system

Abstract

The system according to this embodiment aims to accurately read news in fluent Japanese or a foreign language. [Solution] The system according to this embodiment comprises an acquisition unit, an analysis unit, an instruction unit, and a control unit. The acquisition unit acquires news text data. The analysis unit analyzes the text data acquired by the acquisition unit. The instruction unit issues instructions to the robot to read aloud based on the data analyzed by the analysis unit. The control unit controls the robot, which speaks fluent Japanese or a foreign language, based on the instructions issued by the instruction unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there are problems such as mistakes occurring in news reading and difficulty in fluent Japanese or foreign language reading.

[0005] The system according to the embodiment aims to accurately read news in fluent Japanese or foreign language.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, an analysis unit, an instruction unit, and a control unit. The acquisition unit acquires news text data. The analysis unit analyzes the text data acquired by the acquisition unit. The instruction unit issues instructions to the robot to read aloud based on the data analyzed by the analysis unit. The control unit controls the robot, which speaks fluent Japanese or a foreign language, based on the instructions issued by the instruction unit. [Effects of the Invention]

[0007] The system according to this embodiment can accurately read news in fluent Japanese or a foreign language. [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 controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". 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 reception 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 reception 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 program announcement robot system according to an embodiment of the present invention is a robot system that reads news using an AI agent. This news program announcement robot system acquires news text data and analyzes it using natural language processing technology. Based on the results of this analysis, it issues instructions to the robot to read the news. The robot can speak fluent Japanese and foreign languages ​​using speech synthesis technology. The AI ​​agent has multiple language models and can read news in foreign languages ​​by switching between them. This mechanism allows a robot to replace news announcers, enabling reductions in labor costs and prevention of errors. For example, the news program announcement robot system could be introduced to television stations and news distribution companies. These companies are troubled by the labor costs and errors of announcers, and introducing a news program announcement robot system utilizing an AI agent can solve these problems. For example, the news program announcement robot system acquires news text data. For example, news in various formats and types such as online news, newspaper articles, and breaking news are targeted. Next, the news program announcement robot system analyzes the news text data using natural language processing technology. For example, specific natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis are used. Next, the news program announcement robot system issues instructions to the robot to read based on the analysis results. For example, it issues instructions to the robot to read the news in fluent Japanese or a foreign language. Next, the news program announcement robot system uses speech synthesis technology to control the robot that speaks fluent Japanese or a foreign language. For example, specific speech synthesis technologies such as text-to-speech (TTS) and speech synthesis algorithms are used. As a result, the news program announcement robot system can read the news in fluent Japanese or a foreign language. Thus, the news program announcement robot system can read the news in fluent Japanese or a foreign language by acquiring news text data, analyzing it, issuing instructions, and controlling the robot.

[0029] The news program announcement robot system according to this embodiment comprises an acquisition unit, an analysis unit, an instruction unit, and a control unit. The acquisition unit acquires news text data. News text data includes, but is not limited to, online news, newspaper articles, and breaking news. The acquisition unit acquires news text data using, for example, the API of a news site. The acquisition unit can also acquire news text data by subscribing to a news feed. Furthermore, the acquisition unit can acquire news text data using scraping techniques. For example, the acquisition unit acquires the latest news articles using the API of a news site. By subscribing to a news feed, news that is updated in real time can be obtained. By using scraping techniques, news text data can be automatically obtained from web pages. The analysis unit analyzes the news text data acquired by the acquisition unit using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit divides the news text data into word units using morphological analysis. Furthermore, the analysis unit can analyze the grammatical structure of the news text data using grammatical analysis. In addition, the analysis unit can analyze the meaning of the news text data using semantic analysis. For example, morphological analysis divides the news text data into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the news text data and identifies sentence components such as subject, predicate, and object. Semantic analysis analyzes the meaning of the news text data and understands the meaning of the sentence. The instruction unit gives instructions to the robot to read aloud based on the data analyzed by the analysis unit. For example, the instruction unit can instruct the robot to read the news aloud in fluent Japanese or a foreign language. For example, the instruction unit can also instruct the robot on the reading speed and intonation of the news. For example, the instruction unit can instruct the robot to add emotional expressions when reading the news. For example, the instruction unit can instruct the robot to adjust the reading speed of the news.The instruction unit can give instructions to the robot to add emotional expression when reading the news. The control unit controls the robot to speak fluent Japanese or a foreign language based on the instructions given by the instruction unit. The control unit uses speech synthesis technology to control the robot to speak fluent Japanese or a foreign language. Speech synthesis technology includes, but is not limited to, text-to-speech (TTS) and speech synthesis algorithms. For example, the control unit uses text-to-speech (TTS) technology to convert news text data into speech. The control unit can also use a speech synthesis algorithm to control the robot to speak fluent Japanese or a foreign language. For example, text-to-speech (TTS) technology converts news text data into speech, enabling the robot to speak fluently. A speech synthesis algorithm generates natural pronunciation and intonation based on the news text data. As a result, the news program announcement robot system according to this embodiment can read the news fluently in Japanese or a foreign language by acquiring news text data, analyzing it, giving instructions, and controlling the robot.

[0030] The acquisition unit acquires news text data. This news text data includes, but is not limited to, online news, newspaper articles, and breaking news. The acquisition unit can acquire news text data by, for example, using the API of a news site. It can also acquire news text data by subscribing to a news feed. Furthermore, the acquisition unit can acquire news text data using scraping techniques. For example, the acquisition unit can acquire the latest news articles by using the API of a news site. By subscribing to a news feed, it can acquire news that is updated in real time. By using scraping techniques, news text data can be automatically acquired from web pages. By combining these methods, the acquisition unit can efficiently collect diverse news data from a wide range of news sources. For example, by using an API, it can acquire regularly updated data from reliable news sources, and by subscribing to a news feed, it can acquire highly timely news in real time. Furthermore, by using scraping techniques, it can collect data from news sites that cannot be acquired through APIs or news feeds. As a result, the acquisition unit can quickly collect the latest and diverse news data, ensuring the freshness and diversity of information throughout the system. Furthermore, the acquisition unit can build a database that centrally manages the collected news data, allowing the analysis and instruction units to access it efficiently. This enables the acquisition unit to handle everything from news data collection to management in a consistent manner, improving the overall efficiency and reliability of the system.

[0031] The analysis unit analyzes the news text data acquired by the acquisition unit using natural language processing techniques. These techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide the news text data into individual words. It can also analyze the grammatical structure of the news text data using grammatical analysis. Furthermore, it can analyze the meaning of the news text data using semantic analysis. For example, morphological analysis divides the news text data into individual words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the news text data and identifies sentence components such as subject, predicate, and object. Semantic analysis analyzes the meaning of the news text data and understands the meaning of the sentence. By combining these analysis techniques, the analysis unit can analyze the news text data from multiple angles and gain a deeper understanding of the news content. For example, it can perform grammatical analysis based on data divided into individual words using morphological analysis to clarify the sentence structure. Furthermore, semantic analysis allows for an accurate understanding of the content and intent of the news. Based on these analysis results, the analysis unit can evaluate the importance and urgency of the news and determine the appropriate reading order and expression. The analysis unit can also identify proper nouns and technical terms contained in the news text data and provide information for generating appropriate pronunciation and intonation. As a result, the analysis unit can accurately and thoroughly analyze the content of the news, providing a foundation for the instruction and control units to give appropriate instructions and control.

[0032] The instruction unit issues instructions to the robot to read aloud based on the data analyzed by the analysis unit. For example, the instruction unit can instruct the robot to read the news fluently in Japanese or a foreign language. The instruction unit can also instruct the robot on the speed and intonation of reading the news. For example, the instruction unit can instruct the robot to add emotional expression when reading the news. For example, the instruction unit can instruct the robot to adjust the speed of reading the news. The instruction unit can instruct the robot to add emotional expression when reading the news. Based on the analysis results provided by the analysis unit, the instruction unit determines an appropriate reading method according to the content and importance of the news. For example, for urgent or important news, it can instruct the robot to read it quickly and add emotional expression to increase the impact on the audience. In addition, the instruction unit can facilitate audience comprehension by instructing appropriate intonation and emphasis according to the content of the news. Furthermore, the instruction unit can implement techniques to attract the audience's attention when reading the news. For example, it can instruct the robot to emphasize important points at the beginning of the news to attract the audience's attention. Furthermore, by incorporating appropriate pauses during news reading, the system makes it easier for viewers to process the information. The control unit provides these instructions to the robot in real time, ensuring that the news is read smoothly and effectively. This allows the control unit to deliver clear and engaging news to viewers.

[0033] The control unit controls a robot that speaks fluent Japanese or a foreign language based on instructions issued by the instruction unit. The control unit uses speech synthesis technology to control the robot that speaks fluent Japanese or a foreign language. Speech synthesis technology includes, but is not limited to, text-to-speech (TTS) and speech synthesis algorithms. For example, the control unit uses text-to-speech (TTS) technology to convert news text data into speech. The control unit can also use speech synthesis algorithms to control a robot that speaks fluent Japanese or a foreign language. For example, text-to-speech (TTS) technology converts news text data into speech, enabling the robot to speak fluently. Speech synthesis algorithms generate natural pronunciation and intonation based on news text data. The control unit aims to use these technologies to enable the robot to produce natural and easy-to-understand speech. For example, the control unit sets appropriate speech parameters according to the content of the news and controls the robot to read the news accurately and fluently. Furthermore, the control unit can also control the robot's movements and facial expressions to complement visual information and enhance the effectiveness of information transmission to the audience. For example, by changing the robot's facial expressions according to the news content, emotional expression to the viewer can be enhanced. Furthermore, by controlling the robot's movements, the viewer's attention can be captured, and the news content can be conveyed more effectively. The control unit performs these controls in real time, ensuring that the news is read smoothly and effectively. This allows the control unit to provide viewers with clear and engaging news.

[0034] The analysis unit can analyze news text data using natural language processing techniques. For example, the analysis unit can divide the news text data into words using morphological analysis. For example, the analysis unit can divide the news text data into words using morphological analysis and identify the part of speech of each word. The analysis unit can also analyze the grammatical structure of the news text data using grammatical analysis. For example, the analysis unit can analyze the grammatical structure of the news text data using grammatical analysis and identify sentence components such as subjects, predicates, and objects. Furthermore, the analysis unit can analyze the meaning of the news text data using semantic analysis. For example, the analysis unit can analyze the meaning of the news text data using semantic analysis and understand the meaning of the sentence. In this way, news text data can be accurately analyzed using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input news text data into a generating AI, which can then perform morphological analysis, grammatical analysis, and semantic analysis.

[0035] The control unit can control a robot that speaks fluent Japanese or a foreign language using speech synthesis technology. For example, the control unit can convert news text data into speech using text-to-speech (TTS) technology. For example, the control unit can convert news text data into speech using text-to-speech (TTS) technology, enabling the robot to speak fluently. The control unit can also control a robot that speaks fluent Japanese or a foreign language using speech synthesis algorithms. For example, the control unit can use a speech synthesis algorithm to generate natural pronunciation and intonation based on news text data. This allows the robot to speak fluent Japanese or a foreign language using speech synthesis technology. Speech synthesis technology includes, but is not limited to, text-to-speech (TTS) and speech synthesis algorithms. Some or all of the above-described processes in the control unit may be performed using, for example, AI, or not using AI. For example, the control unit can input news text data into a generating AI and have the generating AI perform speech synthesis.

[0036] The control unit has multiple language models and can read aloud news in foreign languages ​​by switching between them. The control unit has specific language models such as an English model, a Japanese model, and a French model. For example, the control unit can read aloud English news using the English model. The control unit can also read aloud Japanese news using the Japanese model. Furthermore, the control unit can read aloud French news using the French model. For example, the control unit can select and switch the appropriate language model according to the language of the news. This allows the control unit to read aloud news in foreign languages ​​by switching between multiple language models. The multiple language models include, but are not limited to, an English model, a Japanese model, and a French model. Some or all of the above processing in the control unit may be performed using AI, for example, or without AI. For example, the control unit can have a generating AI select an appropriate language model according to the language of the news, and have the generating AI perform the language model switching.

[0037] The news retrieval unit can filter news based on the user's areas of interest and past browsing history. For example, the retrieval unit can prioritize retrieving news categories that the user has frequently viewed in the past. The retrieval unit can also prioritize retrieving news related to the user's areas of interest, delaying other news. Furthermore, the retrieval unit can analyze the user's past browsing history and automatically select and retrieve news that is likely to be of interest. This allows the system to provide users with news that is highly relevant to them by filtering news based on their areas of interest and past browsing history. News filtering may be performed using, for example, a generative AI, or without one. For example, the retrieval unit can input the user's areas of interest and past browsing history into a generative AI, which can then perform news filtering.

[0038] The retrieval unit can obtain the latest information from news sources that are updated in real time when retrieving news. For example, the retrieval unit can use the API of a news site to retrieve the latest news articles in real time. The retrieval unit can also collect trending information from social media and retrieve news that includes the latest topics. For example, the retrieval unit can collect trending information from social media and retrieve news that includes the latest topics. Furthermore, the retrieval unit can receive push notifications from news distribution services and instantly retrieve the latest news. For example, the retrieval unit can receive push notifications from news distribution services and instantly retrieve the latest news. This ensures that the latest news is always provided by retrieving the latest information from news sources that are updated in real time. News retrieval may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the retrieval unit can input the API of a news site into a generative AI and have the generative AI retrieve the latest news articles.

[0039] The news acquisition unit can prioritize acquiring highly relevant news by considering the user's geographical location information when acquiring news. For example, the acquisition unit can prioritize acquiring local news related to the user's current location. For example, the acquisition unit can prioritize acquiring local news related to the user's current location. Furthermore, if the user is traveling, the acquisition unit can prioritize acquiring news related to the region they are visiting. For example, if the user is traveling, the acquisition unit can prioritize acquiring news related to the region they are visiting. In addition, based on the user's geographical location information, the acquisition unit can prioritize acquiring information on events and weather in nearby areas. For example, based on the user's geographical location information, the acquisition unit can prioritize acquiring information on events and weather in nearby areas. In this way, by acquiring news while considering the user's geographical location information, it is possible to provide the user with news that is highly relevant to them. News acquisition may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the acquisition unit can input the user's geographical location information into a generative AI, and have the generative AI acquire highly relevant news.

[0040] The acquisition unit can analyze the user's social media activity and acquire relevant news when acquiring news. For example, the acquisition unit can analyze the content of posts from accounts that the user follows on social media and acquire relevant news. The acquisition unit can also acquire news that the user might be interested in based on articles that the user has shared on social media. Furthermore, the acquisition unit can analyze the user's comments and reactions on social media and acquire news related to topics of interest. For example, the acquisition unit can analyze the user's comments and reactions on social media and acquire news related to topics of interest. In this way, by analyzing the user's social media activity and acquiring news, it is possible to provide the user with news that is of interest to them. News acquisition may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the acquisition unit can input the user's social media activity data into a generative AI and have the generative AI acquire relevant news.

[0041] The analysis unit can adjust the level of detail in its analysis based on the importance of the news. For example, for important news articles, the analysis unit can perform a detailed analysis and provide background and related information. For example, for important news articles, the analysis unit can perform a detailed analysis and provide background and related information. The analysis unit can also perform a concise analysis that focuses on the main points for general news articles. For example, for general news articles, the analysis unit can perform a concise analysis that focuses on the main points for general news articles. Furthermore, for breaking news, the analysis unit can perform a rapid analysis and immediately provide important information. For example, for breaking news, the analysis unit can perform a rapid analysis and immediately provide important information. In this way, by adjusting the level of detail in the analysis based on the importance of the news, a detailed analysis can be provided for important news. The evaluation of news importance may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the analysis unit can input the news importance into a generative AI and have the generative AI perform the importance evaluation.

[0042] The analysis unit can apply different analysis algorithms depending on the news category when analyzing news. For example, for political news, the analysis unit can apply an analysis algorithm that takes into account the political background and impact. For example, for economic news, the analysis unit can apply an analysis algorithm that takes into account economic indicators and market trends. For example, for sports news, the analysis unit can apply an analysis algorithm that takes into account match results and player performance. In this way, by applying different analysis algorithms depending on the news category, the system can provide optimal analysis results for each category. The classification of news categories may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the news categories into a generative AI and have the generative AI perform the category classification.

[0043] The analysis unit can determine the priority of news analysis based on the publication date of the news. For example, the analysis unit can prioritize the analysis of the latest news articles and provide the information immediately. The analysis unit can also postpone the analysis of older news articles. Furthermore, the analysis unit can prioritize the analysis of breaking news regardless of the publication date. In this way, by determining the priority of analysis based on the publication date of the news, the latest news can be prioritized. The publication date of the news may be determined using, for example, a generative AI, or it may be done without using a generative AI. For example, the analysis unit can input the publication date of the news into a generative AI and have the generative AI determine the publication date.

[0044] The analysis unit can adjust the order of analysis based on the relevance of the news articles. For example, the analysis unit can prioritize analyzing news related to the user's areas of interest. The analysis unit can also prioritize analyzing highly relevant news based on the user's past browsing history. Furthermore, if the content of one news article is related to other news articles, the analysis unit can analyze related news articles together. This allows the analysis unit to prioritize the analysis of highly relevant news articles by adjusting the order of analysis based on the relevance of the news articles. The evaluation of news relevance may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the relevance of the news articles into a generative AI and have the generative AI perform the relevance evaluation.

[0045] The instruction unit can adjust the level of detail in instructions given to the robot based on the importance of the news. For example, for important news articles, the instruction unit can give detailed instructions and instruct the robot to read them carefully. For example, for important news articles, the instruction unit can give detailed instructions and instruct the robot to read them carefully. For general news articles, the instruction unit can give concise instructions and instruct the robot to read them concisely. For example, for general news articles, the instruction unit can give concise instructions and instruct the robot to read them concisely. Furthermore, for breaking news, the instruction unit can give quick instructions and instruct the robot to read them immediately. For example, for breaking news, the instruction unit can give quick instructions and instruct the robot to read them immediately. In this way, by adjusting the level of detail in instructions based on the importance of the news, detailed instructions can be given for important news. The evaluation of news importance may be performed using, for example, generative AI, or without using generative AI. For example, the instruction unit can input the importance level of news items into the generating AI, which can then perform the importance evaluation.

[0046] The instruction unit can apply different instruction algorithms to the robot depending on the news category. For example, for political news, the instruction unit can apply an instruction algorithm that takes into account the political background and influence. For economic news, the instruction unit can also apply an instruction algorithm that takes into account economic indicators and market trends. Furthermore, for sports news, the instruction unit can apply an instruction algorithm that takes into account match results and player performance. By applying different instruction algorithms depending on the news category, the optimal instructions can be given for each category. The classification of news categories may be performed using, for example, a generative AI, or without using a generative AI. For example, the instruction unit can input the news categories into a generative AI, and have the generative AI perform the category classification.

[0047] The instruction unit can prioritize instructions to the robot based on the timing of news submission. For example, the instruction unit can prioritize the latest news articles and have them read aloud immediately. The instruction unit can also postpone instructions for older news articles. Furthermore, the instruction unit can prioritize instructions for breaking news regardless of the submission timing. This allows the robot to receive the latest news preferentially by prioritizing instructions based on the timing of news submission. The timing of news submission can be determined using, for example, a generative AI, or without using a generative AI. For example, the instruction unit can input the timing of news submission into a generative AI, which can then determine the timing.

[0048] The instruction unit can adjust the order of instructions given to the robot based on the relevance of the news. For example, the instruction unit can prioritize giving instructions to news related to the user's areas of interest. The instruction unit can also prioritize giving instructions to highly relevant news based on the user's past browsing history. Furthermore, if the content of one news item is related to another, the instruction unit can group related news items together and give instructions to those items together. This allows the robot to prioritize the provision of highly relevant news by adjusting the order of instructions based on the relevance of the news. The evaluation of news relevance may be performed using, for example, a generative AI, or without using a generative AI. For example, the instruction unit can input the relevance of the news into a generative AI and have the generative AI perform the relevance evaluation.

[0049] The control unit can adjust the level of detail in the reading of news based on its importance when controlling the robot. For example, the control unit can provide detailed readings of important news articles, including background and related information. The control unit can also provide concise readings of general news articles, focusing on the main points. Furthermore, the control unit can provide rapid readings of breaking news, immediately providing important information. This allows for detailed readings of important news by adjusting the level of detail in the reading based on its importance. The evaluation of news importance may be performed using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the news importance into a generative AI, which can then perform the importance evaluation.

[0050] The control unit can apply different reading algorithms depending on the news category when controlling the robot. For example, for political news, the control unit can apply a reading algorithm that takes into account the political background and impact. For economic news, the control unit can also apply a reading algorithm that takes into account economic indicators and market trends. Furthermore, for sports news, the control unit can apply a reading algorithm that takes into account match results and player performance. By applying different reading algorithms depending on the news category, the optimal reading can be provided for each category. The classification of news categories may be performed using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the news categories into a generative AI and have the generative AI perform the category classification.

[0051] The control unit can determine the reading priority based on the timing of news submission when controlling the robot. For example, the control unit can prioritize reading the latest news articles to provide information immediately. The control unit can also postpone reading older news articles. Furthermore, the control unit can prioritize reading breaking news regardless of the submission timing. This allows the robot to prioritize reading the latest news by determining the reading priority based on the timing of news submission. The timing of news submission can be determined using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the timing of news submission into a generative AI, which can then determine the timing.

[0052] The control unit can adjust the reading order of news articles based on their relevance when controlling the robot. For example, the control unit can prioritize reading news articles related to the user's areas of interest. The control unit can also prioritize reading highly relevant news articles based on the user's past browsing history. Furthermore, if the content of one news article is related to another, the control unit can read related news articles together. This allows the system to prioritize the provision of highly relevant news articles by adjusting the reading order based on their relevance. The evaluation of news relevance may be performed using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the news relevance into a generative AI and have the generative AI perform the relevance evaluation.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The news program announcement robot system can analyze a user's past news viewing history and customize news based on the user's interests. For example, if a user has frequently viewed economic news in the past, economic news can be prioritized. Similarly, if a user is interested in sports news, the system can provide the latest sports news. Furthermore, if a user is interested in news from a specific region, news from that region can be prioritized. This allows the system to provide the most relevant news according to the user's interests.

[0055] The news program announcement robot system can adjust the order in which news is read based on its importance. For example, it can read breaking news or important news first, while general news can be postponed. Furthermore, the order of news can be customized according to the user's interests, allowing important news to be delivered preferentially.

[0056] The news program announcement robot system can customize news based on the user's geographical location. For example, if the user is in a specific region, it can prioritize news related to that region. If the user is traveling, it can also provide news relevant to their destination. Furthermore, it can provide local news based on the user's current location. This allows the system to deliver the most relevant news according to the user's geographical location.

[0057] The news program announcement robot system can apply different reading algorithms depending on the news category. For example, for political news, it can apply a reading algorithm that takes into account the political background and impact. For economic news, it can apply a reading algorithm that takes into account economic indicators and market trends. Furthermore, for sports news, it can apply a reading algorithm that takes into account match results and player performance. This allows the system to provide the most optimal reading for each news category.

[0058] The news program announcement robot system can prioritize news based on when it was submitted. For example, it can prioritize providing the latest news articles and deliver information immediately. It can also postpone older news articles. Furthermore, it can prioritize breaking news regardless of when it was submitted. This allows the system to provide the most relevant news based on when it was submitted.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The acquisition unit retrieves news text data. This news text data includes online news, newspaper articles, breaking news, etc. The acquisition unit uses news site APIs to retrieve news text data. It can also retrieve news text data by subscribing to news feeds. Furthermore, it can automatically retrieve news text data from web pages using scraping techniques. Step 2: The analysis unit analyzes the news text data acquired by the acquisition unit using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis is used to divide the news text data into words, grammatical analysis is used to analyze the grammatical structure, and semantic analysis is used to analyze the meaning of the news text data. Step 3: The instruction unit issues instructions to the robot to read aloud based on the data analyzed by the analysis unit. The instruction unit instructs the robot to read the news aloud in fluent Japanese or a foreign language. It can also issue instructions to adjust the reading speed, intonation, and emotional expression of the news. Step 4: The control unit controls the robot, which speaks fluent Japanese and foreign languages, based on instructions issued by the instruction unit. The control unit uses speech synthesis technology to convert news text data into speech, enabling the robot to speak fluently. Speech synthesis technology includes text-to-speech (TTS) and speech synthesis algorithms.

[0061] (Example of form 2) The news program announcement robot system according to an embodiment of the present invention is a robot system that reads news using an AI agent. This news program announcement robot system acquires news text data and analyzes it using natural language processing technology. Based on the results of this analysis, it issues instructions to the robot to read the news. The robot can speak fluent Japanese and foreign languages ​​using speech synthesis technology. The AI ​​agent has multiple language models and can read news in foreign languages ​​by switching between them. This mechanism allows a robot to replace news announcers, enabling reductions in labor costs and prevention of errors. For example, the news program announcement robot system could be introduced to television stations and news distribution companies. These companies are troubled by the labor costs and errors of announcers, and introducing a news program announcement robot system utilizing an AI agent can solve these problems. For example, the news program announcement robot system acquires news text data. For example, news in various formats and types such as online news, newspaper articles, and breaking news are targeted. Next, the news program announcement robot system analyzes the news text data using natural language processing technology. For example, specific natural language processing techniques such as morphological analysis, grammatical analysis, and semantic analysis are used. Next, the news program announcement robot system issues instructions to the robot to read based on the analysis results. For example, it issues instructions to the robot to read the news in fluent Japanese or a foreign language. Next, the news program announcement robot system uses speech synthesis technology to control the robot that speaks fluent Japanese or a foreign language. For example, specific speech synthesis technologies such as text-to-speech (TTS) and speech synthesis algorithms are used. As a result, the news program announcement robot system can read the news in fluent Japanese or a foreign language. Thus, the news program announcement robot system can read the news in fluent Japanese or a foreign language by acquiring news text data, analyzing it, issuing instructions, and controlling the robot.

[0062] The news program announcement robot system according to this embodiment comprises an acquisition unit, an analysis unit, an instruction unit, and a control unit. The acquisition unit acquires news text data. News text data includes, but is not limited to, online news, newspaper articles, and breaking news. The acquisition unit acquires news text data using, for example, the API of a news site. The acquisition unit can also acquire news text data by subscribing to a news feed. Furthermore, the acquisition unit can acquire news text data using scraping techniques. For example, the acquisition unit acquires the latest news articles using the API of a news site. By subscribing to a news feed, news that is updated in real time can be obtained. By using scraping techniques, news text data can be automatically obtained from web pages. The analysis unit analyzes the news text data acquired by the acquisition unit using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit divides the news text data into word units using morphological analysis. Furthermore, the analysis unit can analyze the grammatical structure of the news text data using grammatical analysis. In addition, the analysis unit can analyze the meaning of the news text data using semantic analysis. For example, morphological analysis divides the news text data into words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the news text data and identifies sentence components such as subject, predicate, and object. Semantic analysis analyzes the meaning of the news text data and understands the meaning of the sentence. The instruction unit gives instructions to the robot to read aloud based on the data analyzed by the analysis unit. For example, the instruction unit can instruct the robot to read the news aloud in fluent Japanese or a foreign language. For example, the instruction unit can also instruct the robot on the reading speed and intonation of the news. For example, the instruction unit can instruct the robot to add emotional expressions when reading the news. For example, the instruction unit can instruct the robot to adjust the reading speed of the news.The instruction unit can give instructions to the robot to add emotional expression when reading the news. The control unit controls the robot to speak fluent Japanese or a foreign language based on the instructions given by the instruction unit. The control unit uses speech synthesis technology to control the robot to speak fluent Japanese or a foreign language. Speech synthesis technology includes, but is not limited to, text-to-speech (TTS) and speech synthesis algorithms. For example, the control unit uses text-to-speech (TTS) technology to convert news text data into speech. The control unit can also use a speech synthesis algorithm to control the robot to speak fluent Japanese or a foreign language. For example, text-to-speech (TTS) technology converts news text data into speech, enabling the robot to speak fluently. A speech synthesis algorithm generates natural pronunciation and intonation based on the news text data. As a result, the news program announcement robot system according to this embodiment can read the news fluently in Japanese or a foreign language by acquiring news text data, analyzing it, giving instructions, and controlling the robot.

[0063] The acquisition unit acquires news text data. This news text data includes, but is not limited to, online news, newspaper articles, and breaking news. The acquisition unit can acquire news text data by, for example, using the API of a news site. It can also acquire news text data by subscribing to a news feed. Furthermore, the acquisition unit can acquire news text data using scraping techniques. For example, the acquisition unit can acquire the latest news articles by using the API of a news site. By subscribing to a news feed, it can acquire news that is updated in real time. By using scraping techniques, news text data can be automatically acquired from web pages. By combining these methods, the acquisition unit can efficiently collect diverse news data from a wide range of news sources. For example, by using an API, it can acquire regularly updated data from reliable news sources, and by subscribing to a news feed, it can acquire highly timely news in real time. Furthermore, by using scraping techniques, it can collect data from news sites that cannot be acquired through APIs or news feeds. As a result, the acquisition unit can quickly collect the latest and diverse news data, ensuring the freshness and diversity of information throughout the system. Furthermore, the acquisition unit can build a database that centrally manages the collected news data, allowing the analysis and instruction units to access it efficiently. This enables the acquisition unit to handle everything from news data collection to management in a consistent manner, improving the overall efficiency and reliability of the system.

[0064] The analysis unit analyzes the news text data acquired by the acquisition unit using natural language processing techniques. These techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the analysis unit uses morphological analysis to divide the news text data into individual words. It can also analyze the grammatical structure of the news text data using grammatical analysis. Furthermore, it can analyze the meaning of the news text data using semantic analysis. For example, morphological analysis divides the news text data into individual words and identifies the part of speech of each word. Grammatical analysis analyzes the grammatical structure of the news text data and identifies sentence components such as subject, predicate, and object. Semantic analysis analyzes the meaning of the news text data and understands the meaning of the sentence. By combining these analysis techniques, the analysis unit can analyze the news text data from multiple angles and gain a deeper understanding of the news content. For example, it can perform grammatical analysis based on data divided into individual words using morphological analysis to clarify the sentence structure. Furthermore, semantic analysis allows for an accurate understanding of the content and intent of the news. Based on these analysis results, the analysis unit can evaluate the importance and urgency of the news and determine the appropriate reading order and expression. The analysis unit can also identify proper nouns and technical terms contained in the news text data and provide information for generating appropriate pronunciation and intonation. As a result, the analysis unit can accurately and thoroughly analyze the content of the news, providing a foundation for the instruction and control units to give appropriate instructions and control.

[0065] The instruction unit issues instructions to the robot to read aloud based on the data analyzed by the analysis unit. For example, the instruction unit can instruct the robot to read the news fluently in Japanese or a foreign language. The instruction unit can also instruct the robot on the speed and intonation of reading the news. For example, the instruction unit can instruct the robot to add emotional expression when reading the news. For example, the instruction unit can instruct the robot to adjust the speed of reading the news. The instruction unit can instruct the robot to add emotional expression when reading the news. Based on the analysis results provided by the analysis unit, the instruction unit determines an appropriate reading method according to the content and importance of the news. For example, for urgent or important news, it can instruct the robot to read it quickly and add emotional expression to increase the impact on the audience. In addition, the instruction unit can facilitate audience comprehension by instructing appropriate intonation and emphasis according to the content of the news. Furthermore, the instruction unit can implement techniques to attract the audience's attention when reading the news. For example, it can instruct the robot to emphasize important points at the beginning of the news to attract the audience's attention. Furthermore, by incorporating appropriate pauses during news reading, the system makes it easier for viewers to process the information. The control unit provides these instructions to the robot in real time, ensuring that the news is read smoothly and effectively. This allows the control unit to deliver clear and engaging news to viewers.

[0066] The control unit controls a robot that speaks fluent Japanese or a foreign language based on instructions issued by the instruction unit. The control unit uses speech synthesis technology to control the robot that speaks fluent Japanese or a foreign language. Speech synthesis technology includes, but is not limited to, text-to-speech (TTS) and speech synthesis algorithms. For example, the control unit uses text-to-speech (TTS) technology to convert news text data into speech. The control unit can also use speech synthesis algorithms to control a robot that speaks fluent Japanese or a foreign language. For example, text-to-speech (TTS) technology converts news text data into speech, enabling the robot to speak fluently. Speech synthesis algorithms generate natural pronunciation and intonation based on news text data. The control unit aims to use these technologies to enable the robot to produce natural and easy-to-understand speech. For example, the control unit sets appropriate speech parameters according to the content of the news and controls the robot to read the news accurately and fluently. Furthermore, the control unit can also control the robot's movements and facial expressions to complement visual information and enhance the effectiveness of information transmission to the audience. For example, by changing the robot's facial expressions according to the news content, emotional expression to the viewer can be enhanced. Furthermore, by controlling the robot's movements, the viewer's attention can be captured, and the news content can be conveyed more effectively. The control unit performs these controls in real time, ensuring that the news is read smoothly and effectively. This allows the control unit to provide viewers with clear and engaging news.

[0067] The analysis unit can analyze news text data using natural language processing techniques. For example, the analysis unit can divide the news text data into words using morphological analysis. For example, the analysis unit can divide the news text data into words using morphological analysis and identify the part of speech of each word. The analysis unit can also analyze the grammatical structure of the news text data using grammatical analysis. For example, the analysis unit can analyze the grammatical structure of the news text data using grammatical analysis and identify sentence components such as subjects, predicates, and objects. Furthermore, the analysis unit can analyze the meaning of the news text data using semantic analysis. For example, the analysis unit can analyze the meaning of the news text data using semantic analysis and understand the meaning of the sentence. In this way, news text data can be accurately analyzed using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input news text data into a generating AI, which can then perform morphological analysis, grammatical analysis, and semantic analysis.

[0068] The control unit can control a robot that speaks fluent Japanese or a foreign language using speech synthesis technology. For example, the control unit can convert news text data into speech using text-to-speech (TTS) technology. For example, the control unit can convert news text data into speech using text-to-speech (TTS) technology, enabling the robot to speak fluently. The control unit can also control a robot that speaks fluent Japanese or a foreign language using speech synthesis algorithms. For example, the control unit can use a speech synthesis algorithm to generate natural pronunciation and intonation based on news text data. This allows the robot to speak fluent Japanese or a foreign language using speech synthesis technology. Speech synthesis technology includes, but is not limited to, text-to-speech (TTS) and speech synthesis algorithms. Some or all of the above-described processes in the control unit may be performed using, for example, AI, or not using AI. For example, the control unit can input news text data into a generating AI and have the generating AI perform speech synthesis.

[0069] The control unit has multiple language models and can read aloud news in foreign languages ​​by switching between them. The control unit has specific language models such as an English model, a Japanese model, and a French model. For example, the control unit can read aloud English news using the English model. The control unit can also read aloud Japanese news using the Japanese model. Furthermore, the control unit can read aloud French news using the French model. For example, the control unit can select and switch the appropriate language model according to the language of the news. This allows the control unit to read aloud news in foreign languages ​​by switching between multiple language models. The multiple language models include, but are not limited to, an English model, a Japanese model, and a French model. Some or all of the above processing in the control unit may be performed using AI, for example, or without AI. For example, the control unit can have a generating AI select an appropriate language model according to the language of the news, and have the generating AI perform the language model switching.

[0070] The news retrieval unit can estimate the user's emotions and adjust the timing of news retrieval based on the estimated emotions. For example, if the user is relaxed, the news retrieval unit can retrieve news immediately and provide the latest information in real time. For example, if the user is relaxed, the news retrieval unit can retrieve news immediately and provide the latest information in real time. The news retrieval unit can also slightly delay news retrieval if the user is stressed and wait until the user calms down. For example, if the user is stressed, the news retrieval unit can slightly delay news retrieval and wait until the user calms down. Furthermore, if the user is busy, the news retrieval unit can adjust the timing of news retrieval according to the user's emotions and provide it at an appropriate time. For example, if the user is busy, the news retrieval unit can adjust the timing of news retrieval according to the user's emotions and provide it at an appropriate time. In this way, news can be provided at an appropriate time by adjusting the timing of news retrieval according to the user's emotions. User emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the acquisition unit may be performed using AI, or not using AI. For example, the acquisition unit may input user emotion data into the generating AI and have the generating AI perform emotion estimation.

[0071] The news retrieval unit can filter news based on the user's areas of interest and past browsing history. For example, the retrieval unit can prioritize retrieving news categories that the user has frequently viewed in the past. The retrieval unit can also prioritize retrieving news related to the user's areas of interest, delaying other news. Furthermore, the retrieval unit can analyze the user's past browsing history and automatically select and retrieve news that is likely to be of interest. This allows the system to provide users with news that is highly relevant to them by filtering news based on their areas of interest and past browsing history. News filtering may be performed using, for example, a generative AI, or without one. For example, the retrieval unit can input the user's areas of interest and past browsing history into a generative AI, which can then perform news filtering.

[0072] The retrieval unit can obtain the latest information from news sources that are updated in real time when retrieving news. For example, the retrieval unit can use the API of a news site to retrieve the latest news articles in real time. The retrieval unit can also collect trending information from social media and retrieve news that includes the latest topics. For example, the retrieval unit can collect trending information from social media and retrieve news that includes the latest topics. Furthermore, the retrieval unit can receive push notifications from news distribution services and instantly retrieve the latest news. For example, the retrieval unit can receive push notifications from news distribution services and instantly retrieve the latest news. This ensures that the latest news is always provided by retrieving the latest information from news sources that are updated in real time. News retrieval may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the retrieval unit can input the API of a news site into a generative AI and have the generative AI retrieve the latest news articles.

[0073] The retrieval unit can estimate the user's emotions and determine the priority of news to retrieve based on the estimated emotions. For example, if the user is excited, the retrieval unit can prioritize retrieving positive news. For example, if the user is depressed, the retrieval unit can prioritize retrieving news that offers encouragement or hope. For example, if the user is depressed, the retrieval unit can prioritize retrieving news that offers encouragement or hope. Furthermore, if the user is relaxed, the retrieval unit can prioritize retrieving interesting feature articles or entertainment news. For example, if the user is relaxed, the retrieval unit can prioritize retrieving interesting feature articles or entertainment news. In this way, by determining the priority of news according to the user's emotions, the system can provide the user with the most suitable news. User emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, 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 acquisition unit may be performed using AI, for example, or without using AI. For example, the acquisition unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0074] The news acquisition unit can prioritize acquiring highly relevant news by considering the user's geographical location information when acquiring news. For example, the acquisition unit can prioritize acquiring local news related to the user's current location. For example, the acquisition unit can prioritize acquiring local news related to the user's current location. Furthermore, if the user is traveling, the acquisition unit can prioritize acquiring news related to the region they are visiting. For example, if the user is traveling, the acquisition unit can prioritize acquiring news related to the region they are visiting. In addition, based on the user's geographical location information, the acquisition unit can prioritize acquiring information on events and weather in nearby areas. For example, based on the user's geographical location information, the acquisition unit can prioritize acquiring information on events and weather in nearby areas. In this way, by acquiring news while considering the user's geographical location information, it is possible to provide the user with news that is highly relevant to them. News acquisition may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the acquisition unit can input the user's geographical location information into a generative AI, and have the generative AI acquire highly relevant news.

[0075] The acquisition unit can analyze the user's social media activity and acquire relevant news when acquiring news. For example, the acquisition unit can analyze the content of posts from accounts that the user follows on social media and acquire relevant news. The acquisition unit can also acquire news that the user might be interested in based on articles that the user has shared on social media. Furthermore, the acquisition unit can analyze the user's comments and reactions on social media and acquire news related to topics of interest. For example, the acquisition unit can analyze the user's comments and reactions on social media and acquire news related to topics of interest. In this way, by analyzing the user's social media activity and acquiring news, it is possible to provide the user with news that is of interest to them. News acquisition may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the acquisition unit can input the user's social media activity data into a generative AI and have the generative AI acquire relevant news.

[0076] The analysis unit can estimate the user's emotions and adjust the news analysis method based on the estimated emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and provide background and relevant information about the news. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and provide background and relevant information about the news. For example, if the user is in a hurry, the analysis unit can perform a concise analysis and provide only the important information. For example, if the user is in a hurry, the analysis unit can perform a concise analysis and provide only the important information. Furthermore, if the user is excited, the analysis unit can provide the analysis results using visually appealing graphics or infographics. For example, if the user is excited, the analysis unit can provide the analysis results using visually appealing graphics or infographics. In this way, by adjusting the news analysis method according to the user's emotions, the optimal analysis results can be provided to the user. User emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0077] The analysis unit can adjust the level of detail in its analysis based on the importance of the news. For example, for important news articles, the analysis unit can perform a detailed analysis and provide background and related information. For example, for important news articles, the analysis unit can perform a detailed analysis and provide background and related information. The analysis unit can also perform a concise analysis that focuses on the main points for general news articles. For example, for general news articles, the analysis unit can perform a concise analysis that focuses on the main points for general news articles. Furthermore, for breaking news, the analysis unit can perform a rapid analysis and immediately provide important information. For example, for breaking news, the analysis unit can perform a rapid analysis and immediately provide important information. In this way, by adjusting the level of detail in the analysis based on the importance of the news, a detailed analysis can be provided for important news. The evaluation of news importance may be performed using, for example, a generative AI, or it may be performed without using a generative AI. For example, the analysis unit can input the news importance into a generative AI and have the generative AI perform the importance evaluation.

[0078] The analysis unit can apply different analysis algorithms depending on the news category when analyzing news. For example, for political news, the analysis unit can apply an analysis algorithm that takes into account the political background and impact. For example, for economic news, the analysis unit can apply an analysis algorithm that takes into account economic indicators and market trends. For example, for sports news, the analysis unit can apply an analysis algorithm that takes into account match results and player performance. In this way, by applying different analysis algorithms depending on the news category, the system can provide optimal analysis results for each category. The classification of news categories may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the news categories into a generative AI and have the generative AI perform the category classification.

[0079] The analysis unit can estimate the user's emotions and adjust the display method of the news analysis results based on the estimated user emotions. For example, if the user is tense, the analysis unit can provide a simple and easy-to-read display method. For example, if the user is tense, the analysis unit can provide a simple and easy-to-read display method. For example, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. For example, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. For example, if the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. In this way, by adjusting the display method of the news analysis results according to the user's emotions, the optimal display method can be provided for the user. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input user emotion data into a generating AI, which can then perform emotion estimation.

[0080] The analysis unit can determine the priority of news analysis based on the publication date of the news. For example, the analysis unit can prioritize the analysis of the latest news articles and provide the information immediately. The analysis unit can also postpone the analysis of older news articles. Furthermore, the analysis unit can prioritize the analysis of breaking news regardless of the publication date. In this way, by determining the priority of analysis based on the publication date of the news, the latest news can be prioritized. The publication date of the news may be determined using, for example, a generative AI, or it may be done without using a generative AI. For example, the analysis unit can input the publication date of the news into a generative AI and have the generative AI determine the publication date.

[0081] The analysis unit can adjust the order of analysis based on the relevance of the news articles. For example, the analysis unit can prioritize analyzing news related to the user's areas of interest. The analysis unit can also prioritize analyzing highly relevant news based on the user's past browsing history. Furthermore, if the content of one news article is related to other news articles, the analysis unit can analyze related news articles together. This allows the analysis unit to prioritize the analysis of highly relevant news articles by adjusting the order of analysis based on the relevance of the news articles. The evaluation of news relevance may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input the relevance of the news articles into a generative AI and have the generative AI perform the relevance evaluation.

[0082] The instruction unit can estimate the user's emotions and adjust the instructions given to the robot based on the estimated emotions. For example, if the user is relaxed, the instruction unit can give detailed instructions and instruct the robot to read them carefully. If the user is in a hurry, the instruction unit can give concise instructions and instruct the robot to read them to the point. Furthermore, if the user is excited, the instruction unit can give instructions with visually appealing effects and instruct the robot to read them in an engaging way. In this way, by adjusting the instructions given to the robot according to the user's emotions, the optimal instructions for the user can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the instruction unit may be performed using AI, or not using AI. For example, the instruction unit may input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0083] The instruction unit can adjust the level of detail in instructions given to the robot based on the importance of the news. For example, for important news articles, the instruction unit can give detailed instructions and instruct the robot to read them carefully. For example, for important news articles, the instruction unit can give detailed instructions and instruct the robot to read them carefully. For general news articles, the instruction unit can give concise instructions and instruct the robot to read them concisely. For example, for general news articles, the instruction unit can give concise instructions and instruct the robot to read them concisely. Furthermore, for breaking news, the instruction unit can give quick instructions and instruct the robot to read them immediately. For example, for breaking news, the instruction unit can give quick instructions and instruct the robot to read them immediately. In this way, by adjusting the level of detail in instructions based on the importance of the news, detailed instructions can be given for important news. The evaluation of news importance may be performed using, for example, generative AI, or without using generative AI. For example, the instruction unit can input the importance level of news items into the generating AI, which can then perform the importance evaluation.

[0084] The instruction unit can apply different instruction algorithms to the robot depending on the news category. For example, for political news, the instruction unit can apply an instruction algorithm that takes into account the political background and influence. For economic news, the instruction unit can also apply an instruction algorithm that takes into account economic indicators and market trends. Furthermore, for sports news, the instruction unit can apply an instruction algorithm that takes into account match results and player performance. By applying different instruction algorithms depending on the news category, the optimal instructions can be given for each category. The classification of news categories may be performed using, for example, a generative AI, or without using a generative AI. For example, the instruction unit can input the news categories into a generative AI, and have the generative AI perform the category classification.

[0085] The instruction unit can estimate the user's emotions and determine the priority of instructions to the robot based on the estimated emotions. For example, if the user is excited, the instruction unit can prioritize positive news. For example, if the user is excited, the instruction unit can prioritize positive news. For example, if the user is depressed, the instruction unit can prioritize encouraging or hopeful news. For example, if the user is depressed, the instruction unit can prioritize encouraging or hopeful news. For example, if the user is relaxed, the instruction unit can prioritize interesting feature articles or entertainment news. For example, if the user is relaxed, the instruction unit can prioritize interesting feature articles or entertainment news. In this way, by determining the priority of instructions to the robot according to the user's emotions, the most suitable news for the user can be provided preferentially. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the instruction unit may be performed using AI, for example, or without AI. For example, the instruction unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0086] The instruction unit can prioritize instructions to the robot based on the timing of news submission. For example, the instruction unit can prioritize the latest news articles and have them read aloud immediately. The instruction unit can also postpone instructions for older news articles. Furthermore, the instruction unit can prioritize instructions for breaking news regardless of the submission timing. This allows the robot to receive the latest news preferentially by prioritizing instructions based on the timing of news submission. The timing of news submission can be determined using, for example, a generative AI, or without using a generative AI. For example, the instruction unit can input the timing of news submission into a generative AI, which can then determine the timing.

[0087] The instruction unit can adjust the order of instructions given to the robot based on the relevance of the news. For example, the instruction unit can prioritize giving instructions to news related to the user's areas of interest. The instruction unit can also prioritize giving instructions to highly relevant news based on the user's past browsing history. Furthermore, if the content of one news item is related to another, the instruction unit can group related news items together and give instructions to those items together. This allows the robot to prioritize the provision of highly relevant news by adjusting the order of instructions based on the relevance of the news. The evaluation of news relevance may be performed using, for example, a generative AI, or without using a generative AI. For example, the instruction unit can input the relevance of the news into a generative AI and have the generative AI perform the relevance evaluation.

[0088] The control unit can estimate the user's emotions and adjust the robot's reading method based on the estimated emotions. For example, if the user is relaxed, the control unit can read at a relaxed pace. The control unit can also read quickly and concisely if the user is in a hurry. Furthermore, if the user is excited, the control unit can add visually appealing effects to the reading. By adjusting the robot's reading method according to the user's emotions, the optimal reading can be provided to the user. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input user emotion data into a generating AI, which can then perform emotion estimation.

[0089] The control unit can adjust the level of detail in the reading of news based on its importance when controlling the robot. For example, the control unit can provide detailed readings of important news articles, including background and related information. The control unit can also provide concise readings of general news articles, focusing on the main points. Furthermore, the control unit can provide rapid readings of breaking news, immediately providing important information. This allows for detailed readings of important news by adjusting the level of detail in the reading based on its importance. The evaluation of news importance may be performed using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the news importance into a generative AI, which can then perform the importance evaluation.

[0090] The control unit can apply different reading algorithms depending on the news category when controlling the robot. For example, for political news, the control unit can apply a reading algorithm that takes into account the political background and impact. For economic news, the control unit can also apply a reading algorithm that takes into account economic indicators and market trends. Furthermore, for sports news, the control unit can apply a reading algorithm that takes into account match results and player performance. By applying different reading algorithms depending on the news category, the optimal reading can be provided for each category. The classification of news categories may be performed using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the news categories into a generative AI and have the generative AI perform the category classification.

[0091] The control unit can estimate the user's emotions and determine the priority of the robot's reading based on the estimated emotions. For example, if the user is excited, the control unit can prioritize reading positive news. Similarly, if the user is depressed, the control unit can prioritize reading encouraging or hopeful news. Furthermore, if the user is relaxed, the control unit can prioritize reading interesting feature articles or entertainment news. This allows the robot to prioritize the reading based on the user's emotions, thereby providing the user with the most relevant news. The estimation of user emotions is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the control unit may be performed using AI, for example, or without AI. For example, the control unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0092] The control unit can determine the reading priority based on the timing of news submission when controlling the robot. For example, the control unit can prioritize reading the latest news articles to provide information immediately. The control unit can also postpone reading older news articles. Furthermore, the control unit can prioritize reading breaking news regardless of the submission timing. This allows the robot to prioritize reading the latest news by determining the reading priority based on the timing of news submission. The timing of news submission can be determined using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the timing of news submission into a generative AI, which can then determine the timing.

[0093] The control unit can adjust the reading order of news articles based on their relevance when controlling the robot. For example, the control unit can prioritize reading news articles related to the user's areas of interest. The control unit can also prioritize reading highly relevant news articles based on the user's past browsing history. Furthermore, if the content of one news article is related to another, the control unit can read related news articles together. This allows the system to prioritize the provision of highly relevant news articles by adjusting the reading order based on their relevance. The evaluation of news relevance may be performed using, for example, a generative AI, or without using a generative AI. For example, the control unit can input the news relevance into a generative AI and have the generative AI perform the relevance evaluation.

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

[0095] The news program announcement robot system can estimate the user's emotions and customize the news content based on those emotions. For example, if the user is stressed, it can select news that helps them relax. If the user is excited, it can prioritize providing positive news. Furthermore, if the user is depressed, it can select news that offers encouragement and hope. This allows the system to provide the most appropriate news according to the user's emotions.

[0096] The news program announcement robot system can analyze a user's past news viewing history and customize news based on the user's interests. For example, if a user has frequently viewed economic news in the past, economic news can be prioritized. Similarly, if a user is interested in sports news, the system can provide the latest sports news. Furthermore, if a user is interested in news from a specific region, news from that region can be prioritized. This allows the system to provide the most relevant news according to the user's interests.

[0097] The news program announcement robot system can estimate the user's emotions and adjust the news reading speed based on those emotions. For example, if the user is relaxed, the news can be read at a leisurely pace. If the user is in a hurry, the news can be read quickly. Furthermore, if the user is excited, the news can be read in an energetic tone. This allows the system to provide the optimal reading speed according to the user's emotions.

[0098] The news program announcement robot system can adjust the order in which news is read based on its importance. For example, it can read breaking news or important news first, while general news can be postponed. Furthermore, the order of news can be customized according to the user's interests, allowing important news to be delivered preferentially.

[0099] The news program announcement robot system can estimate the user's emotions and filter the news content based on those emotions. For example, if the user is stressed, it can avoid negative news. If the user is relaxed, it can prioritize providing positive news. Furthermore, if the user is excited, it can provide entertainment news. This allows the system to deliver the most relevant news according to the user's emotions.

[0100] The news program announcement robot system can customize news based on the user's geographical location. For example, if the user is in a specific region, it can prioritize news related to that region. If the user is traveling, it can also provide news relevant to their destination. Furthermore, it can provide local news based on the user's current location. This allows the system to deliver the most relevant news according to the user's geographical location.

[0101] The news program announcement robot system can estimate the user's emotions and adjust the tone of the news reading based on those emotions. For example, if the user is relaxed, the news can be read in a calm tone. If the user is in a hurry, the news can be read in a clear and concise tone. Furthermore, if the user is excited, the news can be read in an energetic tone. This allows the system to provide the optimal reading tone according to the user's emotions.

[0102] The news program announcement robot system can apply different reading algorithms depending on the news category. For example, for political news, it can apply a reading algorithm that takes into account the political background and impact. For economic news, it can apply a reading algorithm that takes into account economic indicators and market trends. Furthermore, for sports news, it can apply a reading algorithm that takes into account match results and player performance. This allows the system to provide the most optimal reading for each news category.

[0103] The news program announcement robot system can estimate the user's emotions and adjust how the news is displayed based on those emotions. For example, if the user is relaxed, it can provide a display method that includes detailed information. If the user is in a hurry, it can provide a concise display method that gets straight to the point. Furthermore, if the user is excited, it can provide a display method that uses visually appealing graphics. This allows the system to provide the most appropriate display method according to the user's emotions.

[0104] The news program announcement robot system can prioritize news based on when it was submitted. For example, it can prioritize providing the latest news articles and deliver information immediately. It can also postpone older news articles. Furthermore, it can prioritize breaking news regardless of when it was submitted. This allows the system to provide the most relevant news based on when it was submitted.

[0105] The following briefly describes the processing flow for example form 2.

[0106] Step 1: The acquisition unit retrieves news text data. This news text data includes online news, newspaper articles, breaking news, etc. The acquisition unit uses news site APIs to retrieve news text data. It can also retrieve news text data by subscribing to news feeds. Furthermore, it can automatically retrieve news text data from web pages using scraping techniques. Step 2: The analysis unit analyzes the news text data acquired by the acquisition unit using natural language processing techniques. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis. For example, morphological analysis is used to divide the news text data into words, grammatical analysis is used to analyze the grammatical structure, and semantic analysis is used to analyze the meaning of the news text data. Step 3: The instruction unit issues instructions to the robot to read aloud based on the data analyzed by the analysis unit. The instruction unit instructs the robot to read the news aloud in fluent Japanese or a foreign language. It can also issue instructions to adjust the reading speed, intonation, and emotional expression of the news. Step 4: The control unit controls the robot, which speaks fluent Japanese and foreign languages, based on instructions issued by the instruction unit. The control unit uses speech synthesis technology to convert news text data into speech, enabling the robot to speak fluently. Speech synthesis technology includes text-to-speech (TTS) and speech synthesis algorithms.

[0107] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires 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.

[0108] 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.

[0109] 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.

[0110] Each of the multiple elements described above, including the acquisition unit, analysis unit, instruction unit, and control unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the acquisition unit acquires news text data using a news site API via the communication I / F 44 of the smart device 14. The analysis unit analyzes the news text data using natural language processing technology by the specific processing unit 290 of the data processing unit 12. The instruction unit issues instructions to the robot to read aloud based on the analysis results by the specific processing unit 290 of the data processing unit 12. The control unit controls the robot using speech synthesis technology by the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.).

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires 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.

[0124] 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.

[0125] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is 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.

[0126] Each of the multiple elements described above, including the acquisition unit, analysis unit, instruction unit, and control unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit acquires news text data using a news site API via the communication I / F 44 of the smart glasses 214. The analysis unit analyzes the news text data using natural language processing technology by the specific processing unit 290 of the data processing unit 12. The instruction unit issues instructions to the robot to read aloud based on the analysis results by the specific processing unit 290 of the data processing unit 12. The control unit controls the robot using speech synthesis technology by the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0142] Each of the multiple elements described above, including the acquisition unit, analysis unit, instruction unit, and control unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit acquires news text data using a news site API via the communication I / F 44 of the headset terminal 314. The analysis unit analyzes the news text data using natural language processing technology by the specific processing unit 290 of the data processing unit 12. The instruction unit issues instructions to the robot to read aloud based on the analysis results by the specific processing unit 290 of the data processing unit 12. The control unit controls the robot using speech synthesis technology by the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

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

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.).

[0156] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the 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.

[0157] 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.

[0158] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is 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.

[0159] Each of the multiple elements described above, including the acquisition unit, analysis unit, instruction unit, and control unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit acquires news text data using a news site API via the robot 414's communication I / F 44. The analysis unit analyzes the news text data using natural language processing technology by the specific processing unit 290 of the data processing unit 12. The instruction unit issues instructions to the robot to read aloud based on the analysis results by the specific processing unit 290 of the data processing unit 12. The control unit controls the robot 414 using speech synthesis technology by the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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."

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] (Note 1) The acquisition unit retrieves text data for news articles, An analysis unit analyzes the text data acquired by the acquisition unit, Based on the data analyzed by the aforementioned analysis unit, the instruction unit issues instructions to the robot to read aloud, The system includes a control unit that controls a robot that speaks fluent Japanese or a foreign language based on instructions issued by the aforementioned instruction unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze news text data using natural language processing techniques. The system described in Appendix 1, characterized by the features described herein. (Note 3) The control unit, Using speech synthesis technology, we control robots that speak fluent Japanese and foreign languages. The system described in Appendix 1, characterized by the features described herein. (Note 4) The control unit, It has multiple language models, and by switching between them, it can also read out news in foreign languages. The system described in Appendix 1, characterized by the features described herein. (Note 5) The acquisition unit is, It estimates the user's sentiment and adjusts the timing of news retrieval based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, When retrieving news, filtering is performed based on the user's areas of interest and past browsing history. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, When retrieving news, the latest information is obtained from news sources that are updated in real time. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, It estimates the user's sentiment and determines the priority of news to retrieve based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, When retrieving news, the system prioritizes retrieving highly relevant news by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, When retrieving news, the system analyzes the user's social media activity and retrieves relevant news. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, We estimate user sentiment and adjust news analysis methods based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, When analyzing news, adjust the level of detail based on the importance of the news. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, When analyzing news, different analysis algorithms are applied depending on the news category. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, It estimates the user's sentiment and adjusts how news analysis results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing news, we determine the priority of analysis based on when the news was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, When analyzing news, the order of analysis is adjusted based on the relevance of the news items. The system described in Appendix 1, characterized by the features described herein. (Note 17) The indicator unit is, It estimates the user's emotions and adjusts the instructions given to the robot based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The indicator unit is, When giving instructions to the robot, adjust the level of detail of the instructions based on the importance of the news item. The system described in Appendix 1, characterized by the features described herein. (Note 19) The indicator unit is, When giving instructions to the robot, different instruction algorithms are applied depending on the news category. The system described in Appendix 1, characterized by the features described herein. (Note 20) The indicator unit is, It estimates the user's emotions and prioritizes instructions to the robot based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The indicator unit is, When giving instructions to the robot, the priority of the instructions is determined based on when the news should be submitted. The system described in Appendix 1, characterized by the features described herein. (Note 22) The indicator unit is, When giving instructions to the robot, the order of instructions is adjusted based on the relevance of the news. The system described in Appendix 1, characterized by the features described herein. (Note 23) The control unit, It estimates the user's emotions and adjusts the robot's reading method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The control unit, When controlling the robot, adjust the level of detail in the reading based on the importance of the news item. The system described in Appendix 1, characterized by the features described herein. (Note 25) The control unit, When controlling the robot, different reading algorithms are applied depending on the news category. The system described in Appendix 1, characterized by the features described herein. (Note 26) The control unit, The system estimates the user's emotions and determines the priority of the robot's speech based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The control unit, When controlling the robot, the priority of reading news is determined based on when the news was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 28) The control unit, When controlling the robot, adjust the reading order based on the relevance of the news items. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0179] 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. The acquisition unit retrieves text data for news articles, An analysis unit analyzes the text data acquired by the acquisition unit, Based on the data analyzed by the aforementioned analysis unit, the instruction unit issues instructions to the robot to read aloud, The system includes a control unit that controls a robot that speaks fluent Japanese or a foreign language based on instructions issued by the aforementioned instruction unit. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze news text data using natural language processing techniques. The system according to feature 1.

3. The control unit, Using speech synthesis technology, we control robots that speak fluent Japanese and foreign languages. The system according to feature 1.

4. The control unit, It has multiple language models, and by switching between them, it can also read out news in foreign languages. The system according to feature 1.

5. The acquisition unit is, It estimates the user's sentiment and adjusts the timing of news retrieval based on the estimated user sentiment. The system according to feature 1.

6. The acquisition unit is, When retrieving news, filtering is performed based on the user's areas of interest and past browsing history. The system according to feature 1.

7. The acquisition unit is, When retrieving news, the latest information is obtained from news sources that are updated in real time. The system according to feature 1.

8. The acquisition unit is, It estimates the user's sentiment and determines the priority of news to retrieve based on the estimated user sentiment. The system according to feature 1.

9. The acquisition unit is, When retrieving news, the system prioritizes retrieving highly relevant news by considering the user's geographical location. The system according to feature 1.

10. The acquisition unit is, When retrieving news, the system analyzes the user's social media activity and retrieves relevant news. The system according to feature 1.

Images