system

Abstract

The system according to this embodiment aims to extract important information from the text of an e-book and present it according to the user's preferences. [Solution] The system according to the embodiment comprises an analysis unit, a highlighting unit, and a recommendation unit. The analysis unit analyzes the text of the ebook. The highlighting unit highlights the keywords and phrases extracted by the analysis unit on the ebook. The recommendation unit recommends topics from the ebook text that are related to the user's preferences.

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, it has not been sufficiently done to efficiently extract important information from the long text of an e-book and present it according to the user's preferences, and there is room for improvement.

[0005] The system according to the embodiment aims to extract important information from the text of an e-book and present it according to the user's preferences.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a highlighting unit, and a recommendation unit. The analysis unit analyzes the text of the ebook. The highlighting unit highlights the keywords and phrases extracted by the analysis unit on the ebook. The recommendation unit recommends topics from the ebook text that are related to the user's preferences. [Effects of the Invention]

[0007] The system according to this embodiment can extract important information from the text of an e-book and present it according to the user's preferences. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI assistant for an automated e-book summary system according to an embodiment of the present invention is a system that analyzes the text of an e-book, highlights important keywords and phrases, and recommends topics related to the user's preferences. The AI ​​assistant for the automated e-book summary system analyzes the text of an e-book, highlights important keywords and phrases, and recommends topics related to the user's preferences. For example, the AI ​​assistant for the automated e-book summary system analyzes the text of an e-book. The analysis unit extracts keywords or phrases from the text content using natural language processing technology. Next, it highlights the extracted keywords or phrases on the e-book. Furthermore, it recommends topics related to the user's preferences. For example, it can recommend relevant topics based on the user's reading history. It can also estimate the user's emotions and modify keywords or phrases based on the estimated emotions. Furthermore, it includes a summarization unit that displays summaries of sentences or chapters longer than a certain threshold. The summarization unit can display the main points in a list format. This allows the user to concisely grasp long texts or the main points of each chapter. It is also possible to change the keywords or phrases extracted according to the genre of the book. For example, in specialized books, specific technical terms and phrases can be prioritized for extraction. This mechanism allows users to efficiently grasp the content of ebooks and find relevant sections and topics according to their interests and needs. For instance, when reading a business book, important keywords and phrases are highlighted, and related topics are recommended, allowing for efficient information acquisition. In addition, summaries of long texts and chapters are displayed, allowing users to grasp the main points concisely. Thus, the AI ​​assistant in the ebook automatic summary system enables users to efficiently grasp the content of ebooks and find relevant sections and topics.

[0029] The AI ​​assistant for an automated e-book summary system according to this embodiment comprises an analysis unit, a highlighting unit, and a recommendation unit. The analysis unit analyzes the text of the e-book. The analysis unit extracts keywords or phrases from the content of the text using, for example, natural language processing technology. The analysis unit divides the text using, for example, morphological analysis and extracts important keywords. The analysis unit can also analyze the structure of sentences using grammatical analysis and extract important phrases. Furthermore, the analysis unit can understand the meaning of the text using semantic analysis and extract important information. For example, the analysis unit divides the text into words using morphological analysis and extracts high-frequency words. It analyzes the structure of sentences using grammatical analysis and extracts important elements such as subjects and predicates. It understands the meaning of the text using semantic analysis and extracts important information. The highlighting unit highlights the keywords or phrases extracted by the analysis unit on the e-book. The highlighting unit highlights keywords using, for example, color. The highlighting unit displays important keywords in red and less important keywords in blue. Furthermore, the highlighted section can emphasize keywords by changing the font style. For example, important keywords can be displayed in bold, and less important keywords in italics. In addition, the highlighted section can emphasize keywords by changing the background color. For example, important keywords can have a yellow background, and less important keywords can have a gray background. The recommendation section recommends topics from the ebook text that are relevant to the user's preferences. For example, the recommendation section recommends relevant topics based on the user's past reading history. For example, the recommendation section recommends relevant topics based on keywords from books the user has read in the past. The recommendation section can also recommend relevant topics based on the user's survey results. For example, it recommends relevant topics based on topics the user has shown interest in in a survey. Furthermore, the recommendation section can also recommend relevant topics based on the user's social media activity. For example, it recommends relevant topics based on topics the user has shown interest in on social media.As a result, the AI ​​assistant for the automated e-book summary system according to the embodiment can analyze the text of the e-book, highlight important keywords and phrases, and recommend topics related to the user's preferences. Some or all of the above-described processes in the analysis unit, highlighting unit, and recommendation unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the text of the e-book into a generating AI and cause the generating AI to extract keywords and phrases. The highlighting unit can perform highlighting based on the keywords and phrases extracted by the generating AI. The recommendation unit can recommend topics related to the user based on the topics recommended by the generating AI.

[0030] The analysis unit analyzes the text of the ebook. For example, it extracts keywords or phrases from the text using natural language processing techniques. Specifically, it uses morphological analysis to divide the text into words and extracts high-frequency words. Morphological analysis is a technique that identifies the words and phrases that make up the text and determines their parts of speech. This allows the analysis unit to efficiently extract important keywords within the text. Furthermore, it uses grammatical analysis to analyze the sentence structure and extract important elements such as subjects and predicates. Grammatical analysis is a technique that understands the structure of a sentence and clarifies the relationships between each element within the sentence. This allows the analysis unit to grasp the meaning of the entire sentence and identify important phrases. Furthermore, it uses semantic analysis to understand the meaning of the text and extract important information. Semantic analysis is a technique that understands the context and meaning of the text and extracts important information. For example, the analysis unit can extract information related to a specific theme or topic within the text and provide useful information to the user. The analysis unit combines these analysis techniques to comprehensively analyze the text of the ebook and extract important keywords and phrases. This allows the analysis unit to efficiently grasp the content of ebooks and provide users with important information. Furthermore, the analysis unit can also perform text analysis using generative AI. Generative AI can learn from large amounts of text data and analyze text content using advanced natural language processing techniques. For example, the generative AI can take ebook text as input and automatically extract important keywords and phrases. This enables the analysis unit to achieve more accurate and efficient text analysis.

[0031] The highlighting section highlights keywords or phrases extracted by the analysis section on the ebook. Specifically, it uses color to emphasize keywords. For example, important keywords can be displayed in red, and less important keywords in blue. This allows users to identify important information at a glance. The highlighting section can also emphasize keywords by changing the font style. For example, important keywords can be displayed in bold, and less important keywords in italics. This allows users to visually distinguish important information. Furthermore, the highlighting section can emphasize keywords by changing the background color. For example, the background of important keywords can be set to yellow, and the background of less important keywords to gray. This allows users to identify important information through the difference in background color. By combining these visual highlighting methods, the highlighting section can deliver information in the most effective way for the user. In addition, the highlighting section can perform highlighting based on keywords and phrases extracted by the generative AI. The generative AI can analyze the content of the text and automatically extract important information. This allows the highlighting section to perform highlighting efficiently and accurately based on the information provided by the generative AI. For example, the generation AI analyzes the text of an ebook, extracts important keywords and phrases, and provides them to the highlight section. Based on this information, the highlight section can visually highlight the most important information for the user. This allows the highlight section to help the user efficiently understand the content of the ebook and quickly grasp important information.

[0032] The recommendation system recommends topics related to the user's preferences from the text of ebooks. Specifically, it recommends relevant topics based on the user's past reading history. For example, it recommends relevant topics based on keywords from books the user has read in the past. This allows users to efficiently find topics that match their interests. The recommendation system can also recommend relevant topics based on the user's survey results. For example, it recommends relevant topics based on topics the user indicated interest in in a survey. This allows users to efficiently find topics that match their interests. Furthermore, the recommendation system can also recommend relevant topics based on the user's social media activity. For example, it recommends relevant topics based on topics the user indicated interest in on social media. This allows users to efficiently find topics that match their interests. The recommendation system can combine this information to recommend the most relevant topics for the user. In addition, the recommendation system can use generative AI to analyze user preferences and recommend relevant topics. Generative AI can learn from large amounts of data and analyze user preferences with high accuracy. For example, generative AI can analyze a user's past reading history, survey results, and social media activity to automatically recommend the most relevant topics for the user. This allows the recommendation system to efficiently recommend topics that match the user's preferences, thereby improving the user's reading experience.

[0033] The summarization unit can display summaries of texts longer than a certain threshold, as well as summaries of individual chapters. For example, the summarization unit can automatically summarize long texts and display the main points in a list format. For example, the summarization unit can analyze long texts using natural language processing techniques and extract important information. For example, the summarization unit can divide long texts using morphological analysis and extract important keywords. Furthermore, the summarization unit can analyze sentence structure using grammatical analysis and extract important phrases. In addition, the summarization unit can understand the meaning of long texts using semantic analysis and extract important information. For example, the summarization unit can divide long texts into individual words using morphological analysis and extract high-frequency words. It can analyze sentence structure using grammatical analysis and extract important elements such as subjects and predicates. It can understand the meaning of long texts using semantic analysis and extract important information. This allows the user to grasp the main points concisely by displaying summaries of long texts and individual chapters. Some or all of the above-described processes in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input a long text into a generation AI and have the generation AI perform the summarization.

[0034] The summary section can display key points in list format. For example, the summary section can display important information in bullet points. For example, the summary section can display important keywords or phrases in list format. The summary section can also display key points using numbered lists. For example, the summary section can display important information in numbered lists to indicate the priority of the information. Furthermore, the summary section can also display key points using hierarchical lists. For example, the summary section can display important information in a hierarchical list to indicate the relationships between the information. This makes it easier for users to organize information by displaying key points in list format. Some or all of the above processing in the summary section may be performed using AI, for example, or without AI. For example, the summary section can display key points in list format based on points extracted by a generation AI.

[0035] The analysis unit can change the keywords and phrases extracted from ebooks according to the genre of the book. For example, the analysis unit changes the keywords and phrases extracted according to genres such as fiction, nonfiction, and technical books. For example, in the case of fiction, the analysis unit extracts keywords related to the flow of the story and the relationships between characters. In the case of nonfiction, it extracts keywords related to facts and data. In the case of technical books, it extracts specialized terms and technical phrases. In this way, the analysis unit can extract more appropriate information by changing the keywords and phrases according to the genre of the book. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the genre of the book into a generating AI and have the generating AI perform the extraction of keywords and phrases according to the genre.

[0036] The analysis unit can extract keywords or phrases from the content of text using natural language processing techniques. For example, the analysis unit can segment the text using morphological analysis and extract important keywords. The analysis unit can also analyze the structure of sentences using grammatical analysis and extract important phrases. Furthermore, the analysis unit can understand the meaning of the text using semantic analysis and extract important information. For example, the analysis unit can segment the text into words using morphological analysis and extract high-frequency words. It can analyze the structure of sentences using grammatical analysis and extract important elements such as subjects and predicates. It can understand the meaning of the text using semantic analysis and extract important information. In this way, the analysis unit can extract appropriate keywords and phrases from the content of text by using natural language processing techniques. 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 text into a generating AI and have the generating AI perform keyword and phrase extraction.

[0037] The analysis unit can extract keywords or phrases from ebooks based on the user's past reading history. For example, the analysis unit can extract relevant keywords based on a list of books the user has read in the past. For example, the analysis unit can extract relevant keywords based on keywords from books the user has read in the past. The analysis unit can also extract relevant keywords based on the user's reading time. For example, it can extract relevant keywords based on keywords from books the user has read for a long time. Furthermore, the analysis unit can prioritize the extraction of keywords related to specific genres from the user's reading history. For example, it can extract relevant keywords based on keywords from genres the user has read frequently in the past. In this way, the analysis unit can provide highly relevant information by extracting keywords and phrases based on the user's past reading history. 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 user's reading history data into a generating AI and have the generating AI perform the extraction of keywords and phrases.

[0038] The analysis unit can preferentially extract specific technical terms and phrases. For example, the analysis unit can extract technical terms based on a list of terms in a specific field. For example, in the case of a technical book, the analysis unit can extract technical terms based on a list of technical terms. The analysis unit can also extract technical terms using frequency analysis. For example, it can extract terms that are frequently used in a specific field. Furthermore, the analysis unit can also extract technical terms using co-occurrence network analysis. For example, it can extract terms that co-occur in a specific field. In this way, the analysis unit can provide specialized information by preferentially extracting specific technical terms and phrases. 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 a list of technical terms into a generating AI and have the generating AI perform the extraction of technical terms.

[0039] The analysis unit can apply different natural language processing algorithms depending on the genre of the book. For example, in the case of a novel, the analysis unit applies an algorithm that emphasizes the flow of the story and the relationships between characters. For example, in the case of a business book, the analysis unit applies an algorithm that extracts important business terms and concepts. Furthermore, in the case of an academic book, the analysis unit can also apply an algorithm that emphasizes specialized terminology and research results. This allows the analysis unit to perform more accurate analysis by applying the appropriate algorithm according to the genre of the book. 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 genre of the book into a generating AI and have the generating AI execute the application of a natural language processing algorithm appropriate to the genre.

[0040] The analysis unit can analyze a user's past reading history and extract the most relevant keywords or phrases. For example, the analysis unit can extract relevant keywords based on keywords from books the user has read in the past. For example, the analysis unit can extract phrases related to topics the user has shown interest in in the past. The analysis unit can also preferentially extract keywords related to specific genres from the user's reading history. In this way, the analysis unit can extract highly relevant keywords and phrases by analyzing the user's past reading history. 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 user's reading history data into a generating AI and have the generating AI perform keyword and phrase extraction.

[0041] The analysis unit can change the keywords or phrases it extracts based on the publication year of the book. For example, in the case of an older book, the analysis unit extracts keywords related to the historical context. For example, in the case of a newer book, the analysis unit extracts keywords related to the latest trends and technologies. The analysis unit can also extract phrases that are appropriate for the time period, depending on the publication year. In this way, the analysis unit can provide timely information by changing keywords and phrases based on the publication year of the book. 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 book's publication year data into a generating AI and have the generating AI perform the extraction of keywords and phrases.

[0042] The analysis unit can extract keywords or phrases that match a specific author's style, taking into account the author's information in the book. For example, the analysis unit can extract keywords related to a specific theme or style based on the author's past works. For example, the analysis unit can prioritize extracting phrases related to the author's area of ​​expertise. The analysis unit can also extract specific expressions that match the author's writing style. In this way, the analysis unit can provide more appropriate information by extracting keywords and phrases that match the author's style. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input data on the author's past works into a generating AI and have the generating AI perform the extraction of keywords and phrases.

[0043] The highlighting section can apply different emphasis methods based on the importance of keywords when highlighting them. For example, the highlighting section might use bold or underline for important keywords, it might use italics for keywords of moderate importance, or it might use regular highlighting for keywords of low importance. In this way, the highlighting section can highlight important information by applying different emphasis methods based on the importance of keywords. Some or all of the above processing in the highlighting section may be performed using AI, for example, or not. For example, the highlighting section could input keyword importance data into a generating AI and have the generating AI perform the application of emphasis methods.

[0044] The highlighting function can select the optimal display method by referring to the user's past highlighting history when displaying highlights. For example, the highlighting function may prioritize the use of highlight colors and styles that the user has previously preferred. For example, the highlighting function may extract specific patterns from the user's past highlighting history and suggest the optimal display method. The highlighting function can also analyze the user's past highlighting history and select the most effective display method. Thus, the highlighting function can select the optimal display method by referring to the user's past highlighting history. Some or all of the above processing in the highlighting function may be performed using AI, for example, or without AI. For example, the highlighting function can input the user's highlighting history data into a generating AI and have the generating AI perform the selection of the display method.

[0045] The highlighting function can select the optimal display method when highlighting, taking into account the user's device information. For example, on a smartphone, the highlighting function will display highlights according to the screen size. On a tablet, for example, the highlighting function will display highlights optimized for the larger screen. Furthermore, on a desktop, the highlighting function can also display highlights that include detailed information. In this way, the highlighting function can select the optimal display method by taking into account the user's device information. Some or all of the above processing in the highlighting function may be performed using AI, for example, or without AI. For example, the highlighting function can input the user's device information into a generating AI and have the generating AI perform the selection of the display method.

[0046] The highlighting function can analyze the user's reading speed when highlighting text and display highlights at the appropriate time. For example, if the user is speed-reading, the highlighting function will quickly highlight important keywords. If the user is reading slowly, the highlighting function will sequentially highlight keywords containing detailed information. The highlighting function can also display highlights at the optimal time according to the user's reading speed. This allows the highlighting function to provide more relevant information by displaying highlights according to the user's reading speed. Some or all of the above processing in the highlighting function may be performed using AI, for example, or without AI. For example, the highlighting function can input the user's reading speed data into a generating AI and have the generating AI execute the timing of the highlights.

[0047] The recommendation system can analyze a user's past reading history to recommend the most suitable topics. For example, the recommendation system can recommend content related to topics the user has read in the past. For example, the recommendation system can recommend topics that the user might be interested in based on their past reading history. The recommendation system can also analyze the user's reading history and recommend highly relevant topics. In this way, the recommendation system can recommend highly relevant topics by analyzing the user's past reading history. Some or all of the above processes in the recommendation system may be performed using AI, for example, or without AI. For example, the recommendation system can input the user's reading history data into a generating AI and have the generating AI perform topic recommendations.

[0048] The recommendation system can customize topics based on the user's current reading status when making recommendations. For example, the recommendation system can recommend topics related to the content of the book the user is currently reading. For example, the recommendation system can recommend topics to read next based on the user's current reading progress. The recommendation system can also analyze the user's current reading status and customize the most suitable topics. This allows the recommendation system to make more appropriate recommendations by customizing topics based on the user's current reading status. Some or all of the above processes in the recommendation system may be performed using AI, for example, or not using AI. For example, the recommendation system can input the user's reading status data into a generating AI and have the generating AI perform topic customization.

[0049] The recommendation unit can recommend highly relevant topics by considering the user's geographical location. For example, the recommendation unit can recommend topics related to the user's current location. For example, the recommendation unit can recommend topics related to local trends based on the user's geographical location. The recommendation unit can also analyze the user's geographical location and recommend the most suitable topics. This allows the recommendation unit to recommend highly relevant topics by considering the user's geographical location. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's geographical location data into a generating AI and have the generating AI perform topic recommendations.

[0050] The recommendation unit can analyze a user's social media activity and recommend relevant topics during the recommendation process. For example, the recommendation unit can recommend topics that the user has shown interest in on social media. For example, the recommendation unit can recommend highly relevant topics based on the user's social media activity. The recommendation unit can also analyze the user's social media activity and recommend the most suitable topics. In this way, the recommendation unit can recommend highly relevant topics by analyzing the user's social media activity. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's social media activity data into a generating AI and have the generating AI perform topic recommendations.

[0051] The summarization unit can adjust the level of detail in the summary based on the importance of the text during summary generation. For example, the summarization unit provides a detailed summary for important text, a concise summary for text of moderate importance, and a minimal summary for text of low importance. By adjusting the level of detail based on the importance of the text, the summarization unit can provide a more appropriate summary. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input text importance data into a generating AI and have the generating AI determine the level of detail in the summary.

[0052] The summarization unit can apply different summarization algorithms depending on the text category when generating summaries. For example, in the case of a novel, the summarization unit can apply a summarization algorithm that emphasizes the flow of the story and the relationships between characters. For example, in the case of a business book, the summarization unit can apply a summarization algorithm that extracts important business terms and concepts. Furthermore, in the case of an academic book, the summarization unit can also apply a summarization algorithm that emphasizes specialized terminology and research findings. In this way, the summarization unit can provide more appropriate summaries by applying different summarization algorithms depending on the text category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input text category data into a generating AI and have the generating AI execute the application of the summarization algorithm.

[0053] The summarization unit can determine the priority of summaries based on the submission date of the text when generating summaries. For example, the summarization unit may prioritize summaries for the most recent texts and postpone summaries for older texts. The summarization unit can also adjust the priority of summaries according to the submission date. This allows the summarization unit to provide more appropriate summaries by determining the priority of summaries based on the submission date of the texts. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input text submission date data into a generation AI and have the generation AI perform the summary priority calculation.

[0054] The summarization unit can adjust the order of summaries based on the relevance of the text during summary generation. For example, the summarization unit might summarize important text first, then text of moderate importance, and finally text of low importance. By adjusting the order of summaries based on the relevance of the text, the summarization unit can provide more appropriate summaries. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input text relevance data into a generation AI and have the generation AI execute the order of summaries.

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

[0056] The analysis unit can monitor the user's reading speed in real time and adjust the method of extracting keywords and phrases according to the reading speed. For example, if the user is speed reading, the analysis unit will prioritize extracting short, important keywords. If the user is reading slowly, it will extract keywords that include detailed phrases and context. Furthermore, if the user's reading speed fluctuates, the analysis unit can dynamically adjust the extraction method accordingly. This allows the analysis unit to provide optimal information according to the user's reading speed.

[0057] The summarization function can analyze the user's reading history and customize the summary style based on the content of books they have read in the past. For example, if a user prefers the summary style of books they have read previously, it will generate summaries based on that style. If a user reads many books of a particular genre, it will apply a summary style appropriate for that genre. It can also prioritize displaying summaries related to specific topics based on the user's reading history. In this way, the summarization function can provide the most suitable summaries based on the user's reading history.

[0058] The highlighting feature can adjust its display method based on the user's device's battery level. For example, when the battery level is low, the highlight color and style can be changed to an energy-saving one. When the battery level is sufficient, the highlighting is displayed as normal. Furthermore, when the battery level is moderate, the frequency and emphasis of the highlighting can also be adjusted. This allows the highlighting feature to provide the optimal display method according to the device's battery status.

[0059] The analysis unit can monitor the user's reading environment and adjust the keyword and phrase extraction method according to the environment. For example, if the user is reading in a quiet environment, it will extract keywords containing detailed phrases and context. If the user is reading in a noisy environment, it will prioritize extracting short, important keywords. Furthermore, if the user's reading environment changes, the analysis unit can dynamically adjust the extraction method accordingly. This allows the analysis unit to provide optimal information according to the user's reading environment.

[0060] The highlighting function can analyze the user's reading history and customize the highlighting display based on the highlighting colors and styles the user has previously preferred. For example, if the user has previously preferred red highlighting, red highlighting will be prioritized. If the user has previously preferred bold highlighting, bold highlighting will be prioritized. It can also extract specific patterns from the user's reading history and suggest the optimal highlighting display. In this way, the highlighting function can provide the most optimal highlighting display based on the user's reading history.

[0061] The analysis unit can adjust the method of extracting keywords and phrases based on the user's reading time. For example, if the user is reading at night, it will prioritize extracting keywords and phrases that promote relaxation. If the user is reading during the day, it will extract keywords and phrases that enhance concentration. Furthermore, if the user's reading time fluctuates, the analysis unit can dynamically adjust the extraction method accordingly. This allows the analysis unit to provide optimal information based on the user's reading time.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The analysis unit analyzes the text of the ebook. The analysis unit uses natural language processing techniques to extract keywords or phrases from the text content. For example, it can use morphological analysis to segment the text and extract important keywords. It can also use grammatical analysis to analyze the structure of sentences and extract important phrases. Furthermore, it can use semantic analysis to understand the meaning of the text and extract important information. Step 2: The highlighting section highlights the keywords or phrases extracted by the analysis section on the ebook. For example, keywords can be highlighted using color. Important keywords can be displayed in red, and less important keywords in blue. Keywords can also be emphasized by changing the font style. For example, important keywords can be displayed in bold, and less important keywords in italics. Furthermore, keywords can be emphasized by changing the background color. For example, the background of important keywords can be set to yellow, and the background of less important keywords to gray. Step 3: The recommendation team recommends topics from the ebook text that are relevant to the user's preferences. For example, it can recommend topics based on the user's past reading history. It can also recommend topics based on keywords from books the user has read in the past. Furthermore, it can recommend topics based on the user's survey results. For example, it can recommend topics based on topics the user has shown interest in in a survey. In addition, it can recommend topics based on the user's social media activity. For example, it can recommend topics based on topics the user has shown interest in on social media.

[0064] (Example of form 2) An AI assistant for an automated e-book summary system according to an embodiment of the present invention is a system that analyzes the text of an e-book, highlights important keywords and phrases, and recommends topics related to the user's preferences. The AI ​​assistant for the automated e-book summary system analyzes the text of an e-book, highlights important keywords and phrases, and recommends topics related to the user's preferences. For example, the AI ​​assistant for the automated e-book summary system analyzes the text of an e-book. The analysis unit extracts keywords or phrases from the text content using natural language processing technology. Next, it highlights the extracted keywords or phrases on the e-book. Furthermore, it recommends topics related to the user's preferences. For example, it can recommend relevant topics based on the user's reading history. It can also estimate the user's emotions and modify keywords or phrases based on the estimated emotions. Furthermore, it includes a summarization unit that displays summaries of sentences or chapters longer than a certain threshold. The summarization unit can display the main points in a list format. This allows the user to concisely grasp long texts or the main points of each chapter. It is also possible to change the keywords or phrases extracted according to the genre of the book. For example, in specialized books, specific technical terms and phrases can be prioritized for extraction. This mechanism allows users to efficiently grasp the content of ebooks and find relevant sections and topics according to their interests and needs. For instance, when reading a business book, important keywords and phrases are highlighted, and related topics are recommended, allowing for efficient information acquisition. In addition, summaries of long texts and chapters are displayed, allowing users to grasp the main points concisely. Thus, the AI ​​assistant in the ebook automatic summary system enables users to efficiently grasp the content of ebooks and find relevant sections and topics.

[0065] The AI ​​assistant for an automated e-book summary system according to this embodiment comprises an analysis unit, a highlighting unit, and a recommendation unit. The analysis unit analyzes the text of the e-book. The analysis unit extracts keywords or phrases from the content of the text using, for example, natural language processing technology. The analysis unit divides the text using, for example, morphological analysis and extracts important keywords. The analysis unit can also analyze the structure of sentences using grammatical analysis and extract important phrases. Furthermore, the analysis unit can understand the meaning of the text using semantic analysis and extract important information. For example, the analysis unit divides the text into words using morphological analysis and extracts high-frequency words. It analyzes the structure of sentences using grammatical analysis and extracts important elements such as subjects and predicates. It understands the meaning of the text using semantic analysis and extracts important information. The highlighting unit highlights the keywords or phrases extracted by the analysis unit on the e-book. The highlighting unit highlights keywords using, for example, color. The highlighting unit displays important keywords in red and less important keywords in blue. Furthermore, the highlighted section can emphasize keywords by changing the font style. For example, important keywords can be displayed in bold, and less important keywords in italics. In addition, the highlighted section can emphasize keywords by changing the background color. For example, important keywords can have a yellow background, and less important keywords can have a gray background. The recommendation section recommends topics from the ebook text that are relevant to the user's preferences. For example, the recommendation section recommends relevant topics based on the user's past reading history. For example, the recommendation section recommends relevant topics based on keywords from books the user has read in the past. The recommendation section can also recommend relevant topics based on the user's survey results. For example, it recommends relevant topics based on topics the user has shown interest in in a survey. Furthermore, the recommendation section can also recommend relevant topics based on the user's social media activity. For example, it recommends relevant topics based on topics the user has shown interest in on social media.As a result, the AI ​​assistant for the automated e-book summary system according to the embodiment can analyze the text of the e-book, highlight important keywords and phrases, and recommend topics related to the user's preferences. Some or all of the above-described processes in the analysis unit, highlighting unit, and recommendation unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the text of the e-book into a generating AI and cause the generating AI to extract keywords and phrases. The highlighting unit can perform highlighting based on the keywords and phrases extracted by the generating AI. The recommendation unit can recommend topics related to the user based on the topics recommended by the generating AI.

[0066] The analysis unit analyzes the text of the ebook. For example, it extracts keywords or phrases from the text using natural language processing techniques. Specifically, it uses morphological analysis to divide the text into words and extracts high-frequency words. Morphological analysis is a technique that identifies the words and phrases that make up the text and determines their parts of speech. This allows the analysis unit to efficiently extract important keywords within the text. Furthermore, it uses grammatical analysis to analyze the sentence structure and extract important elements such as subjects and predicates. Grammatical analysis is a technique that understands the structure of a sentence and clarifies the relationships between each element within the sentence. This allows the analysis unit to grasp the meaning of the entire sentence and identify important phrases. Furthermore, it uses semantic analysis to understand the meaning of the text and extract important information. Semantic analysis is a technique that understands the context and meaning of the text and extracts important information. For example, the analysis unit can extract information related to a specific theme or topic within the text and provide useful information to the user. The analysis unit combines these analysis techniques to comprehensively analyze the text of the ebook and extract important keywords and phrases. This allows the analysis unit to efficiently grasp the content of ebooks and provide users with important information. Furthermore, the analysis unit can also perform text analysis using generative AI. Generative AI can learn from large amounts of text data and analyze text content using advanced natural language processing techniques. For example, the generative AI can take ebook text as input and automatically extract important keywords and phrases. This enables the analysis unit to achieve more accurate and efficient text analysis.

[0067] The highlighting section highlights keywords or phrases extracted by the analysis section on the ebook. Specifically, it uses color to emphasize keywords. For example, important keywords can be displayed in red, and less important keywords in blue. This allows users to identify important information at a glance. The highlighting section can also emphasize keywords by changing the font style. For example, important keywords can be displayed in bold, and less important keywords in italics. This allows users to visually distinguish important information. Furthermore, the highlighting section can emphasize keywords by changing the background color. For example, the background of important keywords can be set to yellow, and the background of less important keywords to gray. This allows users to identify important information through the difference in background color. By combining these visual highlighting methods, the highlighting section can deliver information in the most effective way for the user. In addition, the highlighting section can perform highlighting based on keywords and phrases extracted by the generative AI. The generative AI can analyze the content of the text and automatically extract important information. This allows the highlighting section to perform highlighting efficiently and accurately based on the information provided by the generative AI. For example, the generation AI analyzes the text of an ebook, extracts important keywords and phrases, and provides them to the highlight section. Based on this information, the highlight section can visually highlight the most important information for the user. This allows the highlight section to help the user efficiently understand the content of the ebook and quickly grasp important information.

[0068] The recommendation system recommends topics related to the user's preferences from the text of ebooks. Specifically, it recommends relevant topics based on the user's past reading history. For example, it recommends relevant topics based on keywords from books the user has read in the past. This allows users to efficiently find topics that match their interests. The recommendation system can also recommend relevant topics based on the user's survey results. For example, it recommends relevant topics based on topics the user indicated interest in in a survey. This allows users to efficiently find topics that match their interests. Furthermore, the recommendation system can also recommend relevant topics based on the user's social media activity. For example, it recommends relevant topics based on topics the user indicated interest in on social media. This allows users to efficiently find topics that match their interests. The recommendation system can combine this information to recommend the most relevant topics for the user. In addition, the recommendation system can use generative AI to analyze user preferences and recommend relevant topics. Generative AI can learn from large amounts of data and analyze user preferences with high accuracy. For example, generative AI can analyze a user's past reading history, survey results, and social media activity to automatically recommend the most relevant topics for the user. This allows the recommendation system to efficiently recommend topics that match the user's preferences, thereby improving the user's reading experience.

[0069] The summarization unit can display summaries of texts longer than a certain threshold, as well as summaries of individual chapters. For example, the summarization unit can automatically summarize long texts and display the main points in a list format. For example, the summarization unit can analyze long texts using natural language processing techniques and extract important information. For example, the summarization unit can divide long texts using morphological analysis and extract important keywords. Furthermore, the summarization unit can analyze sentence structure using grammatical analysis and extract important phrases. In addition, the summarization unit can understand the meaning of long texts using semantic analysis and extract important information. For example, the summarization unit can divide long texts into individual words using morphological analysis and extract high-frequency words. It can analyze sentence structure using grammatical analysis and extract important elements such as subjects and predicates. It can understand the meaning of long texts using semantic analysis and extract important information. This allows the user to grasp the main points concisely by displaying summaries of long texts and individual chapters. Some or all of the above-described processes in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input a long text into a generation AI and have the generation AI perform the summarization.

[0070] The summary section can display key points in list format. For example, the summary section can display important information in bullet points. For example, the summary section can display important keywords or phrases in list format. The summary section can also display key points using numbered lists. For example, the summary section can display important information in numbered lists to indicate the priority of the information. Furthermore, the summary section can also display key points using hierarchical lists. For example, the summary section can display important information in a hierarchical list to indicate the relationships between the information. This makes it easier for users to organize information by displaying key points in list format. Some or all of the above processing in the summary section may be performed using AI, for example, or without AI. For example, the summary section can display key points in list format based on points extracted by a generation AI.

[0071] The analysis unit can change the keywords and phrases extracted from ebooks according to the genre of the book. For example, the analysis unit changes the keywords and phrases extracted according to genres such as fiction, nonfiction, and technical books. For example, in the case of fiction, the analysis unit extracts keywords related to the flow of the story and the relationships between characters. In the case of nonfiction, it extracts keywords related to facts and data. In the case of technical books, it extracts specialized terms and technical phrases. In this way, the analysis unit can extract more appropriate information by changing the keywords and phrases according to the genre of the book. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the genre of the book into a generating AI and have the generating AI perform the extraction of keywords and phrases according to the genre.

[0072] The analysis unit can extract keywords or phrases from the content of text using natural language processing techniques. For example, the analysis unit can segment the text using morphological analysis and extract important keywords. The analysis unit can also analyze the structure of sentences using grammatical analysis and extract important phrases. Furthermore, the analysis unit can understand the meaning of the text using semantic analysis and extract important information. For example, the analysis unit can segment the text into words using morphological analysis and extract high-frequency words. It can analyze the structure of sentences using grammatical analysis and extract important elements such as subjects and predicates. It can understand the meaning of the text using semantic analysis and extract important information. In this way, the analysis unit can extract appropriate keywords and phrases from the content of text by using natural language processing techniques. 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 text into a generating AI and have the generating AI perform keyword and phrase extraction.

[0073] The analysis unit can estimate the user's emotions and modify the keywords or phrases extracted from the ebook based on the estimated emotions. For example, the analysis unit can estimate the user's emotions using facial recognition technology. For example, the analysis unit can capture the user's facial expression with a camera and estimate the emotions using a facial recognition algorithm. The analysis unit can also estimate the user's emotions using text analysis technology. For example, it can analyze text entered by the user and estimate the emotions. Furthermore, the analysis unit can also estimate the user's emotions using speech analysis technology. For example, it can record the user's voice and estimate the emotions using a speech analysis algorithm. This allows the analysis unit to provide more appropriate information by modifying keywords and phrases based on the user's emotions. 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, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0074] The analysis unit can extract keywords or phrases from ebooks based on the user's past reading history. For example, the analysis unit can extract relevant keywords based on a list of books the user has read in the past. For example, the analysis unit can extract relevant keywords based on keywords from books the user has read in the past. The analysis unit can also extract relevant keywords based on the user's reading time. For example, it can extract relevant keywords based on keywords from books the user has read for a long time. Furthermore, the analysis unit can prioritize the extraction of keywords related to specific genres from the user's reading history. For example, it can extract relevant keywords based on keywords from genres the user has read frequently in the past. In this way, the analysis unit can provide highly relevant information by extracting keywords and phrases based on the user's past reading history. 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 user's reading history data into a generating AI and have the generating AI perform the extraction of keywords and phrases.

[0075] The analysis unit can preferentially extract specific technical terms and phrases. For example, the analysis unit can extract technical terms based on a list of terms in a specific field. For example, in the case of a technical book, the analysis unit can extract technical terms based on a list of technical terms. The analysis unit can also extract technical terms using frequency analysis. For example, it can extract terms that are frequently used in a specific field. Furthermore, the analysis unit can also extract technical terms using co-occurrence network analysis. For example, it can extract terms that co-occur in a specific field. In this way, the analysis unit can provide specialized information by preferentially extracting specific technical terms and phrases. 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 a list of technical terms into a generating AI and have the generating AI perform the extraction of technical terms.

[0076] The analysis unit can estimate the user's emotions and modify the keywords or phrases extracted based on the estimated emotions. For example, if the user is excited, the analysis unit will prioritize extracting positive keywords or phrases. If the user is depressed, the analysis unit will extract encouraging or comforting keywords or phrases. The analysis unit can also extract professional and detailed keywords or phrases if the user is focused. This allows the analysis unit to provide more appropriate information by modifying keywords and phrases based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with 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 facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0077] The analysis unit can apply different natural language processing algorithms depending on the genre of the book. For example, in the case of a novel, the analysis unit applies an algorithm that emphasizes the flow of the story and the relationships between characters. For example, in the case of a business book, the analysis unit applies an algorithm that extracts important business terms and concepts. Furthermore, in the case of an academic book, the analysis unit can also apply an algorithm that emphasizes specialized terminology and research results. This allows the analysis unit to perform more accurate analysis by applying the appropriate algorithm according to the genre of the book. 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 genre of the book into a generating AI and have the generating AI execute the application of a natural language processing algorithm appropriate to the genre.

[0078] The analysis unit can analyze a user's past reading history and extract the most relevant keywords or phrases. For example, the analysis unit can extract relevant keywords based on keywords from books the user has read in the past. For example, the analysis unit can extract phrases related to topics the user has shown interest in in the past. The analysis unit can also preferentially extract keywords related to specific genres from the user's reading history. In this way, the analysis unit can extract highly relevant keywords and phrases by analyzing the user's past reading history. 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 user's reading history data into a generating AI and have the generating AI perform keyword and phrase extraction.

[0079] The analysis unit can estimate the user's emotions and determine the priority of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit will prioritize analyzing important keywords. If the user is relaxed, the analysis unit will perform a detailed analysis. The analysis unit can also prioritize analyzing specialized content if the user is focused. In this way, the analysis unit can provide more appropriate information by determining the priority of the analysis based on the user's emotions. 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 not using AI. For example, the analysis unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0080] The analysis unit can change the keywords or phrases it extracts based on the publication year of the book. For example, in the case of an older book, the analysis unit extracts keywords related to the historical context. For example, in the case of a newer book, the analysis unit extracts keywords related to the latest trends and technologies. The analysis unit can also extract phrases that are appropriate for the time period, depending on the publication year. In this way, the analysis unit can provide timely information by changing keywords and phrases based on the publication year of the book. 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 book's publication year data into a generating AI and have the generating AI perform the extraction of keywords and phrases.

[0081] The analysis unit can extract keywords or phrases that match a specific author's style, taking into account the author's information in the book. For example, the analysis unit can extract keywords related to a specific theme or style based on the author's past works. For example, the analysis unit can prioritize extracting phrases related to the author's area of ​​expertise. The analysis unit can also extract specific expressions that match the author's writing style. In this way, the analysis unit can provide more appropriate information by extracting keywords and phrases that match the author's style. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input data on the author's past works into a generating AI and have the generating AI perform the extraction of keywords and phrases.

[0082] The highlighting section can estimate the user's emotions and change the highlight color and style based on the estimated emotions. For example, if the user is relaxed, the highlighting section might use softer highlights. If the user is focused, it might use more emphasized highlights. It might also use brighter highlights if the user is excited. This allows the highlighting section to display more appropriately by changing the highlight color and style based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the highlighting section may be performed using AI or not. For example, the highlighting section can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0083] The highlighting section can apply different emphasis methods based on the importance of keywords when highlighting them. For example, the highlighting section might use bold or underline for important keywords, it might use italics for keywords of moderate importance, or it might use regular highlighting for keywords of low importance. In this way, the highlighting section can highlight important information by applying different emphasis methods based on the importance of keywords. Some or all of the above processing in the highlighting section may be performed using AI, for example, or not. For example, the highlighting section could input keyword importance data into a generating AI and have the generating AI perform the application of emphasis methods.

[0084] The highlighting function can select the optimal display method by referring to the user's past highlighting history when displaying highlights. For example, the highlighting function may prioritize the use of highlight colors and styles that the user has previously preferred. For example, the highlighting function may extract specific patterns from the user's past highlighting history and suggest the optimal display method. The highlighting function can also analyze the user's past highlighting history and select the most effective display method. Thus, the highlighting function can select the optimal display method by referring to the user's past highlighting history. Some or all of the above processing in the highlighting function may be performed using AI, for example, or without AI. For example, the highlighting function can input the user's highlighting history data into a generating AI and have the generating AI perform the selection of the display method.

[0085] The highlighting section can estimate the user's emotions and adjust the order of highlights based on the estimated emotions. For example, if the user is in a hurry, the highlighting section will highlight important keywords first. If the user is relaxed, the highlighting section will sequentially highlight keywords containing detailed information. Furthermore, if the user is focused, the highlighting section can prioritize highlighting specialized content. This allows the highlighting section to provide more relevant information by adjusting the order of highlights based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the highlighting section may be performed using AI or not. For example, the highlighting section can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0086] The highlighting function can select the optimal display method when highlighting, taking into account the user's device information. For example, on a smartphone, the highlighting function will display highlights according to the screen size. On a tablet, for example, the highlighting function will display highlights optimized for the larger screen. Furthermore, on a desktop, the highlighting function can also display highlights that include detailed information. In this way, the highlighting function can select the optimal display method by taking into account the user's device information. Some or all of the above processing in the highlighting function may be performed using AI, for example, or without AI. For example, the highlighting function can input the user's device information into a generating AI and have the generating AI perform the selection of the display method.

[0087] The highlighting function can analyze the user's reading speed when highlighting text and display highlights at the appropriate time. For example, if the user is speed-reading, the highlighting function will quickly highlight important keywords. If the user is reading slowly, the highlighting function will sequentially highlight keywords containing detailed information. The highlighting function can also display highlights at the optimal time according to the user's reading speed. This allows the highlighting function to provide more relevant information by displaying highlights according to the user's reading speed. Some or all of the above processing in the highlighting function may be performed using AI, for example, or without AI. For example, the highlighting function can input the user's reading speed data into a generating AI and have the generating AI execute the timing of the highlights.

[0088] The recommendation system can estimate the user's emotions and change the topics it recommends based on those emotions. For example, if the user is relaxed, the recommendation system will recommend topics related to relaxation. If the user is excited, the recommendation system will recommend topics related to entertainment. It can also recommend academic topics if the user is focused. This allows the recommendation system to make more appropriate recommendations by changing topics based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0089] The recommendation system can analyze a user's past reading history to recommend the most suitable topics. For example, the recommendation system can recommend content related to topics the user has read in the past. For example, the recommendation system can recommend topics that the user might be interested in based on their past reading history. The recommendation system can also analyze the user's reading history and recommend highly relevant topics. In this way, the recommendation system can recommend highly relevant topics by analyzing the user's past reading history. Some or all of the above processes in the recommendation system may be performed using AI, for example, or without AI. For example, the recommendation system can input the user's reading history data into a generating AI and have the generating AI perform topic recommendations.

[0090] The recommendation system can customize topics based on the user's current reading status when making recommendations. For example, the recommendation system can recommend topics related to the content of the book the user is currently reading. For example, the recommendation system can recommend topics to read next based on the user's current reading progress. The recommendation system can also analyze the user's current reading status and customize the most suitable topics. This allows the recommendation system to make more appropriate recommendations by customizing topics based on the user's current reading status. Some or all of the above processes in the recommendation system may be performed using AI, for example, or not using AI. For example, the recommendation system can input the user's reading status data into a generating AI and have the generating AI perform topic customization.

[0091] The recommendation system can estimate the user's emotions and prioritize recommendations based on those emotions. For example, if the user is in a hurry, the recommendation system will prioritize recommending important topics. If the user is relaxed, the recommendation system will recommend topics containing detailed information. Furthermore, if the user is focused, the recommendation system can prioritize recommending specialized content. This allows the recommendation system to provide more appropriate recommendations by prioritizing recommendations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the recommendation system may be performed using AI or not. For example, the recommendation system can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0092] The recommendation unit can recommend highly relevant topics by considering the user's geographical location. For example, the recommendation unit can recommend topics related to the user's current location. For example, the recommendation unit can recommend topics related to local trends based on the user's geographical location. The recommendation unit can also analyze the user's geographical location and recommend the most suitable topics. This allows the recommendation unit to recommend highly relevant topics by considering the user's geographical location. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's geographical location data into a generating AI and have the generating AI perform topic recommendations.

[0093] The recommendation unit can analyze a user's social media activity and recommend relevant topics during the recommendation process. For example, the recommendation unit can recommend topics that the user has shown interest in on social media. For example, the recommendation unit can recommend highly relevant topics based on the user's social media activity. The recommendation unit can also analyze the user's social media activity and recommend the most suitable topics. In this way, the recommendation unit can recommend highly relevant topics by analyzing the user's social media activity. Some or all of the above processing in the recommendation unit may be performed using AI, for example, or without AI. For example, the recommendation unit can input the user's social media activity data into a generating AI and have the generating AI perform topic recommendations.

[0094] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the user is relaxed, the summarization unit will provide a summary in a soft tone. If the user is in a hurry, the summarization unit will provide a concise and to-the-point summary. The summarization unit can also provide a summary with detailed information if the user is focused. In this way, the summarization unit can provide a more appropriate summary by adjusting the way the summary is presented based on the user's emotions. 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 summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input user facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0095] The summarization unit can adjust the level of detail in the summary based on the importance of the text during summary generation. For example, the summarization unit provides a detailed summary for important text, a concise summary for text of moderate importance, and a minimal summary for text of low importance. By adjusting the level of detail based on the importance of the text, the summarization unit can provide a more appropriate summary. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input text importance data into a generating AI and have the generating AI determine the level of detail in the summary.

[0096] The summarization unit can apply different summarization algorithms depending on the text category when generating summaries. For example, in the case of a novel, the summarization unit can apply a summarization algorithm that emphasizes the flow of the story and the relationships between characters. For example, in the case of a business book, the summarization unit can apply a summarization algorithm that extracts important business terms and concepts. Furthermore, in the case of an academic book, the summarization unit can also apply a summarization algorithm that emphasizes specialized terminology and research findings. In this way, the summarization unit can provide more appropriate summaries by applying different summarization algorithms depending on the text category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input text category data into a generating AI and have the generating AI execute the application of the summarization algorithm.

[0097] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, if the user is in a hurry, the summarization unit will provide a short, concise summary. If the user is relaxed, the summarization unit will provide a longer summary with more detailed explanations. The summarization unit can also provide a summary with more specialized content if the user is focused. In this way, the summarization unit can provide a more appropriate summary by adjusting the length of the summary based on the user's emotions. 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 summarization unit may be performed using AI or not using AI. For example, the summarization unit can input user facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0098] The summarization unit can determine the priority of summaries based on the submission date of the text when generating summaries. For example, the summarization unit may prioritize summaries for the most recent texts and postpone summaries for older texts. The summarization unit can also adjust the priority of summaries according to the submission date. This allows the summarization unit to provide more appropriate summaries by determining the priority of summaries based on the submission date of the texts. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input text submission date data into a generation AI and have the generation AI perform the summary priority calculation.

[0099] The summarization unit can adjust the order of summaries based on the relevance of the text during summary generation. For example, the summarization unit might summarize important text first, then text of moderate importance, and finally text of low importance. By adjusting the order of summaries based on the relevance of the text, the summarization unit can provide more appropriate summaries. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input text relevance data into a generation AI and have the generation AI execute the order of summaries.

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

[0101] The analysis unit can monitor the user's reading speed in real time and adjust the method of extracting keywords and phrases according to the reading speed. For example, if the user is speed reading, the analysis unit will prioritize extracting short, important keywords. If the user is reading slowly, it will extract keywords that include detailed phrases and context. Furthermore, if the user's reading speed fluctuates, the analysis unit can dynamically adjust the extraction method accordingly. This allows the analysis unit to provide optimal information according to the user's reading speed.

[0102] The summarization function can analyze the user's reading history and customize the summary style based on the content of books they have read in the past. For example, if a user prefers the summary style of books they have read previously, it will generate summaries based on that style. If a user reads many books of a particular genre, it will apply a summary style appropriate for that genre. It can also prioritize displaying summaries related to specific topics based on the user's reading history. In this way, the summarization function can provide the most suitable summaries based on the user's reading history.

[0103] The analysis unit can estimate the user's emotions and dynamically reconstruct the content of the ebook based on those emotions. For example, if the user is relaxed, the analysis unit will prioritize displaying content suitable for relaxation. If the user is focused, it will prioritize displaying detailed and specialized content. Furthermore, if the user is excited, it can prioritize displaying highly entertaining content. In this way, the analysis unit can provide the most appropriate content according to the user's emotions.

[0104] The highlighting feature can adjust its display method based on the user's device's battery level. For example, when the battery level is low, the highlight color and style can be changed to an energy-saving one. When the battery level is sufficient, the highlighting is displayed as normal. Furthermore, when the battery level is moderate, the frequency and emphasis of the highlighting can also be adjusted. This allows the highlighting feature to provide the optimal display method according to the device's battery status.

[0105] The recommendation system can estimate the user's emotions and change the genre of books it recommends based on those estimates. For example, if the user is relaxed, it will recommend books in a genre suitable for relaxation. If the user is excited, it will recommend books in a genre with high entertainment value. It can also recommend books in an academic genre if the user is focused. In this way, the recommendation system can recommend books in the most appropriate genre based on the user's emotions.

[0106] The analysis unit can monitor the user's reading environment and adjust the keyword and phrase extraction method according to the environment. For example, if the user is reading in a quiet environment, it will extract keywords containing detailed phrases and context. If the user is reading in a noisy environment, it will prioritize extracting short, important keywords. Furthermore, if the user's reading environment changes, the analysis unit can dynamically adjust the extraction method accordingly. This allows the analysis unit to provide optimal information according to the user's reading environment.

[0107] The summarization function can estimate the user's emotions and change the summary format based on those emotions. For example, if the user is relaxed, it can provide a summary in a soft format. If the user is in a hurry, it can provide a summary in a concise and to-the-point format. Furthermore, if the user is focused, it can provide a summary in a format that includes detailed information. This allows the summarization function to provide a summary in the most appropriate format based on the user's emotions.

[0108] The highlighting function can analyze the user's reading history and customize the highlighting display based on the highlighting colors and styles the user has previously preferred. For example, if the user has previously preferred red highlighting, red highlighting will be prioritized. If the user has previously preferred bold highlighting, bold highlighting will be prioritized. It can also extract specific patterns from the user's reading history and suggest the optimal highlighting display. In this way, the highlighting function can provide the most optimal highlighting display based on the user's reading history.

[0109] The recommendation system can estimate the user's emotions and adjust the difficulty level of recommended books based on those estimates. For example, if the user is relaxed, it will recommend easy, relaxing books. If the user is focused, it will recommend more challenging books. It can also recommend highly entertaining books if the user is excited. This allows the recommendation system to recommend books of the optimal difficulty level based on the user's emotions.

[0110] The analysis unit can adjust the method of extracting keywords and phrases based on the user's reading time. For example, if the user is reading at night, it will prioritize extracting keywords and phrases that promote relaxation. If the user is reading during the day, it will extract keywords and phrases that enhance concentration. Furthermore, if the user's reading time fluctuates, the analysis unit can dynamically adjust the extraction method accordingly. This allows the analysis unit to provide optimal information based on the user's reading time.

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

[0112] Step 1: The analysis unit analyzes the text of the ebook. The analysis unit uses natural language processing techniques to extract keywords or phrases from the text content. For example, it can use morphological analysis to segment the text and extract important keywords. It can also use grammatical analysis to analyze the structure of sentences and extract important phrases. Furthermore, it can use semantic analysis to understand the meaning of the text and extract important information. Step 2: The highlighting section highlights the keywords or phrases extracted by the analysis section on the ebook. For example, keywords can be highlighted using color. Important keywords can be displayed in red, and less important keywords in blue. Keywords can also be emphasized by changing the font style. For example, important keywords can be displayed in bold, and less important keywords in italics. Furthermore, keywords can be emphasized by changing the background color. For example, the background of important keywords can be set to yellow, and the background of less important keywords to gray. Step 3: The recommendation team recommends topics from the ebook text that are relevant to the user's preferences. For example, it can recommend topics based on the user's past reading history. It can also recommend topics based on keywords from books the user has read in the past. Furthermore, it can recommend topics based on the user's survey results. For example, it can recommend topics based on topics the user has shown interest in in a survey. In addition, it can recommend topics based on the user's social media activity. For example, it can recommend topics based on topics the user has shown interest in on social media.

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

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

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

[0116] For example, the analysis unit is implemented by the processor 46 of the smart device 14 or the processor 28 of the data processing unit 12. For example, the highlighting unit uses the display 40A of the smart device 14 to highlight keywords and phrases. For example, the recommendation unit is implemented by the identification processing unit 290 of the data processing unit 12 and recommends relevant topics based on the user's preferences. For example, the summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates summaries of long texts or chapters. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0132] For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 or the processor 28 of the data processing unit 12. For example, the highlighting unit uses the display of the smart glasses 214 to highlight keywords and phrases. For example, the recommendation unit is implemented by the identification processing unit 290 of the data processing unit 12 and recommends relevant topics based on the user's preferences. For example, the summarization unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates summaries of long texts or chapters. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0148] For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 or the processor 28 of the data processing unit 12. For example, the highlighting unit uses the display 343 of the headset terminal 314 to highlight keywords and phrases. For example, the recommendation unit is implemented by the specific processing unit 290 of the data processing unit 12 and recommends relevant topics based on the user's preferences. For example, the summarization unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates summaries of long texts or chapters. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0165] For example, the analysis unit is implemented by the processor 46 of the robot 414 or the processor 28 of the data processing unit 12. For example, the highlighting unit uses the display of the robot 414 to highlight keywords and phrases. For example, the recommendation unit is implemented by the specific processing unit 290 of the data processing unit 12 and recommends relevant topics based on the user's preferences. For example, the summarization unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates summaries of long texts or chapters. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0184] (Note 1) The analysis unit analyzes the text of the ebook, A highlighting unit that displays keywords and phrases extracted by the analysis unit on the e-book, The aforementioned e-book includes a section that recommends topics related to the user's preferences from the text of the e-book. A system characterized by the following features. (Note 2) It further includes a summary section that displays summaries of texts longer than a certain threshold and summaries of each chapter. The system described in Appendix 1, characterized by the features described herein. (Note 3) The summary section above is, Display the key points in list format. The system described in Appendix 2, characterized by the features described herein. (Note 4) The aforementioned analysis unit, The keywords and phrases extracted from the aforementioned e-books will be changed according to the genre of the book. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, Extract keywords or phrases from text content using natural language processing techniques. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, It includes a unit that estimates the user's emotions, and modifies the keywords or phrases extracted from the e-book based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, Based on the user's past reading history, keywords or phrases are extracted from the aforementioned e-book. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, Prioritize extracting specific technical terms or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It includes a section for estimating user sentiment and modifies the keywords or phrases extracted based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, Depending on the genre of the book, different natural language processing algorithms are applied. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, Analyze the user's past reading history and extract the most relevant keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, It includes a unit that estimates user emotions and determines the priority of analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, Change the keywords or phrases to extract based on the book's publication year. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, Considering the author information of a book, extract keywords or phrases that match the style of a specific author. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned highlight section is, It includes a section that estimates the user's emotions and changes the highlight color and style based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned highlight section is, When highlighting, different emphasis methods are applied based on the importance of the keywords. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned highlight section is, When highlighting content, the system will refer to the user's past highlighting history to select the optimal display method. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned highlight section is, It includes a section that estimates the user's emotions and adjusts the order of highlights based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned highlight section is, When highlighting, the system selects the optimal display method considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned highlight section is, When highlighting text, the system analyzes the user's reading speed and displays highlights at the appropriate time. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned recommendation department, It includes a section for estimating user sentiment and changes the recommended topics based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned recommendation department, When making recommendations, the system analyzes the user's past reading history to suggest the most suitable topics. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned recommendation department, When making recommendations, customize topics based on the user's current reading status. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned recommendation department, It includes a section for estimating user sentiment and determines recommendation priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned recommendation department, When making recommendations, the system takes the user's geographical location into consideration to suggest highly relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned recommendation department, When making recommendations, the system analyzes the user's social media activity and recommends relevant topics. The system described in Appendix 1, characterized by the features described herein. (Note 27) The summary section above is, It includes a section for estimating user emotions and adjusts the way the summary is presented based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the text. The system described in Appendix 2, characterized by the features described herein. (Note 29) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the text category. The system described in Appendix 2, characterized by the features described herein. (Note 30) The summary section above is, It includes a section for estimating user sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 31) The summary section above is, When generating summaries, prioritize summaries based on when the text was submitted. The system described in Appendix 2, characterized by the features described herein. (Note 32) The summary section above is, When generating summaries, the order of the summaries is adjusted based on the relevance of the text. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

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

Claims

1. The analysis unit analyzes the text of the ebook, A highlighting unit that displays keywords and phrases extracted by the analysis unit on the e-book, The aforementioned e-book includes a section that recommends topics related to the user's preferences from the text of the e-book. A system characterized by the following features.

2. It further includes a summary section that displays summaries of texts longer than a certain threshold and summaries of each chapter. The system according to feature 1.

3. The summary section above is, Display the key points in list format. The system according to feature 2.

4. The aforementioned analysis unit, The keywords and phrases extracted from the aforementioned e-books will be changed according to the genre of the book. The system according to feature 1.

5. The aforementioned analysis unit, Extract keywords or phrases from text content using natural language processing techniques. The system according to feature 1.

6. The aforementioned analysis unit, It includes a unit that estimates the user's emotions, and modifies the keywords or phrases extracted from the e-book based on the estimated user emotions. The system according to feature 1.

7. The aforementioned analysis unit, Based on the user's past reading history, keywords or phrases are extracted from the aforementioned e-book. The system according to feature 1.

8. The aforementioned analysis unit, Prioritize extracting specific technical terms or phrases. The system according to feature 1.

9. The aforementioned analysis unit, It includes a section for estimating user sentiment and modifies the keywords or phrases extracted based on the estimated user sentiment. The system according to feature 1.

Images