system

Abstract

The system according to this embodiment aims to reduce the costs and time required for news media to produce video content. [Solution] The system according to the embodiment comprises an analysis unit, a selection unit, and a generation unit. The analysis unit analyzes news articles in text format. The selection unit selects relevant video and audio based on the results analyzed by the analysis unit. The generation unit automatically generates captions based on the video and audio selected by the selection unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is room for improvement in reducing the costs and time involved in news media video production.

[0005] The system according to the embodiment aims to reduce the costs and time involved in news media video production.

Means for Solving the Problems

[0006] [[ID=I46]]The system according to the embodiment includes an analysis unit, a selection unit, and a generation unit. The analysis unit analyzes news articles in text format. The selection unit selects relevant videos and voices based on the results analyzed by the analysis unit. The generation unit automatically generates subtitles based on the videos and voices selected by the selection unit.

Effects of the Invention

[0007] The system according to this embodiment can reduce the cost and time required for news media to produce video. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An embodiment of the present invention provides an automated video news generation system that analyzes a news article in text format, selects relevant video, audio, and captions, and automatically generates video news. This system allows news media to reduce the cost and time required for video production and to deliver news quickly and efficiently. For example, the automated video news generation system analyzes a news article in text format using natural language processing technology. It analyzes the content of the news article in detail and extracts important keywords and phrases. For example, if the news article contains keywords such as "earthquake" or "disaster," it selects relevant video and audio based on these keywords. Next, it automatically selects relevant video and audio based on the analysis results. For example, if the news article contains "earthquake," it selects video of the earthquake and audio from the disaster area. In this case, the quality and relevance of the video and audio are considered during the selection process. Furthermore, it automatically generates captions and places them in appropriate positions. For example, it displays the title of the news article and important information as captions. In this case, the font, color, size, etc. of the captions are automatically adjusted and placed in a visually easy-to-read format. This automated video news generation system allows news media to reduce production time by 80% and video production costs by 50% compared to traditional manual methods. It can also double news productivity. For example, news media can provide high-quality visual content to viewers, improving viewer satisfaction. This automated video news generation system enables news media to deliver news quickly and efficiently.

[0029] The video news automatic generation system according to this embodiment comprises an analysis unit, a selection unit, and a generation unit. The analysis unit analyzes news articles in text format. The analysis unit analyzes the content of news articles in detail, for example, using natural language processing technology, and extracts important keywords and phrases. If the news article contains keywords such as "earthquake" or "disaster," the analysis unit selects relevant video and audio based on these keywords. The selection unit selects relevant video and audio based on the results of the analysis performed by the analysis unit. If the news article contains "earthquake," the selection unit selects video of the earthquake and audio from the disaster area. The selection unit makes selections considering the quality and relevance of the video and audio. For example, the selection unit makes selections based on the resolution of the video, the clarity of the audio, and the degree of agreement with the content of the news article. The generation unit automatically generates captions based on the video and audio selected by the selection unit. For example, the generation unit displays the title of the news article and important information as captions. The generation unit automatically adjusts the font, color, and size of the on-screen text and arranges it in a visually easy-to-read format. For example, the generation unit improves visibility by increasing the font size and brightening the color of the on-screen text. As a result, the video news automatic generation system according to this embodiment can analyze a news article in text format, select relevant video, audio, and on-screen text, and automatically generate video news.

[0030] The analysis unit analyzes news articles in text format. For example, it uses natural language processing techniques to analyze the content of news articles in detail and extract important keywords and phrases. Specifically, it utilizes natural language processing techniques such as morphological analysis, dependency structure analysis, and named entity recognition to understand the context and meaning of news articles. For example, it uses morphological analysis to segment the words in the news article and identify the part of speech of each word. It uses dependency structure analysis to analyze the relationships between words in a sentence and grasp the sentence structure. It uses named entity recognition to extract proper nouns such as place names, personal names, and organization names contained in the news article. Based on these analysis results, it understands the content of the news article in detail and extracts important keywords and phrases. For example, if the news article contains keywords such as "earthquake" or "disaster," it provides information for selecting relevant videos and audio based on these keywords. By accurately analyzing the content of news articles, the analysis unit provides a foundation for the selection and generation units to select and generate appropriate videos, audio, and captions. Furthermore, the analysis unit also performs sentiment analysis on news articles to grasp the tone and emotions of the articles. For example, it distinguishes between positive and negative news articles and provides information for selecting appropriate video and audio content. In this way, the analysis unit can analyze the content of news articles from multiple angles and provide a foundation for the selection and generation units to automatically generate high-quality video news.

[0031] The selection unit selects relevant video and audio based on the results analyzed by the analysis unit. For example, if a news article contains the word "earthquake," the selection unit will select earthquake video and audio from the affected area. Specifically, the selection unit searches for relevant content from video and audio databases based on keywords and phrases provided by the analysis unit. The selection unit makes selections considering the quality and relevance of the video and audio. For example, it selects based on the video resolution, audio clarity, and degree of relevance to the content of the news article. The selection unit confirms that the video resolution is high and the audio is clear, selecting content that is easy for viewers to see and hear. The selection unit also evaluates the degree of relevance to the content of the news article and selects the video and audio that are most appropriate for the article's content. For example, by selecting earthquake video and audio from the affected area for a news article about an earthquake, the content of the news can be accurately conveyed to the viewer. Furthermore, the selection unit checks the copyright and usage rights of the video and audio to select appropriate content. As a result, the selection unit can select the video and audio that are most appropriate for the content of the news article and provide viewers with high-quality video news.

[0032] The generation unit automatically generates captions based on the video and audio selected by the selection unit. For example, the generation unit displays news article titles and important information as captions. Specifically, the generation unit analyzes the content of news articles and extracts information important to the viewer. For example, it extracts the news article title, main keywords, and important phrases, and displays these as captions. The generation unit automatically adjusts the font, color, and size of the captions, arranging them in a visually appealing manner. For example, it improves visibility by increasing the font size and brightness of the captions. Furthermore, the generation unit adjusts the timing and position of the captions to create a sense of unity with the video and audio. For example, it displays captions in sync with important information in the news article to effectively convey information to the viewer. In addition, the generation unit adds animations and effects to the captions to enhance their visual appeal. For example, it adds animations such as fade-in and fade-out to attract the viewer's attention. This allows the generation unit to automatically generate visually appealing and effectively informative captions based on the video and audio selected by the selection unit.

[0033] The analysis unit can analyze the content of news articles in detail. For example, the analysis unit can use natural language processing technology to delve deeper into the content of news articles and understand the context. For example, the analysis unit can analyze the relationships between paragraphs and sentences in news articles and extract important information. For example, by analyzing the content of news articles in detail, the analysis unit can grasp background information and related information about the news articles. This allows for more accurate analysis results by analyzing the content of news articles in detail. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of news articles into a generating AI, which can then understand the context and extract important information.

[0034] The extraction unit can extract important keywords and phrases. For example, the extraction unit extracts important keywords and phrases from news articles using natural language processing technology. For example, the extraction unit extracts keywords and phrases based on frequency of occurrence or contextual importance. For example, the extraction unit extracts particularly important information from news articles and performs analysis based on it. By doing so, the accuracy of news article analysis can be improved by extracting important keywords and phrases. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of a news article into a generating AI, and the generating AI can extract important keywords and phrases.

[0035] The quality evaluation unit can select video and audio by considering their quality and relevance. For example, the quality evaluation unit selects video and audio based on video resolution, audio clarity, and degree of relevance to the content of the news article. For example, the quality evaluation unit evaluates the quality of video and audio and selects the one that is most suitable for the content of the news article. For example, the quality evaluation unit evaluates how well the content of the video and audio matches the content of the news article. By selecting video and audio by considering their quality and relevance, more appropriate video and audio can be selected. Some or all of the above processing in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation unit can input the video and audio quality evaluation into a generating AI, and the generating AI can perform the quality evaluation.

[0036] The adjustment unit can automatically adjust the font, color, size, etc., of the on-screen text. For example, the adjustment unit can improve visibility by increasing the font size and brightening the color of the on-screen text. For example, the adjustment unit can adjust the size of the on-screen text to ensure readability on the screen. For example, the adjustment unit can adjust the color of the on-screen text to match the background and position it in a visually easy-to-read manner. In this way, by automatically adjusting the font, color, size, etc., the on-screen text can be generated in a visually easy-to-read manner. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input the adjustments for the font, color, and size of the on-screen text into a generating AI, and the generating AI can perform the adjustments.

[0037] The analysis unit can optimize its analysis algorithm by referring to past news article data when analyzing news articles. For example, the analysis unit can identify frequently occurring keywords and phrases based on past news article data and reflect them in the analysis algorithm. For example, the analysis unit can extract patterns related to specific topics from past news article data and adjust the analysis algorithm. For example, the analysis unit can analyze past news article data and build a feedback loop to improve the accuracy of the analysis algorithm. This allows for improved analysis accuracy by optimizing the analysis algorithm by referring to past news article data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past news article data into a generating AI and have the generating AI optimize the analysis algorithm.

[0038] The analysis unit can apply different analysis methods to each category of news articles when analyzing them. For example, in the case of political news, the analysis unit can apply methods specialized in analyzing technical terms and proper nouns. For example, in the case of sports news, the analysis unit can apply methods that focus on analyzing match results and player names. For example, in the case of entertainment news, the analysis unit can apply methods that analyze celebrity names and work titles. By applying different analysis methods to each category of article, the accuracy of the analysis can be improved. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input news article category information into a generating AI, and the generating AI can apply category-specific analysis methods.

[0039] The analysis unit can improve the accuracy of its analysis by considering the source information of news articles. For example, the analysis unit can prioritize the analysis of news articles from highly reliable sources to improve accuracy. For example, the analysis unit can consider the bias of the source and reflect it in the analysis results. For example, the analysis unit can evaluate the past reliability of the source and incorporate it into the analysis algorithm. By improving the accuracy of the analysis by considering the source information of the articles, more accurate analysis results can be obtained. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the source information of news articles into a generating AI, and the generating AI can improve the accuracy of the analysis.

[0040] The analysis unit can improve the accuracy of its analysis by referring to related literature when analyzing news articles. For example, the analysis unit can supplement background information on news articles based on related literature to improve the accuracy of its analysis. For example, the analysis unit can reflect data obtained from related literature into its analysis algorithm. For example, the analysis unit can refer to related literature and apply analysis methods to gain a deeper understanding of the content of news articles. By improving the accuracy of the analysis by referring to related literature, more accurate analysis results can be obtained. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input related literature for news articles into a generating AI, and the generating AI can improve the accuracy of the analysis.

[0041] The selection unit can optimize its selection algorithm by referring to past selection data when selecting video and audio. For example, the selection unit can identify frequently occurring video and audio patterns based on past selection data and reflect them in the selection algorithm. For example, the selection unit can extract video and audio related to a specific topic from past selection data and adjust the selection algorithm. For example, the selection unit can analyze past selection data and build a feedback loop to improve the accuracy of the selection algorithm. This allows for improved selection accuracy by optimizing the selection algorithm by referring to past selection data. Some or all of the above processes in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input past selection data into a generating AI, and the generating AI can optimize the selection algorithm.

[0042] The selection unit can apply different selection methods to each category of news article when selecting video and audio. For example, in the case of political news, the selection unit can apply a method for selecting specialized video and audio. For example, in the case of sports news, the selection unit can apply a method for selecting match highlights and athlete interviews. For example, in the case of entertainment news, the selection unit can apply a method for selecting celebrity interviews and event footage. By applying different selection methods to each category of news article, the selection accuracy can be improved. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input news article category information into a generating AI, and the generating AI can apply a category-specific selection method.

[0043] The selection unit can improve the accuracy of its selection process by considering the source information of the video and audio when selecting them. For example, the selection unit can prioritize selecting video and audio from highly reliable sources to improve accuracy. For example, the selection unit can consider the bias of the source and reflect it in the selection results. For example, the selection unit can evaluate the past reliability of the source and incorporate it into the selection algorithm. By improving the accuracy of selection by considering the source information of the video and audio, more accurate selection results can be obtained. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the source information of the video and audio into a generating AI, and the generating AI can improve the accuracy of the selection.

[0044] The selection unit can improve the accuracy of its selection by referring to the metadata of the relevant video and audio when selecting video and audio. For example, the selection unit improves the accuracy of its selection based on the metadata of the relevant video and audio. For example, the selection unit reflects the information obtained from the metadata into the selection algorithm. For example, the selection unit makes the selection results more accurate by referring to the metadata of the relevant video and audio. In this way, by improving the accuracy of the selection by referring to the metadata of the relevant video and audio, more accurate selection results can be obtained. Some or all of the above processing in the selection unit may be performed using AI, for example, or without using AI. For example, the selection unit can input the metadata of the video and audio into a generating AI, and the generating AI can improve the accuracy of the selection.

[0045] The generation unit can optimize its generation algorithm by referring to past generation data when generating text overlays. For example, the generation unit can identify frequently occurring text overlay patterns based on past generation data and reflect them in the generation algorithm. For example, the generation unit can extract text overlays related to specific topics from past generation data and adjust the generation algorithm. For example, the generation unit can analyze past generation data and build a feedback loop to improve the accuracy of the generation algorithm. This allows for improved generation accuracy by optimizing the generation algorithm by referring to past generation data. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input past generation data into a generation AI and have the generation AI optimize the generation algorithm.

[0046] The generation unit can apply different generation methods to each category of news article when generating captions. For example, in the case of political news, the generation unit can apply a method to generate specialized captions. For example, in the case of sports news, the generation unit can apply a method to generate captions that focus on displaying match results and player names. For example, in the case of entertainment news, the generation unit can apply a method to generate captions that display celebrity names and work titles. By applying different generation methods to each category of news article, the generation accuracy can be improved. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input news article category information into a generation AI, and the generation AI can apply a category-specific generation method.

[0047] The generation unit can improve the accuracy of text generation by considering the text display position information. For example, the generation unit automatically determines the optimal display position based on the text display position information. For example, the generation unit places the text in a highly visible position, taking into account the text display position information. For example, the generation unit refers to the text display position information and places it so that it does not overlap with other elements. By improving the accuracy of generation by considering the text display position information, more accurate generation results can be obtained. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the text display position information into a generation AI, and the generation AI can improve the accuracy of generation.

[0048] The generation unit can improve the accuracy of its generation by referring to the metadata of related subtitles when generating subtitles. For example, the generation unit improves the accuracy of its generation based on the metadata of related subtitles. For example, the generation unit reflects the information obtained from the metadata into the generation algorithm. For example, the generation unit makes the generation result more accurate by referring to the metadata of related subtitles. In this way, a more accurate generation result can be obtained by improving the accuracy of generation by referring to the metadata of related subtitles. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI. For example, the generation unit can input the metadata of the subtitles into a generation AI, and the generation AI can improve the accuracy of the generation.

[0049] The analysis unit can optimize its analysis algorithm by referring to past analysis data when analyzing news articles. For example, the analysis unit can identify frequently occurring keywords and phrases based on past analysis data and reflect them in the analysis algorithm. For example, the analysis unit can extract patterns related to specific topics from past analysis data and adjust the analysis algorithm. For example, the analysis unit can analyze past analysis data and build a feedback loop to improve the accuracy of the analysis algorithm. This allows for improved analysis accuracy by optimizing the analysis algorithm by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis data into a generating AI and have the generating AI optimize the analysis algorithm.

[0050] The analysis unit can improve the accuracy of its analysis by considering the source information of news articles. For example, the analysis unit can prioritize the analysis of news articles from reliable sources to improve accuracy. For example, the analysis unit can consider the bias of the source and reflect it in the analysis results. For example, the analysis unit can evaluate the past reliability of the source and incorporate it into the analysis algorithm. By improving the accuracy of the analysis by considering the source information of the articles, more accurate analysis results can be obtained. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the source information of news articles into a generating AI, and the generating AI can improve the accuracy of the analysis.

[0051] The extraction unit can optimize its extraction algorithm by referring to past extraction data when extracting keywords and phrases. For example, the extraction unit can identify frequently occurring keywords and phrases based on past extraction data and reflect them in the extraction algorithm. For example, the extraction unit can extract patterns related to specific topics from past extraction data and adjust the extraction algorithm. For example, the extraction unit can analyze past extraction data and build a feedback loop to improve the accuracy of the extraction algorithm. This allows for improved extraction accuracy by optimizing the extraction algorithm by referring to past extraction data. Some or all of the above processes in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input past extraction data into a generating AI, and the generating AI can optimize the extraction algorithm.

[0052] The extraction unit can improve the accuracy of keyword and phrase extraction by considering the source information of the articles. For example, the extraction unit can improve accuracy by prioritizing the extraction of news articles from highly reliable sources. For example, the extraction unit can consider the bias of the source and reflect it in the extraction results. For example, the extraction unit can evaluate the past reliability of the source and incorporate it into the extraction algorithm. By improving the accuracy of extraction by considering the source information of the articles, more accurate extraction results can be obtained. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the source information of news articles into a generating AI, and the generating AI can improve the accuracy of the extraction.

[0053] The quality evaluation unit can optimize its evaluation algorithm by referring to past evaluation data when evaluating the quality of video and audio. For example, the quality evaluation unit can identify frequently occurring evaluation criteria based on past evaluation data and reflect them in the evaluation algorithm. For example, the quality evaluation unit can extract evaluation criteria related to a specific topic from past evaluation data and adjust the evaluation algorithm. For example, the quality evaluation unit can analyze past evaluation data and build a feedback loop to improve the accuracy of the evaluation algorithm. This allows for improved evaluation accuracy by optimizing the evaluation algorithm by referring to past evaluation data. Some or all of the above processes in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation unit can input past evaluation data into a generating AI and use the generating AI to optimize the evaluation algorithm.

[0054] The quality evaluation unit can improve the accuracy of its evaluations by considering the source information of video and audio when evaluating the quality of video and audio. For example, the quality evaluation unit can prioritize the evaluation of video and audio from highly reliable sources to improve accuracy. For example, the quality evaluation unit can consider the bias of the source and reflect it in the evaluation results. For example, the quality evaluation unit can evaluate the past reliability of the source and incorporate it into the evaluation algorithm. By improving the accuracy of the evaluation by considering the source information of video and audio, more accurate evaluation results can be obtained. Some or all of the above processing in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation unit can input the source information of video and audio into a generating AI, and the generating AI can improve the accuracy of the evaluation.

[0055] The adjustment unit can optimize the adjustment algorithm by referring to past adjustment data when adjusting the text overlays. For example, the adjustment unit can identify frequently occurring font, color, and size patterns based on past adjustment data and reflect them in the adjustment algorithm. For example, the adjustment unit can extract fonts, colors, and sizes related to a specific topic from past adjustment data and adjust the adjustment algorithm. For example, the adjustment unit can analyze past adjustment data and build a feedback loop to improve the accuracy of the adjustment algorithm. This allows for improved adjustment accuracy by optimizing the adjustment algorithm by referring to past adjustment data. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input past adjustment data into a generating AI and have the generating AI optimize the adjustment algorithm.

[0056] The adjustment unit can improve the accuracy of the adjustment by considering the display position information of the on-screen text when adjusting it. For example, the adjustment unit automatically determines the optimal display position based on the display position information of the on-screen text. For example, the adjustment unit considers the display position information of the on-screen text and places the on-screen text in a position with high visibility. For example, the adjustment unit refers to the display position information of the on-screen text and places it so that it does not overlap with other elements. By improving the accuracy of the adjustment by considering the display position information of the on-screen text, a more accurate adjustment result can be obtained. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the display position information of the on-screen text into a generating AI, and the generating AI can improve the accuracy of the adjustment.

[0057] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0058] The analysis unit can also evaluate the reliability of news articles when analyzing their content. For example, it can assess the reliability of the news article's source and filter out information from unreliable sources. Furthermore, it can check whether the news article's content is consistent with other reliable sources and issue a warning if it is inconsistent. It can also point out inconsistencies if the news article's content contradicts historical data. This enhances the reliability of news articles and provides viewers with accurate information.

[0059] The extraction unit can also evaluate the importance of news articles when analyzing their content. For example, it can assess how important a news article's content is to the viewer and prioritize extracting the most important information. Furthermore, it can evaluate how important a news article's content is compared to other news articles and highlight the most important information. It can also assess how much impact a news article's content has on the viewer and take measures to maximize that impact. This allows for the management of news article importance and the provision of appropriate information to the viewer.

[0060] The analysis unit can apply different analysis methods depending on the category of the news article when analyzing its content. For example, in the case of political news, the analysis unit can apply methods specialized in analyzing technical terms and proper nouns. Furthermore, in the case of sports news, the analysis unit can apply methods that focus on analyzing match results and player names. In addition, in the case of entertainment news, the analysis unit can apply methods that analyze celebrity names and titles of works. By applying different analysis methods to each category of article, the accuracy of the analysis can be improved.

[0061] The analysis unit can also consider the source information of news articles when analyzing their content. For example, it can evaluate the reliability of the news article's source and filter out information from unreliable sources. Furthermore, it can check whether the news article's content is consistent with other reliable sources and issue a warning if it is inconsistent. It can also point out inconsistencies if the news article's content contradicts historical data. This enhances the reliability of news articles and provides viewers with accurate information.

[0062] The selection unit can optimize its selection algorithm by referring to past selection data when selecting video and audio. For example, it can identify frequently occurring video and audio patterns based on past selection data and reflect them in the selection algorithm. Furthermore, it can extract video and audio related to specific topics from past selection data and adjust the selection algorithm. In addition, the selection unit can analyze past selection data and build a feedback loop to improve the accuracy of the selection algorithm. As a result, the selection accuracy can be improved by optimizing the selection algorithm by referring to past selection data.

[0063] The following briefly describes the processing flow for example form 1.

[0064] Step 1: The analysis unit analyzes the news article in text format. The analysis unit uses natural language processing technology to analyze the content of the news article in detail and extract important keywords and phrases. For example, if the news article contains keywords such as "earthquake" or "disaster," it selects related videos and audio based on these keywords. Step 2: The selection unit selects relevant video and audio based on the results analyzed by the analysis unit. If the news article contains the word "earthquake," the selection unit selects video of the earthquake and audio from the affected area. The selection unit makes its selections considering the quality and relevance of the video and audio, for example, based on the resolution of the video, the clarity of the audio, and the degree of matching with the content of the news article. Step 3: The generation unit automatically generates captions based on the video and audio selected by the selection unit. The generation unit displays the title and important information of the news article as captions, and automatically adjusts the font, color, and size of the captions to arrange them in a visually easy-to-read format. For example, the font size of the captions is increased and the color is made brighter to improve readability.

[0065] (Example of form 2) An embodiment of the present invention provides an automated video news generation system that analyzes a news article in text format, selects relevant video, audio, and captions, and automatically generates video news. This system allows news media to reduce the cost and time required for video production and to deliver news quickly and efficiently. For example, the automated video news generation system analyzes a news article in text format using natural language processing technology. It analyzes the content of the news article in detail and extracts important keywords and phrases. For example, if the news article contains keywords such as "earthquake" or "disaster," it selects relevant video and audio based on these keywords. Next, it automatically selects relevant video and audio based on the analysis results. For example, if the news article contains "earthquake," it selects video of the earthquake and audio from the disaster area. In this case, the quality and relevance of the video and audio are considered during the selection process. Furthermore, it automatically generates captions and places them in appropriate positions. For example, it displays the title of the news article and important information as captions. In this case, the font, color, size, etc. of the captions are automatically adjusted and placed in a visually easy-to-read format. This automated video news generation system allows news media to reduce production time by 80% and video production costs by 50% compared to traditional manual methods. It can also double news productivity. For example, news media can provide high-quality visual content to viewers, improving viewer satisfaction. This automated video news generation system enables news media to deliver news quickly and efficiently.

[0066] The video news automatic generation system according to this embodiment comprises an analysis unit, a selection unit, and a generation unit. The analysis unit analyzes news articles in text format. The analysis unit analyzes the content of news articles in detail, for example, using natural language processing technology, and extracts important keywords and phrases. If the news article contains keywords such as "earthquake" or "disaster," the analysis unit selects relevant video and audio based on these keywords. The selection unit selects relevant video and audio based on the results of the analysis performed by the analysis unit. If the news article contains "earthquake," the selection unit selects video of the earthquake and audio from the disaster area. The selection unit makes selections considering the quality and relevance of the video and audio. For example, the selection unit makes selections based on the resolution of the video, the clarity of the audio, and the degree of agreement with the content of the news article. The generation unit automatically generates captions based on the video and audio selected by the selection unit. For example, the generation unit displays the title of the news article and important information as captions. The generation unit automatically adjusts the font, color, and size of the on-screen text and arranges it in a visually easy-to-read format. For example, the generation unit improves visibility by increasing the font size and brightening the color of the on-screen text. As a result, the video news automatic generation system according to this embodiment can analyze a news article in text format, select relevant video, audio, and on-screen text, and automatically generate video news.

[0067] The analysis unit analyzes news articles in text format. For example, it uses natural language processing techniques to analyze the content of news articles in detail and extract important keywords and phrases. Specifically, it utilizes natural language processing techniques such as morphological analysis, dependency structure analysis, and named entity recognition to understand the context and meaning of news articles. For example, it uses morphological analysis to segment the words in the news article and identify the part of speech of each word. It uses dependency structure analysis to analyze the relationships between words in a sentence and grasp the sentence structure. It uses named entity recognition to extract proper nouns such as place names, personal names, and organization names contained in the news article. Based on these analysis results, it understands the content of the news article in detail and extracts important keywords and phrases. For example, if the news article contains keywords such as "earthquake" or "disaster," it provides information for selecting relevant videos and audio based on these keywords. By accurately analyzing the content of news articles, the analysis unit provides a foundation for the selection and generation units to select and generate appropriate videos, audio, and captions. Furthermore, the analysis unit also performs sentiment analysis on news articles to grasp the tone and emotions of the articles. For example, it distinguishes between positive and negative news articles and provides information for selecting appropriate video and audio content. In this way, the analysis unit can analyze the content of news articles from multiple angles and provide a foundation for the selection and generation units to automatically generate high-quality video news.

[0068] The selection unit selects relevant video and audio based on the results analyzed by the analysis unit. For example, if a news article contains the word "earthquake," the selection unit will select earthquake video and audio from the affected area. Specifically, the selection unit searches for relevant content from video and audio databases based on keywords and phrases provided by the analysis unit. The selection unit makes selections considering the quality and relevance of the video and audio. For example, it selects based on the video resolution, audio clarity, and degree of relevance to the content of the news article. The selection unit confirms that the video resolution is high and the audio is clear, selecting content that is easy for viewers to see and hear. The selection unit also evaluates the degree of relevance to the content of the news article and selects the video and audio that are most appropriate for the article's content. For example, by selecting earthquake video and audio from the affected area for a news article about an earthquake, the content of the news can be accurately conveyed to the viewer. Furthermore, the selection unit checks the copyright and usage rights of the video and audio to select appropriate content. As a result, the selection unit can select the video and audio that are most appropriate for the content of the news article and provide viewers with high-quality video news.

[0069] The generation unit automatically generates captions based on the video and audio selected by the selection unit. For example, the generation unit displays news article titles and important information as captions. Specifically, the generation unit analyzes the content of news articles and extracts information important to the viewer. For example, it extracts the news article title, main keywords, and important phrases, and displays these as captions. The generation unit automatically adjusts the font, color, and size of the captions, arranging them in a visually appealing manner. For example, it improves visibility by increasing the font size and brightness of the captions. Furthermore, the generation unit adjusts the timing and position of the captions to create a sense of unity with the video and audio. For example, it displays captions in sync with important information in the news article to effectively convey information to the viewer. In addition, the generation unit adds animations and effects to the captions to enhance their visual appeal. For example, it adds animations such as fade-in and fade-out to attract the viewer's attention. This allows the generation unit to automatically generate visually appealing and effectively informative captions based on the video and audio selected by the selection unit.

[0070] The analysis unit can analyze the content of news articles in detail. For example, the analysis unit can use natural language processing technology to delve deeper into the content of news articles and understand the context. For example, the analysis unit can analyze the relationships between paragraphs and sentences in news articles and extract important information. For example, by analyzing the content of news articles in detail, the analysis unit can grasp background information and related information about the news articles. This allows for more accurate analysis results by analyzing the content of news articles in detail. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of news articles into a generating AI, which can then understand the context and extract important information.

[0071] The extraction unit can extract important keywords and phrases. For example, the extraction unit extracts important keywords and phrases from news articles using natural language processing technology. For example, the extraction unit extracts keywords and phrases based on frequency of occurrence or contextual importance. For example, the extraction unit extracts particularly important information from news articles and performs analysis based on it. By doing so, the accuracy of news article analysis can be improved by extracting important keywords and phrases. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of a news article into a generating AI, and the generating AI can extract important keywords and phrases.

[0072] The quality evaluation unit can select video and audio by considering their quality and relevance. For example, the quality evaluation unit selects video and audio based on video resolution, audio clarity, and degree of relevance to the content of the news article. For example, the quality evaluation unit evaluates the quality of video and audio and selects the one that is most suitable for the content of the news article. For example, the quality evaluation unit evaluates how well the content of the video and audio matches the content of the news article. By selecting video and audio by considering their quality and relevance, more appropriate video and audio can be selected. Some or all of the above processing in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation unit can input the video and audio quality evaluation into a generating AI, and the generating AI can perform the quality evaluation.

[0073] The adjustment unit can automatically adjust the font, color, size, etc., of the on-screen text. For example, the adjustment unit can improve visibility by increasing the font size and brightening the color of the on-screen text. For example, the adjustment unit can adjust the size of the on-screen text to ensure readability on the screen. For example, the adjustment unit can adjust the color of the on-screen text to match the background and position it in a visually easy-to-read manner. In this way, by automatically adjusting the font, color, size, etc., the on-screen text can be generated in a visually easy-to-read manner. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input the adjustments for the font, color, and size of the on-screen text into a generating AI, and the generating AI can perform the adjustments.

[0074] The analysis unit can estimate the user's emotions and adjust the analysis method of news articles based on the estimated user emotions. For example, if the user is sad, the analysis unit will apply an emotion-sensitive analysis method and avoid emphasizing sensitive content. For example, if the user is excited, the analysis unit will apply an emotionally appealing analysis method and emphasize interesting content. For example, if the user has neutral emotions, the analysis unit will apply a balanced analysis method and provide objective information. By adjusting the analysis method of news articles based on the user's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the analysis method based on the results.

[0075] The analysis unit can optimize its analysis algorithm by referring to past news article data when analyzing news articles. For example, the analysis unit can identify frequently occurring keywords and phrases based on past news article data and reflect them in the analysis algorithm. For example, the analysis unit can extract patterns related to specific topics from past news article data and adjust the analysis algorithm. For example, the analysis unit can analyze past news article data and build a feedback loop to improve the accuracy of the analysis algorithm. This allows for improved analysis accuracy by optimizing the analysis algorithm by referring to past news article data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past news article data into a generating AI and have the generating AI optimize the analysis algorithm.

[0076] The analysis unit can apply different analysis methods to each category of news articles when analyzing them. For example, in the case of political news, the analysis unit can apply methods specialized in analyzing technical terms and proper nouns. For example, in the case of sports news, the analysis unit can apply methods that focus on analyzing match results and player names. For example, in the case of entertainment news, the analysis unit can apply methods that analyze celebrity names and work titles. By applying different analysis methods to each category of article, the accuracy of the analysis can be improved. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input news article category information into a generating AI, and the generating AI can apply category-specific analysis methods.

[0077] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is sad, the analysis unit will apply an emotion-sensitive display method and display sensitive content discreetly. For example, if the user is excited, the analysis unit will apply a display method that enhances the emotion and emphasize interesting content. For example, if the user has neutral emotions, the analysis unit will apply a balanced display method and provide objective information. By adjusting the display method of the analysis results based on the user's emotions, more appropriate display results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the display method based on the results.

[0078] The analysis unit can improve the accuracy of its analysis by considering the source information of news articles. For example, the analysis unit can prioritize the analysis of news articles from highly reliable sources to improve accuracy. For example, the analysis unit can consider the bias of the source and reflect it in the analysis results. For example, the analysis unit can evaluate the past reliability of the source and incorporate it into the analysis algorithm. By improving the accuracy of the analysis by considering the source information of the articles, more accurate analysis results can be obtained. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the source information of news articles into a generating AI, and the generating AI can improve the accuracy of the analysis.

[0079] The analysis unit can improve the accuracy of its analysis by referring to related literature when analyzing news articles. For example, the analysis unit can supplement background information on news articles based on related literature to improve the accuracy of its analysis. For example, the analysis unit can reflect data obtained from related literature into its analysis algorithm. For example, the analysis unit can refer to related literature and apply analysis methods to gain a deeper understanding of the content of news articles. By improving the accuracy of the analysis by referring to related literature, more accurate analysis results can be obtained. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input related literature for news articles into a generating AI, and the generating AI can improve the accuracy of the analysis.

[0080] The selection unit can estimate the user's emotions and adjust the video and audio selection criteria based on the estimated user emotions. For example, if the user is sad, the selection unit will select emotionally appropriate video and audio and downplay sensitive content. For example, if the user is excited, the selection unit will select video and audio that enhances the emotion and emphasize interesting content. For example, if the user is neutral, the selection unit will select balanced video and audio and provide objective information. By adjusting the video and audio selection criteria based on the user's emotions, more appropriate video and audio can be selected. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI or not using AI. For example, the selection unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the selection criteria based on the results.

[0081] The selection unit can optimize its selection algorithm by referring to past selection data when selecting video and audio. For example, the selection unit can identify frequently occurring video and audio patterns based on past selection data and reflect them in the selection algorithm. For example, the selection unit can extract video and audio related to a specific topic from past selection data and adjust the selection algorithm. For example, the selection unit can analyze past selection data and build a feedback loop to improve the accuracy of the selection algorithm. This allows for improved selection accuracy by optimizing the selection algorithm by referring to past selection data. Some or all of the above processes in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input past selection data into a generating AI, and the generating AI can optimize the selection algorithm.

[0082] The selection unit can apply different selection methods to each category of news article when selecting video and audio. For example, in the case of political news, the selection unit can apply a method for selecting specialized video and audio. For example, in the case of sports news, the selection unit can apply a method for selecting match highlights and athlete interviews. For example, in the case of entertainment news, the selection unit can apply a method for selecting celebrity interviews and event footage. By applying different selection methods to each category of news article, the selection accuracy can be improved. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input news article category information into a generating AI, and the generating AI can apply a category-specific selection method.

[0083] The selection unit can estimate the user's emotions and adjust the display method of the selection results based on the estimated user emotions. For example, if the user is sad, the selection unit will apply an emotion-sensitive display method and display sensitive content discreetly. For example, if the user is excited, the selection unit will apply an emotion-enhancing display method and emphasize interesting content. For example, if the user has neutral emotions, the selection unit will apply a balanced display method and provide objective information. By adjusting the display method of the selection results based on the user's emotions, more appropriate display results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the display method based on the result.

[0084] The selection unit can improve the accuracy of its selection process by considering the source information of the video and audio when selecting them. For example, the selection unit can prioritize selecting video and audio from highly reliable sources to improve accuracy. For example, the selection unit can consider the bias of the source and reflect it in the selection results. For example, the selection unit can evaluate the past reliability of the source and incorporate it into the selection algorithm. By improving the accuracy of selection by considering the source information of the video and audio, more accurate selection results can be obtained. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the source information of the video and audio into a generating AI, and the generating AI can improve the accuracy of the selection.

[0085] The selection unit can improve the accuracy of its selection by referring to the metadata of the relevant video and audio when selecting video and audio. For example, the selection unit improves the accuracy of its selection based on the metadata of the relevant video and audio. For example, the selection unit reflects the information obtained from the metadata into the selection algorithm. For example, the selection unit makes the selection results more accurate by referring to the metadata of the relevant video and audio. In this way, by improving the accuracy of the selection by referring to the metadata of the relevant video and audio, more accurate selection results can be obtained. Some or all of the above processing in the selection unit may be performed using AI, for example, or without using AI. For example, the selection unit can input the metadata of the video and audio into a generating AI, and the generating AI can improve the accuracy of the selection.

[0086] The generation unit can estimate the user's emotions and adjust the method of generating the on-screen text based on the estimated emotions. For example, if the user is sad, the generation unit can generate emotionally sensitive on-screen text and downplay sensitive content. For example, if the user is excited, the generation unit can generate on-screen text that enhances the emotion and emphasizes interesting content. For example, if the user has neutral emotions, the generation unit can generate balanced on-screen text and provide objective information. In this way, by adjusting the method of generating on-screen text based on the user's emotions, more appropriate on-screen text can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user emotion data into a generation AI, have the generation AI perform emotion estimation, and adjust the method of generating on-screen text based on the result.

[0087] The generation unit can optimize its generation algorithm by referring to past generation data when generating text overlays. For example, the generation unit can identify frequently occurring text overlay patterns based on past generation data and reflect them in the generation algorithm. For example, the generation unit can extract text overlays related to specific topics from past generation data and adjust the generation algorithm. For example, the generation unit can analyze past generation data and build a feedback loop to improve the accuracy of the generation algorithm. This allows for improved generation accuracy by optimizing the generation algorithm by referring to past generation data. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input past generation data into a generation AI and have the generation AI optimize the generation algorithm.

[0088] The generation unit can apply different generation methods to each category of news article when generating captions. For example, in the case of political news, the generation unit can apply a method to generate specialized captions. For example, in the case of sports news, the generation unit can apply a method to generate captions that focus on displaying match results and player names. For example, in the case of entertainment news, the generation unit can apply a method to generate captions that display celebrity names and work titles. By applying different generation methods to each category of news article, the generation accuracy can be improved. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input news article category information into a generation AI, and the generation AI can apply a category-specific generation method.

[0089] The generation unit can estimate the user's emotions and adjust the display method of the generated results based on the estimated user emotions. For example, if the user is sad, the generation unit will apply an emotion-sensitive display method and display sensitive content discreetly. For example, if the user is excited, the generation unit will apply an emotion-enhancing display method and emphasize interesting content. For example, if the user has neutral emotions, the generation unit will apply a balanced display method and provide objective information. By adjusting the display method of the generated results based on the user's emotions, more appropriate display results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation 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 generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user emotion data into a generation AI, have the generation AI perform emotion estimation, and adjust the display method based on the results.

[0090] The generation unit can improve the accuracy of text generation by considering the text display position information. For example, the generation unit automatically determines the optimal display position based on the text display position information. For example, the generation unit places the text in a highly visible position, taking into account the text display position information. For example, the generation unit refers to the text display position information and places it so that it does not overlap with other elements. By improving the accuracy of generation by considering the text display position information, more accurate generation results can be obtained. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the text display position information into a generation AI, and the generation AI can improve the accuracy of generation.

[0091] The generation unit can improve the accuracy of its generation by referring to the metadata of related subtitles when generating subtitles. For example, the generation unit improves the accuracy of its generation based on the metadata of related subtitles. For example, the generation unit reflects the information obtained from the metadata into the generation algorithm. For example, the generation unit makes the generation result more accurate by referring to the metadata of related subtitles. In this way, a more accurate generation result can be obtained by improving the accuracy of generation by referring to the metadata of related subtitles. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI. For example, the generation unit can input the metadata of the subtitles into a generation AI, and the generation AI can improve the accuracy of the generation.

[0092] The analysis unit can estimate the user's emotions and adjust the analysis method of news articles based on the estimated user emotions. For example, if the user is sad, the analysis unit will apply an emotion-sensitive analysis method and avoid emphasizing sensitive content. For example, if the user is excited, the analysis unit will apply an emotionally appealing analysis method and emphasize interesting content. For example, if the user has neutral emotions, the analysis unit will apply a balanced analysis method and provide objective information. By adjusting the analysis method of news articles based on the user's emotions, more appropriate analysis results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the analysis method based on the results.

[0093] The analysis unit can optimize its analysis algorithm by referring to past analysis data when analyzing news articles. For example, the analysis unit can identify frequently occurring keywords and phrases based on past analysis data and reflect them in the analysis algorithm. For example, the analysis unit can extract patterns related to specific topics from past analysis data and adjust the analysis algorithm. For example, the analysis unit can analyze past analysis data and build a feedback loop to improve the accuracy of the analysis algorithm. This allows for improved analysis accuracy by optimizing the analysis algorithm by referring to past analysis data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past analysis data into a generating AI and have the generating AI optimize the analysis algorithm.

[0094] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is sad, the analysis unit will apply an emotion-sensitive display method and display sensitive content discreetly. For example, if the user is excited, the analysis unit will apply an emotion-enhancing display method and emphasize interesting content. For example, if the user has neutral emotions, the analysis unit will apply a balanced display method and provide objective information. By adjusting the display method of the analysis results based on the user's emotions, more appropriate display results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the display method based on the results.

[0095] The analysis unit can improve the accuracy of its analysis by considering the source information of news articles. For example, the analysis unit can prioritize the analysis of news articles from reliable sources to improve accuracy. For example, the analysis unit can consider the bias of the source and reflect it in the analysis results. For example, the analysis unit can evaluate the past reliability of the source and incorporate it into the analysis algorithm. By improving the accuracy of the analysis by considering the source information of the articles, more accurate analysis results can be obtained. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the source information of news articles into a generating AI, and the generating AI can improve the accuracy of the analysis.

[0096] The extraction unit can estimate the user's emotions and adjust the keyword and phrase extraction method based on the estimated user emotions. For example, if the user is sad, the extraction unit applies an emotion-sensitive extraction method and avoids emphasizing sensitive content. For example, if the user is excited, the extraction unit applies an emotion-enhancing extraction method and emphasizes interesting content. For example, if the user has neutral emotions, the extraction unit applies a balanced extraction method and provides objective information. By adjusting the keyword and phrase extraction method based on the user's emotions, more appropriate extraction results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using AI or not using AI. For example, the extraction unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the extraction method based on the results.

[0097] The extraction unit can optimize its extraction algorithm by referring to past extraction data when extracting keywords and phrases. For example, the extraction unit can identify frequently occurring keywords and phrases based on past extraction data and reflect them in the extraction algorithm. For example, the extraction unit can extract patterns related to specific topics from past extraction data and adjust the extraction algorithm. For example, the extraction unit can analyze past extraction data and build a feedback loop to improve the accuracy of the extraction algorithm. This allows for improved extraction accuracy by optimizing the extraction algorithm by referring to past extraction data. Some or all of the above processes in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input past extraction data into a generating AI, and the generating AI can optimize the extraction algorithm.

[0098] The extraction unit can estimate the user's emotions and adjust the display method of the extraction results based on the estimated user emotions. For example, if the user is sad, the extraction unit applies an emotion-sensitive display method and displays sensitive content discreetly. For example, if the user is excited, the extraction unit applies an emotion-enhancing display method and emphasizes interesting content. For example, if the user has neutral emotions, the extraction unit applies a balanced display method and provides objective information. By adjusting the display method of the extraction results based on the user's emotions, more appropriate display results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the display method based on the result.

[0099] The extraction unit can improve the accuracy of keyword and phrase extraction by considering the source information of the articles. For example, the extraction unit can improve accuracy by prioritizing the extraction of news articles from highly reliable sources. For example, the extraction unit can consider the bias of the source and reflect it in the extraction results. For example, the extraction unit can evaluate the past reliability of the source and incorporate it into the extraction algorithm. By improving the accuracy of extraction by considering the source information of the articles, more accurate extraction results can be obtained. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the source information of news articles into a generating AI, and the generating AI can improve the accuracy of the extraction.

[0100] The quality evaluation unit can estimate the user's emotions and adjust the video and audio quality evaluation criteria based on the estimated user emotions. For example, if the user is sad, the quality evaluation unit will apply emotion-sensitive quality evaluation criteria and evaluate sensitive content sparingly. For example, if the user is excited, the quality evaluation unit will apply quality evaluation criteria that enhance the emotion and highlight interesting content. For example, if the user is neutral, the quality evaluation unit will apply balanced quality evaluation criteria and provide objective information. By adjusting the video and audio quality evaluation criteria based on the user's emotions, more appropriate evaluation results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation department can input user emotion data into a generating AI, have the AI ​​perform emotion estimation, and adjust the quality evaluation criteria based on the results.

[0101] The quality evaluation unit can optimize its evaluation algorithm by referring to past evaluation data when evaluating the quality of video and audio. For example, the quality evaluation unit can identify frequently occurring evaluation criteria based on past evaluation data and reflect them in the evaluation algorithm. For example, the quality evaluation unit can extract evaluation criteria related to a specific topic from past evaluation data and adjust the evaluation algorithm. For example, the quality evaluation unit can analyze past evaluation data and build a feedback loop to improve the accuracy of the evaluation algorithm. This allows for improved evaluation accuracy by optimizing the evaluation algorithm by referring to past evaluation data. Some or all of the above processes in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation unit can input past evaluation data into a generating AI and use the generating AI to optimize the evaluation algorithm.

[0102] The quality evaluation unit can estimate the user's emotions and adjust the display method of the evaluation results based on the estimated user emotions. For example, if the user is sad, the quality evaluation unit will apply an emotion-sensitive display method and display sensitive content discreetly. For example, if the user is excited, the quality evaluation unit will apply a display method that enhances the emotion and emphasize interesting content. For example, if the user has neutral emotions, the quality evaluation unit will apply a balanced display method and provide objective information. By adjusting the display method of the evaluation results based on the user's emotions, more appropriate display results can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and adjust the display method based on the results.

[0103] The quality evaluation unit can improve the accuracy of its evaluations by considering the source information of video and audio when evaluating the quality of video and audio. For example, the quality evaluation unit can prioritize the evaluation of video and audio from highly reliable sources to improve accuracy. For example, the quality evaluation unit can consider the bias of the source and reflect it in the evaluation results. For example, the quality evaluation unit can evaluate the past reliability of the source and incorporate it into the evaluation algorithm. By improving the accuracy of the evaluation by considering the source information of video and audio, more accurate evaluation results can be obtained. Some or all of the above processing in the quality evaluation unit may be performed using AI, for example, or without AI. For example, the quality evaluation unit can input the source information of video and audio into a generating AI, and the generating AI can improve the accuracy of the evaluation.

[0104] The adjustment unit can estimate the user's emotions and change the font, color, and size of the on-screen text based on the estimated emotions. For example, if the user is sad, the adjustment unit will apply an emotionally appropriate font, color, and size, and display sensitive content discreetly. For example, if the user is excited, the adjustment unit will apply an emotionally evocative font, color, and size, and emphasize interesting content. For example, if the user has neutral emotions, the adjustment unit will apply a balanced font, color, and size, and provide objective information. By changing the font, color, and size of the on-screen text based on the user's emotions, a more appropriate display result can be obtained. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input user emotion data into a generating AI, which then performs emotion estimation, and based on the results, it can change the font, color, and size adjustment methods.

[0105] The adjustment unit can optimize the adjustment algorithm by referring to past adjustment data when adjusting the text overlays. For example, the adjustment unit can identify frequently occurring font, color, and size patterns based on past adjustment data and reflect them in the adjustment algorithm. For example, the adjustment unit can extract fonts, colors, and sizes related to a specific topic from past adjustment data and adjust the adjustment algorithm. For example, the adjustment unit can analyze past adjustment data and build a feedback loop to improve the accuracy of the adjustment algorithm. This allows for improved adjustment accuracy by optimizing the adjustment algorithm by referring to past adjustment data. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input past adjustment data into a generating AI and have the generating AI optimize the adjustment algorithm.

[0106] The adjustment unit can estimate the user's emotions and change the display method of the adjustment results based on the estimated user emotions. For example, if the user is sad, the adjustment unit applies an emotion-sensitive display method and displays sensitive content discreetly. For example, if the user is excited, the adjustment unit applies an emotion-enhancing display method and emphasizes interesting content. For example, if the user has neutral emotions, the adjustment unit applies a balanced display method and provides objective information. By changing the display method of the adjustment results based on the user's emotions, more appropriate display results can be obtained. Emotion estimation 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 adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input user emotion data into a generative AI, have the generative AI perform emotion estimation, and change the display method based on the result.

[0107] The adjustment unit can improve the accuracy of the adjustment by considering the display position information of the on-screen text when adjusting it. For example, the adjustment unit automatically determines the optimal display position based on the display position information of the on-screen text. For example, the adjustment unit considers the display position information of the on-screen text and places the on-screen text in a position with high visibility. For example, the adjustment unit refers to the display position information of the on-screen text and places it so that it does not overlap with other elements. By improving the accuracy of the adjustment by considering the display position information of the on-screen text, a more accurate adjustment result can be obtained. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the display position information of the on-screen text into a generating AI, and the generating AI can improve the accuracy of the adjustment.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The analysis unit can also evaluate the reliability of news articles when analyzing their content. For example, it can assess the reliability of the news article's source and filter out information from unreliable sources. Furthermore, it can check whether the news article's content is consistent with other reliable sources and issue a warning if it is inconsistent. It can also point out inconsistencies if the news article's content contradicts historical data. This enhances the reliability of news articles and provides viewers with accurate information.

[0110] The analysis unit can also evaluate the emotional tone of news articles when analyzing their content. For example, it can assess whether the news article has a positive, negative, or neutral tone. Furthermore, it can evaluate whether the news article's content is likely to evoke specific emotions and adjust the analysis method based on the results. It can also predict the emotional impact of the news article's content on viewers and take measures to minimize that impact. This allows for the management of the emotional impact of news articles and the provision of appropriate information to viewers.

[0111] The extraction unit can also evaluate the importance of news articles when analyzing their content. For example, it can assess how important a news article's content is to the viewer and prioritize extracting the most important information. Furthermore, it can evaluate how important a news article's content is compared to other news articles and highlight the most important information. It can also assess how much impact a news article's content has on the viewer and take measures to maximize that impact. This allows for the management of news article importance and the provision of appropriate information to the viewer.

[0112] The Quality Evaluation Department can also consider viewer emotions when evaluating video and audio quality. For example, it can assess how viewers feel about the video and audio and adjust the quality evaluation criteria based on those emotions. Furthermore, it can evaluate how viewer emotions affect video and audio quality and take measures to minimize that impact. It can also predict how viewer emotions will affect evaluations of video and audio quality and take measures to maximize that impact. This allows for the management of video and audio quality and the provision of appropriate information to viewers.

[0113] The adjustment unit can also consider viewer emotions when adjusting the font, color, and size of on-screen text. For example, it can evaluate how viewers feel about the on-screen text and adjust the font, color, and size based on those emotions. Furthermore, it can evaluate how viewer emotions affect the legibility of the on-screen text and take measures to minimize that impact. It can also predict how viewer emotions affect their understanding of the on-screen text content and take measures to maximize that impact. This allows for the management of on-screen text fonts, colors, and sizes, enabling the provision of appropriate information to viewers.

[0114] The analysis unit can apply different analysis methods depending on the category of the news article when analyzing its content. For example, in the case of political news, the analysis unit can apply methods specialized in analyzing technical terms and proper nouns. Furthermore, in the case of sports news, the analysis unit can apply methods that focus on analyzing match results and player names. In addition, in the case of entertainment news, the analysis unit can apply methods that analyze celebrity names and titles of works. By applying different analysis methods to each category of article, the accuracy of the analysis can be improved.

[0115] The selection unit can also consider viewer emotions when selecting video and audio. For example, the selection unit can evaluate how viewers feel about the video and audio and adjust the selection criteria based on those emotions. Furthermore, the selection unit can evaluate how viewer emotions influence the selection of video and audio and take measures to minimize that influence. In addition, the selection unit can predict how viewer emotions will influence the selection results of video and audio and take measures to maximize that influence. This allows for the management of video and audio selection and the provision of appropriate information to viewers.

[0116] The generation unit can also consider the viewer's emotions when generating on-screen text. For example, the generation unit can evaluate how viewers feel about the on-screen text and adjust its content based on those emotions. Furthermore, the generation unit can evaluate how viewers' emotions affect the legibility of the on-screen text and take measures to minimize that impact. In addition, the generation unit can predict how viewers' emotions affect their understanding of the on-screen text and take measures to maximize that impact. This allows for the management of on-screen text generation and the provision of appropriate information to viewers.

[0117] The analysis unit can also consider the source information of news articles when analyzing their content. For example, it can evaluate the reliability of the news article's source and filter out information from unreliable sources. Furthermore, it can check whether the news article's content is consistent with other reliable sources and issue a warning if it is inconsistent. It can also point out inconsistencies if the news article's content contradicts historical data. This enhances the reliability of news articles and provides viewers with accurate information.

[0118] The selection unit can optimize its selection algorithm by referring to past selection data when selecting video and audio. For example, it can identify frequently occurring video and audio patterns based on past selection data and reflect them in the selection algorithm. Furthermore, it can extract video and audio related to specific topics from past selection data and adjust the selection algorithm. In addition, the selection unit can analyze past selection data and build a feedback loop to improve the accuracy of the selection algorithm. As a result, the selection accuracy can be improved by optimizing the selection algorithm by referring to past selection data.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The analysis unit analyzes the news article in text format. The analysis unit uses natural language processing technology to analyze the content of the news article in detail and extract important keywords and phrases. For example, if the news article contains keywords such as "earthquake" or "disaster," it selects related videos and audio based on these keywords. Step 2: The selection unit selects relevant video and audio based on the results analyzed by the analysis unit. If the news article contains the word "earthquake," the selection unit selects video of the earthquake and audio from the affected area. The selection unit makes its selections considering the quality and relevance of the video and audio, for example, based on the resolution of the video, the clarity of the audio, and the degree of matching with the content of the news article. Step 3: The generation unit automatically generates captions based on the video and audio selected by the selection unit. The generation unit displays the title and important information of the news article as captions, and automatically adjusts the font, color, and size of the captions to arrange them in a visually easy-to-read format. For example, the font size of the captions is increased and the color is made brighter to improve readability.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] Each of the multiple elements described above, including the analysis unit, selection unit, and generation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and analyzes the content of a news article using natural language processing technology. The selection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and selects relevant video and audio based on the analysis results. The generation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and automatically generates captions based on the selected video and audio. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the analysis unit, selection unit, and generation unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and analyzes the content of a news article using natural language processing technology. The selection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and selects relevant video and audio based on the analysis results. The generation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and automatically generates captions based on the selected video and audio. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] Each of the multiple elements described above, including the analysis unit, selection unit, and generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and analyzes the content of news articles using natural language processing technology. The selection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and selects relevant video and audio based on the analysis results. The generation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12, and automatically generates captions based on the selected video and audio. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] Each of the multiple elements described above, including the analysis unit, selection unit, and generation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and analyzes the content of a news article using natural language processing technology. The selection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and selects relevant video and audio based on the analysis results. The generation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12, and automatically generates captions based on the selected video and audio. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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."

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] (Note 1) An analysis unit that analyzes news articles in text format, A selection unit selects relevant video and audio based on the results of the analysis performed by the aforementioned analysis unit, The system includes a generation unit that automatically generates captions based on the video and audio selected by the selection unit. A system characterized by the following features. (Note 2) It has an analysis department that analyzes the content of news articles in detail. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes an extraction unit that extracts important keywords and phrases. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a quality evaluation department that selects based on the quality and relationship between video and audio. The system described in Appendix 1, characterized by the features described herein. (Note 5) It features an adjustment unit that automatically adjusts the font, color, size, and other aspects of the on-screen text. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, We estimate user sentiment and adjust the news article analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, When analyzing news articles, the analysis algorithm is optimized by referring to past news article data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing news articles, different analysis methods are applied to each article category. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, When analyzing news articles, we improve the accuracy of the analysis by considering the source information of the articles. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, When analyzing news articles, we improve the accuracy of the analysis by referring to related literature. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned selection unit is The system estimates the user's emotions and adjusts the selection criteria for video and audio based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned selection unit is When selecting video and audio, the selection algorithm is optimized by referring to past selection data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned selection unit is When selecting video and audio, different selection methods are applied depending on the category of the news article. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned selection unit is The system estimates the user's emotions and adjusts how the selection results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned selection unit is When selecting video and audio, we improve the accuracy of the selection by considering the source information of the video and audio. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned selection unit is When selecting video and audio, referencing related video and audio metadata improves the accuracy of the selection. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is The system estimates the user's emotions and adjusts the method of generating on-screen text based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating text overlays, the generation algorithm is optimized by referring to past generation data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating on-screen text, different generation methods are applied depending on the category of the news article. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is It estimates the user's emotions and adjusts how the generated results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is When generating text overlays, the accuracy of the generation is improved by considering the display position information of the text overlays. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating on-screen text, the system improves the accuracy of the generation by referencing metadata of related on-screen text. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit is We estimate user sentiment and adjust the news article analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit is When analyzing news articles, we optimize the analysis algorithm by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned analysis unit is When analyzing news articles, consider the source information of the articles to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 28) The extraction unit is It estimates the user's emotions and adjusts the method of extracting keywords and phrases based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The extraction unit is When extracting keywords and phrases, the extraction algorithm is optimized by referring to past extraction data. The system described in Appendix 1, characterized by the features described herein. (Note 30) The extraction unit is It estimates the user's emotions and adjusts how the extraction results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The extraction unit is When extracting keywords and phrases, we improve the accuracy of the extraction by considering the source information of the articles. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned quality evaluation unit, It estimates the user's emotions and adjusts the video and audio quality evaluation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned quality evaluation unit, When evaluating video and audio quality, the evaluation algorithm is optimized by referring to past evaluation data. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned quality evaluation unit, The system estimates the user's emotions and adjusts how the evaluation results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned quality evaluation unit, When evaluating video and audio quality, consider the source information of the video and audio to improve the accuracy of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 36) The adjustment unit is, The system estimates the user's emotions and adjusts the font, color, and size of the on-screen text based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The adjustment unit is, When adjusting the on-screen text, the adjustment algorithm is optimized by referring to past adjustment data. The system described in Appendix 1, characterized by the features described herein. (Note 38) The adjustment unit is, The system estimates the user's emotions and changes how the adjustment results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The adjustment unit is, When adjusting on-screen text, consider the text's display position information to improve the accuracy of the adjustment. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0193] 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. An analysis unit that analyzes news articles in text format, A selection unit selects relevant video and audio based on the results of the analysis performed by the aforementioned analysis unit, The system includes a generation unit that automatically generates captions based on the video and audio selected by the selection unit. A system characterized by the following features.

2. It has an analysis department that analyzes the content of news articles in detail. The system according to feature 1.

3. It includes an extraction unit that extracts important keywords and phrases. The system according to feature 1.

4. It includes a quality evaluation department that selects based on the quality and relationship between video and audio. The system according to feature 1.

5. It features an adjustment unit that automatically adjusts the font, color, size, and other aspects of the on-screen text. The system according to feature 1.

6. The aforementioned analysis unit, We estimate user sentiment and adjust the news article analysis method based on the estimated user sentiment. The system according to feature 1.

7. The aforementioned analysis unit, When analyzing news articles, the analysis algorithm is optimized by referring to past news article data. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing news articles, different analysis methods are applied to each article category. The system according to feature 1.

9. The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system according to feature 1.

Images