analysis, grammatical analysis, and semantic analysis on a user's question to generate an appropriate response. This allows the processing unit to interact with the user naturally. Some or all of the above-described processing in the processing unit may be performed using generative AI or not. For example, the processing unit inputs a user question into the generative AI, which analyzes the question and generates an appropriate response.

[0036] The generation unit can generate videos in real time. For example, the generation unit can generate videos in real time based on news articles. The generation unit can generate videos in real time using a generation AI. For example, the generation unit inputs the content of a news article into the generation AI, and the generation AI generates a video in real time based on that content. The generation unit can also generate high-quality videos using streaming and encoding technologies. For example, the generation unit delivers the generated video to the user using streaming technology. This allows the generation unit to generate real-time videos to provide information to the user immediately. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the generation unit inputs the content of a news article into the generation AI, and the generation AI generates a video in real time based on that content.

[0037] The personalization unit can analyze a user's past news browsing history and improve the algorithm for selecting the most relevant news. For example, the personalization unit can prioritize displaying news categories that the user has frequently viewed in the past. The personalization unit can also suggest similar news articles based on news articles that the user has previously rated highly. The personalization unit can also predict and provide news that is preferred at specific times of day based on the user's browsing history. In this way, the personalization unit can provide more relevant news by analyzing the user's past news browsing history. Some or all of the above processes in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's news browsing history data into a generating AI and have the generating AI improve the algorithm for selecting the most relevant news.

[0038] The personalization unit can reflect the user's current interests and trends in real time when personalizing news. For example, the personalization unit can provide relevant news based on keywords the user has recently searched for. The personalization unit can also analyze the user's activity on social media and reflect topics of interest. The personalization unit can also provide the most relevant news to the user based on real-time trend information. In this way, the personalization unit can provide more relevant news by reflecting the user's current interests and trends in real time. Some or all of the above processes in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's search keyword data into a generating AI and have the generating AI select news that reflects the user's interests and trends in real time.

[0039] The personalization unit can prioritize providing highly relevant news by considering the user's geographical location when personalizing news. For example, the personalization unit can prioritize displaying local news related to the user's current location. If the user is traveling, the personalization unit can also prioritize providing news from their travel destination. The personalization unit can also prioritize providing weather and traffic information based on the user's geographical location. In this way, the personalization unit can provide more relevant news by considering the user's geographical location. Some or all of the above processing in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's geographical location data into a generating AI and have the generating AI select news based on geographical location information.

[0040] The personalization unit can analyze a user's social media activity and provide relevant news when personalizing news. For example, the personalization unit can provide relevant news based on articles the user has shared on social media. The personalization unit can also analyze the content of posts from accounts the user follows and provide news of interest. The personalization unit can also provide relevant news based on the user's comments and reactions on social media. In this way, the personalization unit can provide more relevant news by analyzing the user's social media activity. Some or all of the above processing in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's social media activity data into a generating AI and have the generating AI select news based on social media activity.

[0041] The generation unit can adjust the level of detail in the anchor's expression based on the importance of the news when generating a virtual news anchor. For example, in the case of important news, the generation unit provides detailed explanations and background information. In the case of minor news, the generation unit may limit the explanation to a concise one. In the case of breaking news, the generation unit can convey information quickly and concisely. In this way, the generation unit can adjust the level of detail in the anchor's expression based on the importance of the news. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input news importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the anchor's expression based on importance.

[0042] The generation unit can apply different generation algorithms depending on the news category when generating virtual newscasters. For example, in the case of sports news, the generation unit may use dynamic presentation. In the case of economic news, the generation unit may also make extensive use of graphs and data. In the case of entertainment news, the generation unit may also use visually appealing presentation. This allows the generation unit to apply different generation algorithms depending on the news category. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input news category data into a generation AI and have the generation AI execute the application of a generation algorithm appropriate to the category.

[0043] The generation unit can select the optimal display method when generating a virtual newscaster, taking into account the user's device information. For example, if the user is using a smartphone, the generation unit provides a display method that matches the screen size. If the user is using a tablet, the generation unit can also provide a display method optimized for a larger screen. If the user is using a smartwatch, the generation unit can also provide a concise and highly visible display method. In this way, the generation unit can provide a more appropriate display method by taking into account the user's device information. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the user's device information into the generation AI and have the generation AI select the optimal display method based on the device information.

[0044] The generation unit can improve the presentation of a virtual news anchor by reflecting past user feedback when generating the anchor. For example, the generation unit can reuse presentation styles that have been well-received by users in the past. The generation unit can also adjust the anchor's tone and speaking style based on user feedback. The generation unit can also analyze past user feedback and suggest the most suitable presentation method. In this way, the generation unit can provide more appropriate news by reflecting past user feedback. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input user feedback data into a generation AI and have the generation AI perform improvements to the anchor's presentation based on the feedback.

[0045] The response unit can generate the optimal response by referring to the user's past question history when generating a response. For example, the response unit can provide relevant information based on the content of questions the user has asked in the past. The response unit can also create templates for frequently asked questions from the user's past question history. The response unit can also analyze the user's past question history and suggest the optimal response method. In this way, the response unit can provide a more appropriate response by referring to the user's past question history. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input the user's question history data into a generation AI and have the generation AI perform the generation of the optimal response based on the question history.

[0046] The response unit can apply different response algorithms depending on the category of the question when generating a response. For example, the response unit can provide detailed technical information for technology-related questions. For entertainment-related questions, it can also provide visually appealing information. For economic questions, it can provide information that makes extensive use of data and graphs. In this way, the response unit can provide a more appropriate response by applying different response algorithms depending on the category of the question. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input question category data into a generating AI and have the generating AI execute the application of a response algorithm appropriate to the category.

[0047] The response unit can provide highly relevant information by considering the user's geographical location when generating a response. For example, the response unit can provide local information related to the user's current location. If the user is traveling, the response unit can also provide information about their travel destination. The response unit can also provide weather and traffic information based on the user's geographical location. In this way, the response unit can provide more relevant information by considering the user's geographical location. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input the user's geographical location data into a generating AI and have the generating AI perform the task of providing information based on geographical location information.

[0048] The response unit can analyze the user's social media activity and provide relevant information when generating a response. For example, the response unit can provide relevant information based on articles the user has shared on social media. The response unit can also analyze the content of posts from accounts the user follows and provide information of interest. The response unit can also provide relevant information based on the user's comments and reactions on social media. In this way, the response unit can provide more relevant information by analyzing the user's social media activity. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input the user's social media activity data into a generating AI and have the generating AI perform the task of providing information based on social media activity.

[0049] The adjustment unit can select the optimal adjustment method by referring to past user feedback during the adjustment process. For example, the adjustment unit may reuse news formats that have been well-received by users in the past. The adjustment unit can also adjust the tone and content of the news based on user feedback. The adjustment unit can also analyze past user feedback and propose the optimal adjustment method. This allows the adjustment unit to make more appropriate adjustments by referring to past user feedback. Some or all of the above processes in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input user feedback data into a generating AI and have the generating AI select an adjustment method based on the feedback.

[0050] The adjustment unit can select the optimal adjustment method by considering the user's device information during the adjustment process. For example, if the user is using a smartphone, the adjustment unit will adjust to the screen size. If the user is using a tablet, the adjustment unit can also perform adjustments optimized for a larger screen. If the user is using a smartwatch, the adjustment unit can also perform adjustments that are simple and easy to read. In this way, the adjustment unit can perform more appropriate adjustments by considering the user's device information. Some or all of the above-described processes in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input the user's device information into a generating AI and have the generating AI select the optimal adjustment method based on the device information.

[0051] The processing unit can select the optimal processing method by referring to the user's past dialogue history during natural language processing. For example, the processing unit performs optimal natural language processing based on the language used by the user in the past. The processing unit can also create templates for frequently asked questions from the user's past dialogue history. The processing unit can also analyze the user's past dialogue history and propose the optimal processing method. This allows the processing unit to perform more appropriate natural language processing by referring to the user's past dialogue history. Some or all of the above processing in the processing unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the processing unit can input the user's dialogue history data into a generative AI and have the generative AI select the optimal processing method based on the dialogue history.

[0052] The processing unit can select the optimal processing method when performing natural language processing, taking into account the user's geographical location information. For example, the processing unit can perform natural language processing based on local information related to the user's current location. If the user is traveling, the processing unit can also perform natural language processing based on information about the travel destination. The processing unit can also perform natural language processing based on weather and traffic information, taking into account the user's geographical location. This allows the processing unit to perform more appropriate natural language processing by taking into account the user's geographical location information. Some or all of the processing described above in the processing unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the processing unit can input the user's geographical location data into a generative AI and have the generative AI select the optimal processing method based on the geographical location information.

[0053] The processing unit can select the optimal processing method while considering the user's health condition during natural language processing. For example, if the user is tired, the processing unit will perform concise and easy-to-understand natural language processing. If the user is healthy, the processing unit can also perform natural language processing that provides detailed information. If the user is unwell, the processing unit can also perform natural language processing in a gentle tone. In this way, the processing unit can perform more appropriate natural language processing by considering the user's health condition. Some or all of the processing described above in the processing unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the processing unit can input the user's health condition data into a generative AI and have the generative AI select the optimal processing method based on the health condition.

[0054] The processing unit can analyze a user's social media activity and provide relevant information during natural language processing. For example, the processing unit can provide relevant information based on articles shared by the user on social media. The processing unit can also analyze the content of posts from accounts followed by the user and provide information of interest. The processing unit can also provide relevant information based on the user's comments and reactions on social media. In this way, the processing unit can provide more relevant information by analyzing the user's social media activity. Some or all of the above processing in the processing unit may be performed using generative AI, or it may be performed without using generative AI. For example, the processing unit can input the user's social media activity data into a generative AI and have the generative AI perform the task of providing information based on social media activity.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The news delivery system can further prioritize local news and region-related information by taking into account the user's geographical location. For example, if a user is in a specific city, it can provide news and event information related to that city. If a user is traveling, it can also provide tourist information and local news from their destination. Furthermore, it can provide real-time weather forecasts and traffic information based on the user's current location. This allows the news delivery system to provide more relevant news based on the user's geographical location. Geographic location information can be obtained using GPS or Wi-Fi location data. For example, the system can obtain the user's smartphone location data and adjust the news content based on that data.

[0057] The news delivery system can further analyze users' social media activity and personalize news content based on that activity. For example, it can analyze articles and comments shared by users on social media to identify topics of interest. It can also provide relevant news based on the content of accounts that users follow. Furthermore, it can analyze users' reactions and engagement on social media to select news that is likely to be of interest. As a result, the news delivery system can provide more personalized news based on users' social media activity. Social media activity analysis can be performed by obtaining data via APIs and using natural language processing technology. For example, it can analyze users' tweets and posts and adjust news content based on their content.

[0058] The news delivery system can further consider the user's device information to provide the optimal news display method. For example, if the user is using a smartphone, the news can be displayed in a layout that matches the screen size. If the user is using a tablet, a display method optimized for larger screens can be provided. Furthermore, if the user is using a smartwatch, a concise and highly visible display method can be provided. In this way, the news delivery system can provide a more appropriate news display method based on the user's device information. Device information can be obtained by detecting the type of device, screen size, resolution, etc. For example, the news display method can be adjusted based on the user's device information obtained.

[0059] The news delivery system can further improve the content and delivery method of news by referring to past user feedback. For example, it can reuse news formats that users have previously given high ratings to. It can also adjust the tone and content of news based on user feedback. Furthermore, it can analyze past user feedback and suggest the optimal news delivery method. In this way, the news delivery system can provide more relevant news by referring to past user feedback. Feedback can be collected using surveys, click data, comments, etc. For example, comments made by users on news articles can be analyzed, and the content of the news can be adjusted based on those comments.

[0060] The news delivery system can further analyze a user's past news browsing history and personalize the news content based on that history. For example, it can prioritize displaying news categories that the user has frequently viewed in the past. It can also suggest similar news articles based on news articles that the user has previously rated highly. Furthermore, it can predict and provide news that users will prefer at specific times of day based on their browsing history. In this way, the news delivery system can provide more relevant news by analyzing a user's past news browsing history. The analysis of news browsing history can be done based on user click data and browsing time. For example, it can analyze the categories of news articles that a user has viewed in the past and adjust the news content based on that data.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The personalization section personalizes news based on the user's interests and preferences. For example, it analyzes the user's past browsing history and selects news that is likely to interest the user. It can also identify user interests based on survey results and social media activity. Specifically, it analyzes the categories of news articles the user has viewed in the past and prioritizes providing news from similar categories. It can also analyze articles and comments the user has shared on social media to identify topics of interest. Step 2: The generation unit generates a virtual news anchor based on the news selected by the personalization unit. For example, it can generate the appearance of the virtual anchor using 3D modeling technology and generate the voice of the virtual anchor using speech synthesis technology. Furthermore, the appearance and voice of the virtual anchor can be customized according to the user's preferences. In addition, to deliver the news in a natural conversational format, it can also generate the movements and facial expressions of the virtual anchor using generation AI. Step 3: The response unit uses a virtual newscaster generated by the generation unit to respond to user questions. For example, when a user asks the virtual caster a question, the response unit analyzes the question and generates an appropriate answer. The response unit can understand the user's question using natural language processing technology and search for relevant information. Specifically, if a user asks, "Tell me more about this news," the response unit searches for relevant information, and the virtual caster conveys that information. It can also adjust the content and presentation of the news in real time based on user feedback.

[0063] (Example of form 2) The news delivery system according to an embodiment of the present invention is a system for providing personalized news to users. This news delivery system personalizes news based on the user's interests and concerns. The AI ​​analyzes the user's past browsing history and interests to select the most relevant news. Next, based on the selected news, the AI ​​generates a virtual news caster. This virtual caster can deliver the news in a natural conversational format. Furthermore, when a user asks the virtual caster a question, the AI ​​analyzes the question and generates an appropriate answer. For example, if a user asks, "Tell me more about this news," the AI ​​searches for relevant information, and the virtual caster conveys that information. It is also possible to adjust the content and delivery method of the news in real time based on user feedback. This system allows users to have an experience as if they were conversing with a real news caster. For example, if a user asks, "What's the weather like today?", the virtual caster provides weather information in real time. Also, if a user says, "I want to know more about this news," the virtual caster provides detailed information. This mechanism allows users to have a visually easy-to-understand and interactive news experience. In particular, it is useful as an efficient way to consume news for young people interested in technology, users who prefer visual content, and busy business people. Furthermore, by utilizing 5G networks and cloud computing technology, it achieves high-speed and high-quality streaming and data analysis. This allows users to comfortably view the news. This system utilizes generative AI technologies such as news content generation, dialogue systems using natural language processing, and real-time video generation. This enables the delivery of personalized news to users and realizes an interactive experience.

[0064] The news delivery system according to this embodiment comprises a personalization unit, a generation unit, and a response unit. The personalization unit personalizes news based on the user's interests and preferences. For example, the personalization unit analyzes the user's past browsing history and selects news that is likely to be of interest to the user. The personalization unit can also identify the user's interests based on survey results and social media activity. For example, the personalization unit analyzes the categories of news articles the user has previously viewed and prioritizes providing news from similar categories. The personalization unit can also analyze articles and comments shared by the user on social media and identify topics of interest. The generation unit generates a virtual news caster based on the news selected by the personalization unit. For example, the generation unit generates the appearance of the virtual caster using 3D modeling technology. The generation unit can also generate the voice of the virtual caster using speech synthesis technology. For example, the generation unit can customize the appearance and voice of the virtual caster according to the user's preferences. The generation unit can also generate the movements and facial expressions of the virtual caster using generation AI in order to deliver the news in a natural conversational format. The response unit uses a virtual newscaster generated by the generation unit to respond to user questions. For example, when a user asks the virtual caster a question, the response unit analyzes the question and generates an appropriate answer. The response unit can understand the user's question using natural language processing technology and search for relevant information. For example, if a user asks, "Tell me more about this news," the response unit searches for relevant information, and the virtual caster conveys that information. The response unit can also adjust the content and delivery method of the news in real time based on user feedback. As a result, the news delivery system according to this embodiment can provide personalized news based on the user's interests and preferences, enabling an interactive experience.

[0065] The personalization unit personalizes news based on user interests and preferences. Specifically, it analyzes users' past browsing history and selects news that is likely to be of interest to them. For example, it analyzes the categories of news articles users have previously viewed and prioritizes providing news from similar categories. The personalization unit can also identify user interests based on survey results and social media activity. For example, it analyzes articles and comments users have shared on social media to identify topics of interest. Furthermore, the personalization unit can analyze users' search history and click patterns to gain a detailed understanding of what kind of news users are interested in. This makes it possible to provide the most relevant news to users. The personalization unit uses machine learning algorithms to predict user interests and select news. For example, it combines collaborative filtering and content-based filtering to model user preferences with high accuracy. This allows it to prioritize providing news similar to news that users have shown interest in in the past. The personalization unit also collects user feedback and continuously improves its news selection algorithms. For example, if a user rates a news article as "interesting," the algorithm is adjusted based on that rating to provide more similar news. This allows the personalization section to provide news optimized to the user's interests, thereby improving user satisfaction.

[0066] The generation unit generates a virtual news anchor based on news selected by the personalization unit. Specifically, the generation unit uses 3D modeling technology to generate the appearance of the virtual anchor. For example, the user can customize the virtual anchor's gender, age, clothing, etc., according to their preferences. The generation unit also uses speech synthesis technology to generate the virtual anchor's voice. For example, the user can select their preferred voice tone and accent. Furthermore, the generation unit uses generation AI to generate the virtual anchor's movements and facial expressions in order to deliver the news in a natural conversational format. For example, by having the virtual anchor make appropriate facial expressions and gestures when reading the news, a more realistic experience is provided. The generation AI can automatically adjust the virtual anchor's facial expressions and movements according to the content of the news. For example, when delivering sad news, the virtual anchor can be set to have a sad expression. The generation unit can also change the background and scene of the virtual anchor according to the content of the news. For example, when delivering sports news, a sports stadium background can be used. In this way, the generation unit can provide users with a visually and aurally engaging news experience. Furthermore, the generation unit can continuously improve the appearance, voice, and movements of the virtual anchor based on user feedback. This allows the generation unit to provide the user with the most suitable virtual newscaster, improving the news viewing experience.

[0067] The response unit uses a virtual newscaster generated by the generation unit to answer user questions. Specifically, when a user asks a question to the virtual caster, the unit analyzes the question and generates an appropriate answer. The response unit can understand user questions using natural language processing technology and search for relevant information. For example, if a user asks, "Tell me more about this news," the response unit searches for relevant information, and the virtual caster conveys that information. The response unit can also adjust the content and presentation of the news in real time based on user feedback. For example, if a user requests, "I want to know more," the response unit provides additional information. Furthermore, the response unit can use generative AI to generate appropriate answers to user questions. The generative AI generates answers in a natural conversational format, and the virtual caster conveys those answers. For example, if a user asks, "Tell me the background of this news," the generative AI generates relevant background information, and the virtual caster conveys that information. The response unit can also utilize cloud-based databases to respond to user questions quickly and accurately. This allows the response unit to provide answers based on the latest information. Furthermore, the response unit can analyze the user's question history to understand what questions the user has asked in the past. This allows the response unit to provide more relevant answers based on the user's interests. As a result, the response unit can provide users with an interactive and personalized news experience, improving user satisfaction.

[0068] The adjustment unit can adjust the content and delivery method of news based on user feedback. For example, the adjustment unit can collect user feedback and modify the news content based on that feedback. The adjustment unit can collect user feedback using surveys, click data, comments, etc. For example, the adjustment unit can analyze comments made by users on news articles and adjust the news content based on those comments. The adjustment unit can also analyze the number of times and the time spent clicking on news articles to identify user interests. This allows the adjustment unit to adjust the content and delivery method of news in real time based on user feedback. Some or all of the above processing in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input user feedback data into a generating AI and have the generating AI perform adjustments to the news content and delivery method based on the feedback.

[0069] The generation unit can generate news content. For example, the generation unit can collect the latest information from news sources and generate news articles based on that information. The generation unit can automatically generate news articles using a generation AI. For example, the generation unit inputs information collected from news sources into the generation AI, and the generation AI generates news articles based on that information. The generation unit can also use an algorithm to evaluate the quality of news articles when generating news content. For example, the generation unit evaluates the content of the generated news articles and makes corrections as necessary. In this way, the generation unit can generate news articles that provide users with the latest information. Some or all of the above processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit inputs information collected from news sources into the generation AI, and the generation AI generates news articles based on that information.

[0070] The processing unit can perform natural language processing. For example, the processing unit can analyze user questions and feedback and generate appropriate responses. The processing unit can perform natural language processing using generative AI. For example, the processing unit inputs a user question into the generative AI, which analyzes the question and generates an appropriate response. Furthermore, the processing unit can use techniques such as morphological analysis, grammatical analysis, and semantic analysis in natural language processing. For example, the processing unit performs morphological analysis, grammatical analysis, and semantic analysis on a user's question to generate an appropriate response. This allows the processing unit to interact with the user naturally. Some or all of the above-described processing in the processing unit may be performed using generative AI or not. For example, the processing unit inputs a user question into the generative AI, which analyzes the question and generates an appropriate response.

[0071] The generation unit can generate videos in real time. For example, the generation unit can generate videos in real time based on news articles. The generation unit can generate videos in real time using a generation AI. For example, the generation unit inputs the content of a news article into the generation AI, and the generation AI generates a video in real time based on that content. The generation unit can also generate high-quality videos using streaming and encoding technologies. For example, the generation unit delivers the generated video to the user using streaming technology. This allows the generation unit to generate real-time videos to provide information to the user immediately. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the generation unit inputs the content of a news article into the generation AI, and the generation AI generates a video in real time based on that content.

[0072] The personalization unit can estimate the user's emotions and adjust the degree of news personalization based on the estimated emotions. For example, if the user is stressed, the personalization unit may prioritize providing relaxing news. If the user is excited, the personalization unit may also prioritize providing entertaining news. If the user is calm, the personalization unit may also prioritize providing detailed analytical articles. In this way, the personalization unit can adjust the degree of news personalization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the personalization unit may be performed using AI or not. For example, the personalization unit can input user emotion data into a generative AI and have the generative AI adjust the degree of news personalization based on emotions.

[0073] The personalization unit can analyze a user's past news browsing history and improve the algorithm for selecting the most relevant news. For example, the personalization unit can prioritize displaying news categories that the user has frequently viewed in the past. The personalization unit can also suggest similar news articles based on news articles that the user has previously rated highly. The personalization unit can also predict and provide news that is preferred at specific times of day based on the user's browsing history. In this way, the personalization unit can provide more relevant news by analyzing the user's past news browsing history. Some or all of the above processes in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's news browsing history data into a generating AI and have the generating AI improve the algorithm for selecting the most relevant news.

[0074] The personalization unit can reflect the user's current interests and trends in real time when personalizing news. For example, the personalization unit can provide relevant news based on keywords the user has recently searched for. The personalization unit can also analyze the user's activity on social media and reflect topics of interest. The personalization unit can also provide the most relevant news to the user based on real-time trend information. In this way, the personalization unit can provide more relevant news by reflecting the user's current interests and trends in real time. Some or all of the above processes in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's search keyword data into a generating AI and have the generating AI select news that reflects the user's interests and trends in real time.

[0075] The personalization unit can estimate the user's emotions and prioritize news based on those emotions. For example, if the user is tired, the personalization unit will prioritize displaying relaxing news. If the user is excited, the personalization unit can also prioritize displaying entertaining news. If the user is calm, the personalization unit can also prioritize displaying detailed analytical articles. In this way, the personalization unit can prioritize news according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the personalization unit may be performed using AI or not. For example, the personalization unit can input user emotion data into a generative AI and have the generative AI perform emotion-based news prioritization.

[0076] The personalization unit can prioritize providing highly relevant news by considering the user's geographical location when personalizing news. For example, the personalization unit can prioritize displaying local news related to the user's current location. If the user is traveling, the personalization unit can also prioritize providing news from their travel destination. The personalization unit can also prioritize providing weather and traffic information based on the user's geographical location. In this way, the personalization unit can provide more relevant news by considering the user's geographical location. Some or all of the above processing in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's geographical location data into a generating AI and have the generating AI select news based on geographical location information.

[0077] The personalization unit can analyze a user's social media activity and provide relevant news when personalizing news. For example, the personalization unit can provide relevant news based on articles the user has shared on social media. The personalization unit can also analyze the content of posts from accounts the user follows and provide news of interest. The personalization unit can also provide relevant news based on the user's comments and reactions on social media. In this way, the personalization unit can provide more relevant news by analyzing the user's social media activity. Some or all of the above processing in the personalization unit may be performed using AI or not. For example, the personalization unit can input the user's social media activity data into a generating AI and have the generating AI select news based on social media activity.

[0078] The generation unit can estimate the user's emotions and adjust the virtual newscaster's presentation based on the estimated emotions. For example, if the user is relaxed, the generation unit can deliver the news in a calm tone. If the user is excited, the generation unit can deliver the news in an energetic tone. If the user is sad, the generation unit can deliver the news in a calm tone. In this way, the generation unit can adjust the virtual newscaster's presentation according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using the generative AI or not. For example, the generation unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the virtual newscaster's presentation based on the emotion.

[0079] The generation unit can adjust the level of detail in the anchor's expression based on the importance of the news when generating a virtual news anchor. For example, in the case of important news, the generation unit provides detailed explanations and background information. In the case of minor news, the generation unit may limit the explanation to a concise one. In the case of breaking news, the generation unit can convey information quickly and concisely. In this way, the generation unit can adjust the level of detail in the anchor's expression based on the importance of the news. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input news importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the anchor's expression based on importance.

[0080] The generation unit can apply different generation algorithms depending on the news category when generating virtual newscasters. For example, in the case of sports news, the generation unit may use dynamic presentation. In the case of economic news, the generation unit may also make extensive use of graphs and data. In the case of entertainment news, the generation unit may also use visually appealing presentation. This allows the generation unit to apply different generation algorithms depending on the news category. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input news category data into a generation AI and have the generation AI execute the application of a generation algorithm appropriate to the category.

[0081] The generation unit can estimate the user's emotions and adjust the speaking speed of the virtual newscaster based on the estimated emotions. For example, if the user is relaxed, the generation unit will speak slowly. If the user is in a hurry, the generation unit can also speak quickly. If the user is excited, the generation unit can also speak at a moderate speed. In this way, the generation unit can adjust the speaking speed of the virtual newscaster according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using the generative AI or not. For example, the generation unit can input user emotion data into the generative AI and have the generative AI perform the emotion-based adjustment of the speaking speed.

[0082] The generation unit can select the optimal display method when generating a virtual newscaster, taking into account the user's device information. For example, if the user is using a smartphone, the generation unit provides a display method that matches the screen size. If the user is using a tablet, the generation unit can also provide a display method optimized for a larger screen. If the user is using a smartwatch, the generation unit can also provide a concise and highly visible display method. In this way, the generation unit can provide a more appropriate display method by taking into account the user's device information. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the user's device information into the generation AI and have the generation AI select the optimal display method based on the device information.

[0083] The generation unit can improve the presentation of a virtual news anchor by reflecting past user feedback when generating the anchor. For example, the generation unit can reuse presentation styles that have been well-received by users in the past. The generation unit can also adjust the anchor's tone and speaking style based on user feedback. The generation unit can also analyze past user feedback and suggest the most suitable presentation method. In this way, the generation unit can provide more appropriate news by reflecting past user feedback. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input user feedback data into a generation AI and have the generation AI perform improvements to the anchor's presentation based on the feedback.

[0084] The response unit can estimate the user's emotions and adjust the way it expresses its response based on the estimated emotions. For example, if the user is relaxed, the response unit will respond in a calm tone. If the user is excited, the response unit may also respond in an energetic tone. If the user is sad, the response unit may also respond in a calm tone. In this way, the response unit can adjust the way it expresses its response according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input user emotion data into a generative AI and have the generative AI adjust the way it expresses its response based on the emotion.

[0085] The response unit can generate the optimal response by referring to the user's past question history when generating a response. For example, the response unit can provide relevant information based on the content of questions the user has asked in the past. The response unit can also create templates for frequently asked questions from the user's past question history. The response unit can also analyze the user's past question history and suggest the optimal response method. In this way, the response unit can provide a more appropriate response by referring to the user's past question history. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input the user's question history data into a generation AI and have the generation AI perform the generation of the optimal response based on the question history.

[0086] The response unit can apply different response algorithms depending on the category of the question when generating a response. For example, the response unit can provide detailed technical information for technology-related questions. For entertainment-related questions, it can also provide visually appealing information. For economic questions, it can provide information that makes extensive use of data and graphs. In this way, the response unit can provide a more appropriate response by applying different response algorithms depending on the category of the question. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input question category data into a generating AI and have the generating AI execute the application of a response algorithm appropriate to the category.

[0087] The response unit can estimate the user's emotions and determine the priority of responses based on the estimated emotions. For example, if the user is asking an urgent question, the response unit will respond quickly. If the user is relaxed, the response unit may also provide detailed information. If the user is excited, the response unit may also provide an energetic response. This allows the response unit to determine the priority of responses according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input user emotion data into a generative AI and have the generative AI perform the determination of emotion-based response priorities.

[0088] The response unit can provide highly relevant information by considering the user's geographical location when generating a response. For example, the response unit can provide local information related to the user's current location. If the user is traveling, the response unit can also provide information about their travel destination. The response unit can also provide weather and traffic information based on the user's geographical location. In this way, the response unit can provide more relevant information by considering the user's geographical location. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input the user's geographical location data into a generating AI and have the generating AI perform the task of providing information based on geographical location information.

[0089] The response unit can analyze the user's social media activity and provide relevant information when generating a response. For example, the response unit can provide relevant information based on articles the user has shared on social media. The response unit can also analyze the content of posts from accounts the user follows and provide information of interest. The response unit can also provide relevant information based on the user's comments and reactions on social media. In this way, the response unit can provide more relevant information by analyzing the user's social media activity. Some or all of the above processing in the response unit may be performed using AI or not. For example, the response unit can input the user's social media activity data into a generating AI and have the generating AI perform the task of providing information based on social media activity.

[0090] The adjustment unit can estimate the user's emotions and adjust the content and delivery method of the news based on the estimated emotions. For example, if the user is relaxed, the adjustment unit can deliver the news in a calm tone. If the user is excited, the adjustment unit can deliver the news in an energetic tone. If the user is sad, the adjustment unit can deliver the news in a calm tone. In this way, the adjustment unit can adjust the content and delivery method of the news according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the news content and delivery method based on the emotions.

[0091] The adjustment unit can select the optimal adjustment method by referring to past user feedback during the adjustment process. For example, the adjustment unit may reuse news formats that have been well-received by users in the past. The adjustment unit can also adjust the tone and content of the news based on user feedback. The adjustment unit can also analyze past user feedback and propose the optimal adjustment method. This allows the adjustment unit to make more appropriate adjustments by referring to past user feedback. Some or all of the above processes in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input user feedback data into a generating AI and have the generating AI select an adjustment method based on the feedback.

[0092] The adjustment unit can estimate the user's emotions and determine adjustment priorities based on the estimated emotions. For example, if the user provides urgent feedback, the adjustment unit can make quick adjustments. If the user is relaxed, the adjustment unit can also make detailed adjustments. If the user is excited, the adjustment unit can also make energetic adjustments. In this way, the adjustment unit can determine adjustment priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input user emotion data into a generative AI and have the generative AI perform the determination of emotion-based adjustment priorities.

[0093] The adjustment unit can select the optimal adjustment method by considering the user's device information during the adjustment process. For example, if the user is using a smartphone, the adjustment unit will adjust to the screen size. If the user is using a tablet, the adjustment unit can also perform adjustments optimized for a larger screen. If the user is using a smartwatch, the adjustment unit can also perform adjustments that are simple and easy to read. In this way, the adjustment unit can perform more appropriate adjustments by considering the user's device information. Some or all of the above-described processes in the adjustment unit may be performed using AI or not. For example, the adjustment unit can input the user's device information into a generating AI and have the generating AI select the optimal adjustment method based on the device information.

[0094] The processing unit can estimate the user's emotions and adjust the natural language processing algorithm based on the estimated emotions. For example, if the user is relaxed, the processing unit will perform natural language processing in a calm tone. If the user is excited, the processing unit may also perform natural language processing in an energetic tone. If the user is sad, the processing unit may also perform natural language processing in a calm tone. In this way, the processing unit can adjust the natural language processing algorithm according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the processing unit may be performed using or without a generative AI. For example, the processing unit can input user emotion data into a generative AI and have the generative AI perform an adjustment of the natural language processing algorithm based on the emotions.

[0095] The processing unit can select the optimal processing method by referring to the user's past dialogue history during natural language processing. For example, the processing unit performs optimal natural language processing based on the language used by the user in the past. The processing unit can also create templates for frequently asked questions from the user's past dialogue history. The processing unit can also analyze the user's past dialogue history and propose the optimal processing method. This allows the processing unit to perform more appropriate natural language processing by referring to the user's past dialogue history. Some or all of the above processing in the processing unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the processing unit can input the user's dialogue history data into a generative AI and have the generative AI select the optimal processing method based on the dialogue history.

[0096] The processing unit can estimate the user's emotions and determine the priority of natural language processing based on the estimated emotions. For example, if the user is asking an urgent question, the processing unit will perform rapid natural language processing. If the user is relaxed, the processing unit can also perform detailed natural language processing. If the user is excited, the processing unit can also perform energetic natural language processing. This allows the processing unit to determine the priority of natural language processing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the processing unit may be performed using or without a generative AI. For example, the processing unit can input user emotion data into a generative AI and have the generative AI perform the determination of emotion-based natural language processing priorities.

[0097] The processing unit can select the optimal processing method when performing natural language processing, taking into account the user's geographical location information. For example, the processing unit can perform natural language processing based on local information related to the user's current location. If the user is traveling, the processing unit can also perform natural language processing based on information about the travel destination. The processing unit can also perform natural language processing based on weather and traffic information, taking into account the user's geographical location. This allows the processing unit to perform more appropriate natural language processing by taking into account the user's geographical location information. Some or all of the processing described above in the processing unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the processing unit can input the user's geographical location data into a generative AI and have the generative AI select the optimal processing method based on the geographical location information.

[0098] The processing unit can select the optimal processing method while considering the user's health condition during natural language processing. For example, if the user is tired, the processing unit will perform concise and easy-to-understand natural language processing. If the user is healthy, the processing unit can also perform natural language processing that provides detailed information. If the user is unwell, the processing unit can also perform natural language processing in a gentle tone. In this way, the processing unit can perform more appropriate natural language processing by considering the user's health condition. Some or all of the processing described above in the processing unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the processing unit can input the user's health condition data into a generative AI and have the generative AI select the optimal processing method based on the health condition.

[0099] The processing unit can analyze a user's social media activity and provide relevant information during natural language processing. For example, the processing unit can provide relevant information based on articles shared by the user on social media. The processing unit can also analyze the content of posts from accounts followed by the user and provide information of interest. The processing unit can also provide relevant information based on the user's comments and reactions on social media. In this way, the processing unit can provide more relevant information by analyzing the user's social media activity. Some or all of the above processing in the processing unit may be performed using generative AI, or it may be performed without using generative AI. For example, the processing unit can input the user's social media activity data into a generative AI and have the generative AI perform the task of providing information based on social media activity.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The news delivery system can further monitor the user's health status and adjust the news content based on that status. For example, if a user is stressed, it can prioritize providing relaxing news. If the user is healthy, it can provide detailed analytical articles or academic news. Furthermore, if the user is unwell, it can provide lighter news or more entertaining news. In this way, the news delivery system can provide the most suitable news according to the user's health status. Health status monitoring can be done using wearable devices or smartphone sensors. For example, heart rate and stress levels can be measured, and the news content can be adjusted based on that data.

[0102] The news delivery system can further prioritize local news and region-related information by taking into account the user's geographical location. For example, if a user is in a specific city, it can provide news and event information related to that city. If a user is traveling, it can also provide tourist information and local news from their destination. Furthermore, it can provide real-time weather forecasts and traffic information based on the user's current location. This allows the news delivery system to provide more relevant news based on the user's geographical location. Geographic location information can be obtained using GPS or Wi-Fi location data. For example, the system can obtain the user's smartphone location data and adjust the news content based on that data.

[0103] The news delivery system can further analyze users' social media activity and personalize news content based on that activity. For example, it can analyze articles and comments shared by users on social media to identify topics of interest. It can also provide relevant news based on the content of accounts that users follow. Furthermore, it can analyze users' reactions and engagement on social media to select news that is likely to be of interest. As a result, the news delivery system can provide more personalized news based on users' social media activity. Social media activity analysis can be performed by obtaining data via APIs and using natural language processing technology. For example, it can analyze users' tweets and posts and adjust news content based on their content.

[0104] The news delivery system can further consider the user's device information to provide the optimal news display method. For example, if the user is using a smartphone, the news can be displayed in a layout that matches the screen size. If the user is using a tablet, a display method optimized for larger screens can be provided. Furthermore, if the user is using a smartwatch, a concise and highly visible display method can be provided. In this way, the news delivery system can provide a more appropriate news display method based on the user's device information. Device information can be obtained by detecting the type of device, screen size, resolution, etc. For example, the news display method can be adjusted based on the user's device information obtained.

[0105] The news delivery system can further improve the content and delivery method of news by referring to past user feedback. For example, it can reuse news formats that users have previously given high ratings to. It can also adjust the tone and content of news based on user feedback. Furthermore, it can analyze past user feedback and suggest the optimal news delivery method. In this way, the news delivery system can provide more relevant news by referring to past user feedback. Feedback can be collected using surveys, click data, comments, etc. For example, comments made by users on news articles can be analyzed, and the content of the news can be adjusted based on those comments.

[0106] The news delivery system can further estimate the user's emotions and adjust the news content based on those emotions. For example, if a user is stressed, it can prioritize providing relaxing news. If a user is excited, it can provide highly entertaining news. Furthermore, if a user is calm, it can provide detailed analytical articles. In this way, the news delivery system can provide the most suitable news according to the user's emotions. Emotion estimation can be performed by analyzing the user's facial expressions, voice, and text data. For example, the user's facial expressions can be captured with a camera, and emotions can be estimated based on that data.

[0107] The news delivery system can further monitor the user's health status and adjust the virtual news anchor's presentation style based on that status. For example, if the user is relaxed, the news can be delivered in a calm tone. If the user is excited, the news can be delivered in an energetic tone. Furthermore, if the user is unwell, the news can be delivered in a calm tone. In this way, the news delivery system can adjust the virtual news anchor's presentation style according to the user's health status. Health status monitoring can be done using sensors on wearable devices or smartphones. For example, heart rate and stress levels can be measured, and the virtual news anchor's presentation style can be adjusted based on that data.

[0108] The news delivery system can further estimate the user's emotions and adjust the speaking speed of the virtual news anchor based on those estimated emotions. For example, if the user is relaxed, the system can speak slowly. If the user is in a hurry, the system can speak quickly. Furthermore, if the user is excited, the system can speak at a moderate pace. In this way, the news delivery system can adjust the speaking speed of the virtual news anchor according to the user's emotions. Emotion estimation can be performed by analyzing the user's facial expressions, voice, and text data. For example, the system can analyze the user's voice tone and estimate their emotions based on that data.

[0109] The news delivery system can further estimate the user's emotions and prioritize news based on those emotions. For example, if the user is tired, it can prioritize displaying relaxing news. If the user is excited, it can prioritize displaying entertaining news. Furthermore, if the user is calm, it can prioritize displaying detailed analytical articles. In this way, the news delivery system can prioritize news according to the user's emotions. Emotion estimation can be performed by analyzing the user's facial expressions, voice, and text data. For example, the user's text messages can be analyzed, and their emotions can be estimated based on that data.

[0110] The news delivery system can further analyze a user's past news browsing history and personalize the news content based on that history. For example, it can prioritize displaying news categories that the user has frequently viewed in the past. It can also suggest similar news articles based on news articles that the user has previously rated highly. Furthermore, it can predict and provide news that users will prefer at specific times of day based on their browsing history. In this way, the news delivery system can provide more relevant news by analyzing a user's past news browsing history. The analysis of news browsing history can be done based on user click data and browsing time. For example, it can analyze the categories of news articles that a user has viewed in the past and adjust the news content based on that data.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The personalization section personalizes news based on the user's interests and preferences. For example, it analyzes the user's past browsing history and selects news that is likely to interest the user. It can also identify user interests based on survey results and social media activity. Specifically, it analyzes the categories of news articles the user has viewed in the past and prioritizes providing news from similar categories. It can also analyze articles and comments the user has shared on social media to identify topics of interest. Step 2: The generation unit generates a virtual news anchor based on the news selected by the personalization unit. For example, it can generate the appearance of the virtual anchor using 3D modeling technology and generate the voice of the virtual anchor using speech synthesis technology. Furthermore, the appearance and voice of the virtual anchor can be customized according to the user's preferences. In addition, to deliver the news in a natural conversational format, it can also generate the movements and facial expressions of the virtual anchor using generation AI. Step 3: The response unit uses a virtual newscaster generated by the generation unit to respond to user questions. For example, when a user asks the virtual caster a question, the response unit analyzes the question and generates an appropriate answer. The response unit can understand the user's question using natural language processing technology and search for relevant information. Specifically, if a user asks, "Tell me more about this news," the response unit searches for relevant information, and the virtual caster conveys that information. It can also adjust the content and presentation of the news in real time based on user feedback.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the above-mentioned personalization unit, generation unit, response unit, adjustment unit, processing unit, and multiple elements including the generation unit is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the personalization unit analyzes the user's interests and preferences using the control unit 46A of the smart device 14 and personalizes the news. The generation unit generates a virtual news caster using the specific processing unit 290 of the data processing unit 12. The response unit responds to the user's questions using the control unit 46A of the smart device 14. The adjustment unit adjusts the content and delivery method of the news based on user feedback using the specific processing unit 290 of the data processing unit 12. The processing unit performs natural language processing using the specific processing unit 290 of the data processing unit 12. The generation unit generates real-time video using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the above example and can be modified in various ways.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the above-mentioned personalization unit, generation unit, response unit, adjustment unit, processing unit, and multiple elements including the generation unit is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the personalization unit analyzes the user's interests and preferences using the control unit 46A of the smart glasses 214 and personalizes the news. The generation unit generates a virtual news caster using the specific processing unit 290 of the data processing unit 12. The response unit responds to the user's questions using the control unit 46A of the smart glasses 214. The adjustment unit adjusts the content and method of delivering the news based on user feedback using the specific processing unit 290 of the data processing unit 12. The processing unit performs natural language processing using the specific processing unit 290 of the data processing unit 12. The generation unit generates real-time video using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the above example and can be modified in various ways.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the above-mentioned personalization unit, generation unit, response unit, adjustment unit, processing unit, and multiple elements including the generation unit is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the personalization unit analyzes the user's interests and preferences using the control unit 46A of the headset terminal 314 and personalizes the news. The generation unit generates a virtual news caster using the specific processing unit 290 of the data processing unit 12. The response unit responds to the user's questions using the control unit 46A of the headset terminal 314. The adjustment unit adjusts the content and delivery method of the news based on user feedback using the specific processing unit 290 of the data processing unit 12. The processing unit performs natural language processing using the specific processing unit 290 of the data processing unit 12. The generation unit generates real-time video using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the above example and can be modified in various ways.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the above-mentioned personalization unit, generation unit, response unit, adjustment unit, processing unit, and multiple elements including the generation unit is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the personalization unit analyzes the user's interests and preferences using the control unit 46A of the robot 414 and personalizes the news. The generation unit generates a virtual news caster using the specific processing unit 290 of the data processing unit 12. The response unit responds to the user's questions using the control unit 46A of the robot 414. The adjustment unit adjusts the content and method of delivering the news based on user feedback using the specific processing unit 290 of the data processing unit 12. The processing unit performs natural language processing using the specific processing unit 290 of the data processing unit 12. The generation unit generates real-time video using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the above example and can be modified in various ways.

[0166] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0176] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] (Note 1) A personalization unit that personalizes news based on the user's interests and preferences, A generation unit generates a virtual news caster based on the news selected by the personalization unit, The system includes a response unit in which the virtual newscaster generated by the generation unit responds to user questions. A system characterized by the following features. (Note 2) It includes an adjustment unit that adjusts the content and delivery method of news based on user feedback. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a generation unit that generates news content. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a processing unit for natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a generation unit that performs real-time video generation. The system described in Appendix 1, characterized by the features described herein. (Note 6) The personalization unit described above is It estimates the user's sentiment and adjusts the degree of news personalization based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The personalization unit described above is We will improve the algorithm that analyzes users' past news browsing history and selects the most relevant news. The system described in Appendix 1, characterized by the features described herein. (Note 8) The personalization unit described above is When personalizing news, reflect the user's current interests and trends in real time. The system described in Appendix 1, characterized by the features described herein. (Note 9) The personalization unit described above is It estimates user sentiment and prioritizes news based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The personalization unit described above is When personalizing news, the system prioritizes providing relevant news by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The personalization unit described above is When personalizing news, we analyze the user's social media activity and provide relevant news. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is The system estimates the user's emotions and adjusts the virtual newscaster's presentation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is When generating a virtual news anchor, adjust the level of detail in the anchor's presentation based on the importance of the news item. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating virtual newscasters, different generation algorithms are applied depending on the news category. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is It estimates the user's emotions and adjusts the speaking speed of the virtual newscaster based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating a virtual newscaster, the optimal display method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is When generating virtual newscasters, the appearance of the casters is improved by incorporating past user feedback. The system described in Appendix 1, characterized by the features described herein. (Note 18) The response unit is It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The response unit is When generating a response, the system refers to the user's past question history to generate the most appropriate response. The system described in Appendix 1, characterized by the features described herein. (Note 20) The response unit is When generating responses, different response algorithms are applied depending on the category of the question. The system described in Appendix 1, characterized by the features described herein. (Note 21) The response unit is It estimates the user's emotions and determines the priority of responses based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The response unit is When generating a response, the system takes the user's geographical location into consideration to provide highly relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 23) The response unit is When generating a response, the system analyzes the user's social media activity and provides relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 24) The adjustment unit is, We estimate user sentiment and adjust the content and delivery method of news based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 25) The adjustment unit is, During the adjustment process, the optimal adjustment method is selected by referring to the user's past feedback. The system described in Appendix 2, characterized by the features described herein. (Note 26) The adjustment unit is, It estimates the user's emotions and determines the priority of adjustments based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 27) The adjustment unit is, During adjustment, the optimal adjustment method is selected considering the user's device information. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned processing unit, It estimates the user's emotions and adjusts the natural language processing algorithm based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 29) The aforementioned processing unit, During natural language processing, the system selects the optimal processing method by referring to the user's past dialogue history. The system described in Appendix 4, characterized by the features described herein. (Note 30) The aforementioned processing unit, It estimates the user's emotions and determines the priority of natural language processing based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 31) The aforementioned processing unit, When processing natural language, the optimal processing method is selected by considering the user's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 32) The aforementioned processing unit, When processing natural language, the optimal processing method is selected while taking the user's health status into consideration. The system described in Appendix 4, characterized by the features described herein. (Note 33) The aforementioned processing unit, During natural language processing, the system analyzes the user's social media activity and provides relevant information. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A personalization unit that personalizes news based on the user's interests and preferences, A generation unit generates a virtual news caster based on the news selected by the personalization unit, The system includes a response unit in which the virtual newscaster generated by the generation unit responds to user questions. A system characterized by the following features.

2. It includes an adjustment unit that adjusts the content and delivery method of news based on user feedback. The system according to feature 1.

3. It includes a generation unit that generates news content. The system according to feature 1.

4. It includes a processing unit for natural language processing. The system according to feature 1.

5. It includes a generation unit that performs real-time video generation. The system according to feature 1.

6. The personalization unit described above is It estimates the user's sentiment and adjusts the degree of news personalization based on that estimated sentiment. The system according to feature 1.

7. The personalization unit described above is We will improve the algorithm that analyzes users' past news browsing history and selects the most relevant news. The system according to feature 1.

8. The personalization unit described above is When personalizing news, reflect the user's current interests and trends in real time. The system according to feature 1.

9. The personalization unit described above is It estimates user sentiment and prioritizes news based on that estimated sentiment. The system according to feature 1.

Images