System

Abstract

A system is provided.SOLUTION: A system comprising: means for storing information; means for extracting key claims from the information using generative artificial intelligence to analyze the information; means for quantifying the key claims; and means for visually displaying the quantified key claims.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Because business books are so diverse, the volume of information and diverse viewpoints can make it difficult to determine which information is correct. Furthermore, the diversity of specific claims and opinions makes reading business books a daunting task. Therefore, there is a need for a system that allows readers to quickly grasp the main points and important claims. [Means for solving the problem]

[0005] This invention is a system that includes a means for storing information, a means for extracting key points from the information using a generative artificial intelligence that analyzes the information, a means for quantifying the key points, and a means for visually displaying the quantified key points. Specifically, the system reads e-book data, analyzes its contents using a natural language processing model, and quantifies the main points using TF-IDF. The system then displays the numerical data in a visual format such as a graph, allowing readers to understand the key points at a glance.

[0006] "Means for storing information" refers to the functionality for storing e-book data and other text data.

[0007] "Generative AI for information analysis" refers to AI technology, including natural language processing models, that has the ability to extract key points or insights from text data.

[0008] "Key point extraction methods" refers to algorithms and techniques that analyze information and automatically identify key points and points within it.

[0009] "Means for quantifying key claims" refers to a function for quantitatively evaluating extracted claims and points and expressing their importance numerically.

[0010] "Visual display means" refers to the ability to display quantified key assertions in the form of graphs, diagrams, charts, etc.

[0011] "E-book data" refers to the content of a book stored in digital form.

[0012] A "natural language processing model" is a machine learning model for understanding and analyzing text data, and includes technology for capturing the meaning and context of text.

[0013] TF-IDF (Term Frequency-Inverse Document Frequency) is a numerical method for assessing the importance of words in a document, indicating how important a particular word is to a particular document. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This system stores information from business books, analyzes it to extract key points, and then quantifies and visually displays those points, allowing readers to quickly grasp important content. A specific embodiment of this system is described below.

[0036] 1. Loading book data

[0037] Subject: Server

[0038] The server reads the electronic data of business books from a specific directory. The electronic data is stored in text files, and the server opens these files and stores their contents in memory.

[0039] 2. Text Preprocessing

[0040] Subject: Server

[0041] The server preprocesses the book data it has loaded. This process removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format that is easy to analyze.

[0042] 3. Content analysis and assertion extraction

[0043] Subject: Server

[0044] The server passes the preprocessed text data to the generative AI, which analyzes its content. The generative AI uses a natural language processing model to extract key points and arguments from the text. This step makes it possible to automatically find summaries and key phrases from large amounts of text data.

[0045] 4. Quantifying your claims

[0046] Subject: Server

[0047] The server quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This allows us to quantitatively indicate which claims are more important.

[0048] 5. Providing results

[0049] Subject: Server

[0050] The server visually displays the key quantified claims. Specifically, it converts the numerical data into graphs and charts and provides them in a format that users can understand at a glance. Visual displays such as bar graphs and pie charts are used.

[0051] Specific examples

[0052] For example, if a user wishes to analyze several business books on "Business Leadership," the following process may be performed.

[0053] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt".

[0054] 2. The server preprocesses the book data, removing unnecessary line breaks and special characters and splitting the text into words.

[0055] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership," "driving innovation," and "effective communication."

[0056] 4. The server quantifies the claims and assigns a score to each claim to assess its importance.

[0057] 5. The server provides the results to the user and creates graphs and charts that visually show the scores of the extracted claims.

[0058] This allows users to see the main points of multiple books on "business leadership" at a glance, allowing them to acquire knowledge efficiently.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[0062] Step 2:

[0063] The server preprocesses the book data it has loaded, removing unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). The text data for each book is then converted into a clean format, ready for analysis.

[0064] Step 3:

[0065] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[0066] Step 4:

[0067] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and calculates an importance score for each claim.

[0068] Step 5:

[0069] The server visually displays the quantified claims. This process uses the numerical data to generate graphs and charts. For example, a bar graph can be used to visually show the importance score of each claim.

[0070] Step 6:

[0071] The user checks the results provided by the server. By viewing the visualized data, the user can understand the main points and important arguments of multiple business books at a glance, which helps them gather information efficiently and make decisions.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] In recent years, with the increase in the amount of information, there has been a growing need to quickly extract important information from electronic data such as many books and papers and effectively understand it. However, conventional methods have had difficulty efficiently processing large amounts of information, extracting key points, and visually presenting them. Therefore, this invention provides a system that automatically and efficiently extracts important points from electronic data, quantifies them, and visualizes them, allowing users to quickly grasp important content.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for reading electronic data from a specific directory, means for preprocessing to remove unnecessary characters and divide the text into tokens, means for extracting key claims from the preprocessed data using a generative AI model, means for quantifying the key claims using TF-IDF, and means for visually displaying the quantified key claims. This allows important information to be efficiently extracted from electronic data, enabling users to quickly grasp the information.

[0077] The following definitions are provided for key terms contained in the claims:

[0078] A "specific directory" refers to a folder or path designated for the server to search for electronic data.

[0079] "Electronic data" refers to files containing written information stored in digital format, such as books, papers, and articles.

[0080] "Preprocessing" refers to a series of operations that remove unnecessary characters from text data and convert it into a format that is easy to analyze.

[0081] A "token" refers to a unit into which text data is divided into words or phrases when analyzing the data.

[0082] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate claims or summaries from text data.

[0083] "Key points" refers to phrases or sentences that indicate the most important information or points in electronic data.

[0084] "TF-IDF" stands for Term Frequency-Inverse Document Frequency and refers to a numerical method for evaluating the importance of terms in text data.

[0085] "Visual display" refers to presenting numerical data in a graphical format such as a graph or chart, so that the user can intuitively understand it.

[0086] This system is designed to efficiently analyze electronic data, extract important assertions, and visually display them. A specific embodiment of this system will be described below.

[0087] The server reads electronic data from a specific directory. For example, it identifies all text files in the " / data / books" folder, opens them, and reads their contents. A computing device with high I / O performance is recommended as the hardware used. The read contents are stored in memory for further processing.

[0088] Next, the server preprocesses the book data it has loaded. Specifically, it uses the Python "re" module to remove unnecessary line breaks and special characters, and then uses the "nltk" library to convert the text to lowercase and split it into tokens (words). This preprocessing prepares the text data in a format that is easy to analyze.

[0089] The preprocessed text data is passed to a generative AI model. The server uses the generative AI model to analyze the text data and extract key assertions. The prompt used is, "Please extract three key assertions about business leadership from the text below." A well-known natural language processing model is suitable as the AI ​​model to use.

[0090] The extracted claims are quantified. Specifically, a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF) is performed using the "scikit-learn" library. This gives a numerical value to the importance of each claim, allowing us to determine which claims are more important.

[0091] Finally, the server visually displays the quantified claims, using Python's matplotlib and plotly libraries to convert the numerical data into graphs and charts, which are displayed in an intuitive format for users to quickly grasp the key points.

[0092] For example, if a user wants to analyze several books on "business leadership," the process would proceed as follows: The server collects book data such as "LeadershipGuide.txt" and "InnovationInManagement.txt," performs preprocessing, and then uses a generative AI model to extract assertions such as "the importance of leadership," "driving innovation," and "effective communication." The extracted assertions are then quantified and displayed visually.

[0093] Example prompt sentence:

[0094] "Identify three key assertions about business leadership from the text below."

[0095] The above is a specific embodiment of this system.

[0096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0097] Step 1:

[0098] The server reads electronic data from a specific directory. Specifically, the server accesses the " / data / books" folder and identifies the ".txt" files stored there. It opens each file and reads its contents into memory. Examples include files such as "LeadershipGuide.txt" and "InnovationInManagement.txt." In this step, the input is the electronic data file, and the output is the text data read into memory.

[0099] Step 2:

[0100] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed using Python's "re" module. Then, the "nltk" library is used to convert the text to lowercase and split it into tokens (words). For example, "Miyamoto Musashi is a Japanese samurai" is converted to "Miyamoto grapes are Japanese samurai." In this step, the input is the loaded text data, and the output is the preprocessed, clean text data.

[0101] Step 3:

[0102] The server passes the preprocessed text data to a generative AI model to extract key claims. Specifically, a generative AI model (e.g., a natural language processing model) is used to analyze the text content based on a prompt. The prompt used here is, "From the text below, please extract three key claims about business leadership." In this step, the input is the preprocessed text data and the prompt, and the output is the claim extraction results from the generative AI model.

[0103] Step 4:

[0104] The server quantifies the claims extracted from the generative AI model. Specifically, it uses the "scikit-learn" library to perform a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF). For example, the claim "The importance of leadership" is quantified to have a TF-IDF score of 0.85. In this step, the input is the extracted claim, and the output is the claim quantified by the TF-IDF score.

[0105] Step 5:

[0106] The server visually displays the quantified claims. Specifically, it uses Python's "matplotlib" and "plotly" libraries to convert the numerical data into graphs and charts. For example, it displays important claims and their importance as a bar graph. In this step, the input is the quantified claims, and the output is a visually displayed graph or chart. Users can use this to quickly grasp the important content.

[0107] (Application example 1)

[0108] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0109] Conventional information provision systems for business books have difficulty quickly and accurately extracting important points from vast amounts of text data and presenting them visually. Furthermore, it takes a great deal of time and effort for users to manually search for important information, making it impossible to efficiently gather information or acquire knowledge.

[0110] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0111] In this invention, the server includes means for storing book data, means for performing preprocessing of the book data, means for analyzing the book data using a natural language processing model, means for extracting and quantifying key claims, and means for converting the quantified key claims into visual display data, thereby enabling users to quickly and accurately grasp the important claims of the book data and effectively visually understand its contents.

[0112] "Information" means data that is collected, stored, and analyzed for a specific purpose.

[0113] "Generative artificial intelligence" refers to sophisticated algorithms that analyze specific input data and automatically generate important information or assertions.

[0114] A "main argument" is the most important, core information or opinion extracted from a text or data.

[0115] "Quantification" is the process of quantitatively evaluating the information value of text or data, and specifically refers to expressing importance and frequency numerically.

[0116] "Visually displaying" refers to the act of visually presenting quantified data or information in the form of graphs, charts, etc.

[0117] "Preprocessing" is the process of initially preparing book data and other information to prepare it in an analyzable format.

[0118] A "natural language processing model" refers to a machine learning model for analyzing, understanding, and generating human language.

[0119] A "summary" is a method of expressing the content of an original text concisely by abbreviating and presenting the main points of the text.

[0120] A "prompt" is text that is input to a generative AI model to cause it to generate a specific output.

[0121] A specific embodiment of the present invention will now be described. First, the server is equipped with a means for storing book data. Using this means, the server reads electronic book data from a specific directory and stores the contents in memory. The read electronic book data is saved in text file format.

[0122] The server then preprocesses the book data, removing unnecessary line breaks and special characters, converting the text to lower case, and splitting it into tokens (words). This process prepares the data in a format that is easy to analyze.

[0123] The server then analyzes the pre-processed text data using a generative AI that includes a natural language processing model. This analysis method uses the natural language processing model to extract key points or points from the text data. To do this, the server uses a generative AI model and inputs prompts such as the following into the model:

[0124] "Please extract key points about business leadership."

[0125] The server then quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This quantification method makes it possible to quantitatively indicate which claims are more important.

[0126] Finally, the server uses a means to visually display the quantified key points by converting the numerical data into graphs and charts and presenting them to the user on their device screen in a format that can be easily understood at a glance, such as bar graphs or pie charts.

[0127] For example, if a user wants to analyze a book on "Business Leadership," the server collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" and preprocesses them. It then uses a generative AI model to analyze the content, extracting key assertions such as "The Importance of Leadership," "Driving Innovation," and "Effective Communication," and quantifying them. It then creates graphs and charts and presents the results to the user on their device, allowing them to easily grasp the key points.

[0128] In this way, the system can quickly and accurately extract important points from business books and present them visually, allowing users to effectively gather information and acquire knowledge.

[0129] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0130] Step 1:

[0131] The server reads e-book data from a specific directory and stores it in memory. As input, the e-book data is given in the form of a text file. The server opens the file, reads its contents, and generates text data as output to store in memory.

[0132] Step 2:

[0133] The server performs preprocessing on the read text data. The text data obtained in step 1 is used as input. The server removes unnecessary line breaks and special characters, converts the text to lower case, and splits it into tokens (words). The output is the preprocessed tokenized text data.

[0134] Step 3:

[0135] The server uses a natural language processing model to parse the preprocessed text data, using as input the tokenized text data generated in step 2. The server inputs the generative AI model using the following prompt sentence:

[0136] "Please extract key points about business leadership."

[0137] The generative AI model extracts key points and summaries and outputs them in summary form.

[0138] Step 4:

[0139] The server then quantifies the extracted claims. The claims extracted in step 3 are used as input. The server then numerically evaluates the importance of each claim using TF-IDF (Term Frequency-Inverse Document Frequency). The output is a quantified importance score.

[0140] Step 5:

[0141] The server converts the quantified key claims into visual display data, using the quantified importance scores from step 4 as input. The server converts these scores into graphs and charts to generate visually displayable data. The output is the visual display data.

[0142] Step 6:

[0143] The terminal displays the visual display data provided by the server on its screen. The visual display data sent from the server is used as input. The terminal displays graphs and charts in a format that the user can understand at a glance and provides them to the user. As output, a display that the user can visually understand is obtained.

[0144] In this way, the specific operation has been explained while clarifying the input and output at each step.

[0145] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0146] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main arguments, and visually displays them, with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0147] 1. Loading book data

[0148] Subject: Server

[0149] The server loads the electronic data of business books from the specified directory. These are saved in text file format, and the server opens the files and stores their contents in memory. For example, a file such as "LeadershipGuide.txt" is loaded.

[0150] 2. Text Preprocessing

[0151] Subject: Server

[0152] The server preprocesses the book data it has loaded. This preprocessing removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[0153] 3. Content analysis and assertion extraction

[0154] Subject: Server

[0155] The server then passes the preprocessed text data to a generative AI system, which analyzes the content using a natural language processing model. This process extracts key points and key ideas from the text, such as "the importance of leadership" and "driving innovation."

[0156] 4. Quantifying your claims

[0157] Subject: Server

[0158] The server then quantifies the extracted key claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate how important each claim is. This results in an importance score being assigned to each claim.

[0159] 5. User Emotion Recognition

[0160] Subject: Server

[0161] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's face through a camera to determine the emotion.

[0162] 6. Providing and adjusting results

[0163] Subject: Server

[0164] The server visually displays the key points, quantified. At this stage, the display is dynamically adjusted based on the user's emotions, as recognized by the emotion engine. For example, if the user is excited, a colorful graph is used to emphasize the main points.

[0165] Specific examples

[0166] For example, if a user wishes to analyze several business books on "business leadership," the following process may be performed:

[0167] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the directory.

[0168] 2. The server preprocesses the book data, removing unnecessary characters and splitting the text into tokens.

[0169] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership" and "driving innovation."

[0170] 4. The server quantifies the claims and uses TF-IDF to evaluate the importance score of each claim.

[0171] 5. The server recognizes the user's emotions and determines their feelings based on facial expression analysis and text input.

[0172] 6. The server provides the results to the user, highlighting key points based on the user's emotions, for example, using colorful graphs if the user is excited.

[0173] This allows users to quickly understand important points from multiple business books, and since their emotions are also taken into consideration in the process, they can receive more personalized information.

[0174] The processing flow will be explained below.

[0175] Step 1:

[0176] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[0177] Step 2:

[0178] The server preprocesses the book data it has loaded. Specifically, it removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[0179] Step 3:

[0180] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[0181] Step 4:

[0182] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and assigns each claim an importance score.

[0183] Step 5:

[0184] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's facial expression through a camera to determine the emotion.

[0185] Step 6:

[0186] The server uses the emotional information obtained from the emotion engine to visually display the quantified claims. This process converts the numerical data into graphs and charts, providing them in a format that users can understand at a glance. The display method is dynamically adjusted based on the user's emotional state. For example, if the user is excited, a colorful graph will be used to emphasize the main points.

[0187] Step 7:

[0188] The user checks the results provided by the server. By viewing visualized data, the user can understand the main points and important arguments of multiple business books at a glance. Personalized information provided according to the user's emotional state allows the user to collect information more effectively and use it to make decisions.

[0189] Example 2

[0190] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0191] Conventional business book analysis systems can extract the main arguments from books and display them in numerical form, but they have the problem of not being able to provide personalized information without taking into account the user's emotions, making it difficult to improve user understanding and satisfaction.

[0192] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0193] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative model that analyzes the information, means for quantifying the main claims, means for visually displaying the quantified main claims, means including an emotion engine for recognizing a user's emotion, and means for dynamically adjusting the display method based on the recognized emotion. This makes it possible to effectively present the main claims of business books while taking the user's emotion into consideration.

[0194] "Information storage means" refers to a device or system that has the function of storing and managing electronic data of business books.

[0195] A "generative model" is a computational model that uses natural language processing to extract key points or insights from text data.

[0196] A "means for extracting key claims" is a device or system that has the functionality to use a generative model to find important claims and information from electronic data of business books.

[0197] The "means for quantifying key claims" is a device or system that has the function of quantitatively evaluating and scoring the importance of extracted claims.

[0198] A "visual display means" is a device or system capable of presenting a quantified assertion to a user in a visual format, such as a graph or chart.

[0199] The "emotion engine" is a calculation engine that recognizes and determines emotions through user text input and facial expression analysis.

[0200] A "dynamic adjustment means" is a device or system that has the capability to adapt the content and manner of display in real time based on the recognized user emotion.

[0201] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main points, and visually displays them, with an emotion engine that recognizes the user's emotions. The following describes how this system is specifically implemented.

[0202] Loading book data

[0203] Subject: Server

[0204] The server reads the electronic data of business books from a specified directory. This data is stored in text file format, and the server opens each file and stores its contents in memory. For example, it reads files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the " / data / books" directory. This process uses a file management system and a software library for input / output operations.

[0205] Text Preprocessing

[0206] Subject: Server

[0207] The server preprocesses the loaded book data. This preprocessing involves using regular expressions to remove unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). This prepares the text data in a format suitable for analysis. The software used includes natural language processing libraries (e.g., NLTK, SpaCy).

[0208] Content analysis and assertion extraction

[0209] Subject: Server

[0210] The server passes the preprocessed text data to a generative AI model for natural language processing. During this process, the generative AI model extracts key points and insights from the text. Specifically, models such as BERT and GPT-3 are used as generative AI models. For example, assertions such as "the importance of leadership" and "driving innovation" are extracted.

[0211] Quantifying claims

[0212] Subject: Server

[0213] The server then quantifies the extracted key claims. Specifically, it uses the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm to numerically evaluate the importance of each claim. For example, "importance of leadership" is assigned a score of 0.8, and "promotion of innovation" is assigned a score of 0.6.

[0214] User Emotion Recognition

[0215] Subject: Server

[0216] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. It analyzes the user's face through a camera to determine their emotion. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[0217] Providing and adjusting results

[0218] Subject: Server

[0219] The server visually displays the key points quantified. At this stage, the display method is dynamically adjusted based on the user's emotions, which are recognized by the emotion engine. For example, if the user is excited, colorful graphs are used to emphasize the main points. For this purpose, data visualization libraries (e.g., D3.js, Matplotlib) are used.

[0220] Specific examples

[0221] As a concrete example, consider a case where a user wants to analyze several business books on "Business Leadership." The following process is performed:

[0222] 1. The server reads the book data and scans "LeadershipGuide.txt", "InnovationInManagement.txt", etc. to obtain the contents.

[0223] 2. The server performs preprocessing, removing unnecessary characters and splitting the text into tokens.

[0224] 3. The server uses generative AI to extract key points, such as "The importance of leadership."

[0225] 4. The server quantifies the importance of the claims using TF-IDF and assigns an importance score to each claim.

[0226] 5. The server analyzes the user's emotions using the camera and microphone to determine their current emotions.

[0227] 6. The server adjusts the visual display based on emotion, highlighting key points with colorful graphs.

[0228] Prompt Sentence Examples

[0229] Use the following as an example prompt for the generative AI model:

[0230] "Summarize the contents of the following business books and extract the main points: LeadershipGuide.txt, InnovationInManagement.txt. Also, analyze user sentiment to highlight key points."

[0231] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0232] Step 1: Loading the book data

[0233] Subject: Server

[0234] The server reads the electronic data of the business book from the specified directory.

[0235] (Input): Directory path " / data / books"

[0236] (Specific behavior): Scan the " / data / books" directory and find files such as "LeadershipGuide.txt" and "InnovationInManagement.txt". Then, open each file one by one and store its contents in memory. If the contents of the text file are in Unicode format, check the encoding and decode it appropriately.

[0237] (Output): Text data stored in memory

[0238] Step 2: Preprocessing the text

[0239] Subject: Server

[0240] The server preprocesses the loaded book data.

[0241] (Input): Text data stored in memory

[0242] (Specific operation): As a preprocessing step, unnecessary line breaks and special characters are removed using regular expressions, and the text is converted to all lowercase. After that, the text is split into tokens by whitespace characters. For example, the sentence "The Leader is ..." is converted to lowercase "the leader is ..." and split into tokens. A natural language processing library (e.g., NLTK, SpaCy) is used for this process.

[0243] (Output): Tokenized word list

[0244] Step 3: Analyze content and extract claims

[0245] Subject: Server

[0246] The server passes the preprocessed data to the generative AI model for natural language processing.

[0247] (Input): Tokenized word list

[0248] (Specific operation): Pass the tokenized data to a generative AI model along with a prompt to extract the main claim. For example, use BERT or GPT-3 as the generative AI model. Provide the prompt "Extract the main claim from the following text: 'the leader is...'". The model will return claims such as "The importance of leadership" and "Promoting innovation".

[0249] (Output): List of extracted key claims

[0250] Step 4: Quantify your claims

[0251] Subject: Server

[0252] The server quantifies the extracted key assertions.

[0253] (Input): List of extracted key claims

[0254] (Specific behavior): Using the TF-IDF algorithm, the importance of each claim is evaluated. For example, "importance of leadership" is assigned a score of 0.8, and "driving innovation" is assigned a score of 0.6. This process is performed using machine learning libraries such as SciKit-Learn.

[0255] (Output): A list of claims and their TF-IDF scores

[0256] Step 5: Recognizing User Emotions

[0257] Subject: Server

[0258] The server uses an emotion engine to recognize the user's emotions.

[0259] (Input): Real-time video and audio data of the user

[0260] (Specific operation): Analyzes the user's facial expressions and voice in real time using a camera and microphone. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[0261] (Output): User's emotional data (e.g., "happy," "confused," etc.)

[0262] Step 6: Delivering and adjusting results

[0263] Subject: Server

[0264] The server visually displays the quantified claims and dynamically adjusts the display content based on the user's emotions.

[0265] (Input): A list of claims and their TF-IDF scores, and user sentiment data

[0266] (Specific Action): Present your main argument in a visual format such as a graph or chart. For example, if the user is excited, use a colorful graph to emphasize the point. Use a data visualization library (e.g., D3.js, Matplotlib) for this process.

[0267] (Output): A dynamically adjusted visual display presented to the user.

[0268] (Application example 2)

[0269] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0270] It is difficult to extract the main points from information-rich documents such as business books and to understand them efficiently. In addition, there is a need for technology that can provide more personalized information by adjusting the display method according to the emotional state of each individual user.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0272] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative artificial intelligence that analyzes the information, means for quantifying the main claims, means for recognizing a user's emotions, means for dynamically adjusting the display method of the quantified main claims based on the user's emotions, and means for visually displaying the quantified main claims. This allows a user to quickly understand important points from multiple books and, in the process, receive more satisfying information through a display method that takes the user's emotional state into consideration.

[0273] "Means for storing information" is a function for saving text data such as business books in a storage device.

[0274] "Generative AI" is an AI technology that uses natural language processing to analyze text data and extract key points.

[0275] "Means for extracting key points" is a function for finding and extracting important points and points from text data.

[0276] The "means for quantifying the main claims" is a function for calculating the importance of the extracted claims and evaluating them numerically.

[0277] "Means for recognizing user emotions" refers to technology that uses a camera or text input to analyze and determine a user's emotional state.

[0278] The "means for dynamically adjusting the display method" is a function for changing the display method of an assertion in real time based on the recognized user sentiment.

[0279] "Visual display means" refers to techniques for presenting analyzed information and key arguments in a form that can be seen by the user, such as graphs, charts, or text.

[0280] This invention is a system that analyzes information from business books, extracts and quantifies key points, and dynamically adjusts the display method of the results by recognizing the user's emotions. This system is composed of a means for storing information, a generative artificial intelligence that analyzes the information, a means for quantifying key points, a means for recognizing the user's emotions, a means for dynamically adjusting the display method, and a means for visually displaying the quantified key points.

[0281] Program processing explanation

[0282] The server reads the digital data of business books from a specified directory and stores it in memory. The read text data is preprocessed to remove unnecessary line breaks and special characters and divide the text into tokens. This text data is then passed to a generative AI model for analysis and content extraction. The generative AI model uses natural language processing techniques to extract and quantify key points.

[0283] To recognize a user's emotions, the server analyzes the user's emotional state using a camera or text input. Image processing libraries such as OpenCV and dedicated emotion recognition models are used for emotion analysis. After the corresponding emotion is determined, the information is used to dynamically adjust the display method.

[0284] Specifically, if the user is "excited," the extracted assertions are emphasized using colorful graphs, etc. On the other hand, if the user is "neutral," the standard display method is applied. This allows the user to visually understand the information in a way that is appropriate for their emotions.

[0285] The device provides visually displayed assertions, which the user can receive through a display or head-mounted display, allowing the user to quickly understand important points from multiple business publications and receive personalized information according to emotional changes.

[0286] Specific examples

[0287] A user loads a book on "Business Leadership." Files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" are collected from the directory by the server. The server then preprocesses the data and passes it to a generative AI model to extract key assertions, such as "The Importance of Leadership" and "Driving Innovation." These assertions are then quantified using TF-IDF. Meanwhile, the user's emotions are analyzed from a photo (e.g., "user_image.jpg"), which is determined to indicate "excitement." Based on this information, the extracted assertions are highlighted in a colorful graph and presented to the user.

[0288] Prompt Sentence Examples

[0289] Prompt: "Extract the main idea from this text:\nText: XXXX"

[0290] This embodiment helps users quickly understand the main arguments of a business book in a manner that is responsive to their emotional state.

[0291] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0292] Step 1:

[0293] The server reads the digital data of a business book from the specified directory. Specifically, it opens a file such as "LeadershipGuide.txt" and stores its contents in memory. The input is the path to the e-book file, and the output is the read text data.

[0294] Step 2:

[0295] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed, all characters are converted to lowercase, and the data is split into tokens (words). The input is the loaded text data, and the output is the preprocessed text data.

[0296] Step 3:

[0297] The server passes the preprocessed text data to the generative AI model, which then uses natural language processing techniques to extract key claims. The input is the preprocessed text data, and the output is the extracted key claims (key phrases). Specifically, the system uses the Hugging Face Transformer model.

[0298] Step 4:

[0299] The server uses TF-IDF to quantify the extracted key claims. The input is the extracted key claims, and the output is the importance score of the key claims. Specifically, we use TfidfVectorizer to calculate the weight of each claim.

[0300] Step 5:

[0301] The server analyzes the user's face captured through a camera to recognize the user's emotions. The input is the user's facial image data, and the output is the determined user's emotional state. Specifically, OpenCV and an emotion recognition model are used.

[0302] Step 6:

[0303] The server dynamically adjusts the display of the quantified key claim based on the user's perceived emotion. The input is the key claim importance score and the user's emotional state, and the output is the adjusted display format. For example, if the user is excited, it is displayed as a colorful graph, and if the user is neutral, it is displayed as standard text.

[0304] Step 7:

[0305] The server visually displays the quantified key assertions in the adjusted display format. The input is the adjusted display format, and the output is the visual content displayed on the user's device. Specifically, it is presented to the user via a display or head-mounted display.

[0306] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0307] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0308] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0309] [Second embodiment]

[0310] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0311] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0312] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0313] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0314] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0315] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0316] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0317] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0318] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0319] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0320] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0321] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0322] This system stores information from business books, analyzes it to extract key points, and then quantifies and visually displays those points, allowing readers to quickly grasp important content. A specific embodiment of this system is described below.

[0323] 1. Loading book data

[0324] Subject: Server

[0325] The server reads the electronic data of business books from a specific directory. The electronic data is stored in text files, and the server opens these files and stores their contents in memory.

[0326] 2. Text Preprocessing

[0327] Subject: Server

[0328] The server preprocesses the book data it has loaded. This process removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format that is easy to analyze.

[0329] 3. Content analysis and assertion extraction

[0330] Subject: Server

[0331] The server passes the preprocessed text data to the generative AI, which analyzes its content. The generative AI uses a natural language processing model to extract key points and arguments from the text. This step makes it possible to automatically find summaries and key phrases from large amounts of text data.

[0332] 4. Quantifying your claims

[0333] Subject: Server

[0334] The server quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This allows us to quantitatively indicate which claims are more important.

[0335] 5. Providing results

[0336] Subject: Server

[0337] The server visually displays the key quantified claims. Specifically, it converts the numerical data into graphs and charts and provides them in a format that users can understand at a glance. Visual displays such as bar graphs and pie charts are used.

[0338] Specific examples

[0339] For example, if a user wishes to analyze several business books on "Business Leadership," the following process may be performed.

[0340] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt".

[0341] 2. The server preprocesses the book data, removing unnecessary line breaks and special characters and splitting the text into words.

[0342] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership," "driving innovation," and "effective communication."

[0343] 4. The server quantifies the claims and assigns a score to each claim to assess its importance.

[0344] 5. The server provides the results to the user and creates graphs and charts that visually show the scores of the extracted claims.

[0345] This allows users to see the main points of multiple books on "business leadership" at a glance, allowing them to acquire knowledge efficiently.

[0346] The processing flow will be explained below.

[0347] Step 1:

[0348] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[0349] Step 2:

[0350] The server preprocesses the book data it has loaded, removing unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). The text data for each book is then converted into a clean format, ready for analysis.

[0351] Step 3:

[0352] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[0353] Step 4:

[0354] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and calculates an importance score for each claim.

[0355] Step 5:

[0356] The server visually displays the quantified claims. This process uses the numerical data to generate graphs and charts. For example, a bar graph can be used to visually show the importance score of each claim.

[0357] Step 6:

[0358] The user checks the results provided by the server. By viewing the visualized data, the user can understand the main points and important arguments of multiple business books at a glance, which helps them gather information efficiently and make decisions.

[0359] Example 1

[0360] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0361] In recent years, with the increase in the amount of information, there has been a growing need to quickly extract important information from electronic data such as many books and papers and effectively understand it. However, conventional methods have had difficulty efficiently processing large amounts of information, extracting key points, and visually presenting them. Therefore, this invention provides a system that automatically and efficiently extracts important points from electronic data, quantifies them, and visualizes them, allowing users to quickly grasp important content.

[0362] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0363] In this invention, the server includes means for reading electronic data from a specific directory, means for preprocessing to remove unnecessary characters and divide the text into tokens, means for extracting key claims from the preprocessed data using a generative AI model, means for quantifying the key claims using TF-IDF, and means for visually displaying the quantified key claims. This allows important information to be efficiently extracted from electronic data, enabling users to quickly grasp the information.

[0364] The following definitions are provided for key terms contained in the claims:

[0365] A "specific directory" refers to a folder or path designated for the server to search for electronic data.

[0366] "Electronic data" refers to files containing written information stored in digital format, such as books, papers, and articles.

[0367] "Preprocessing" refers to a series of operations that remove unnecessary characters from text data and convert it into a format that is easy to analyze.

[0368] A "token" refers to a unit into which text data is divided into words or phrases when analyzing the data.

[0369] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate claims or summaries from text data.

[0370] "Key points" refers to phrases or sentences that indicate the most important information or points in electronic data.

[0371] "TF-IDF" stands for Term Frequency-Inverse Document Frequency and refers to a numerical method for evaluating the importance of terms in text data.

[0372] "Visual display" refers to presenting numerical data in a graphical format such as a graph or chart, so that the user can intuitively understand it.

[0373] This system is designed to efficiently analyze electronic data, extract important assertions, and visually display them. A specific embodiment of this system will be described below.

[0374] The server reads electronic data from a specific directory. For example, it identifies all text files in the " / data / books" folder, opens them, and reads their contents. A computing device with high I / O performance is recommended as the hardware used. The read contents are stored in memory for further processing.

[0375] Next, the server preprocesses the book data it has loaded. Specifically, it uses the Python "re" module to remove unnecessary line breaks and special characters, and then uses the "nltk" library to convert the text to lowercase and split it into tokens (words). This preprocessing prepares the text data in a format that is easy to analyze.

[0376] The preprocessed text data is passed to a generative AI model. The server uses the generative AI model to analyze the text data and extract key assertions. The prompt used is, "Please extract three key assertions about business leadership from the text below." A well-known natural language processing model is suitable as the AI ​​model to use.

[0377] The extracted claims are quantified. Specifically, a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF) is performed using the "scikit-learn" library. This gives a numerical value to the importance of each claim, allowing us to determine which claims are more important.

[0378] Finally, the server visually displays the quantified claims, using Python's matplotlib and plotly libraries to convert the numerical data into graphs and charts, which are displayed in an intuitive format for users to quickly grasp the key points.

[0379] For example, if a user wants to analyze several books on "business leadership," the process would proceed as follows: The server collects book data such as "LeadershipGuide.txt" and "InnovationInManagement.txt," performs preprocessing, and then uses a generative AI model to extract assertions such as "the importance of leadership," "driving innovation," and "effective communication." The extracted assertions are then quantified and displayed visually.

[0380] Example prompt sentence:

[0381] "Identify three key assertions about business leadership from the text below."

[0382] The above is a specific embodiment of this system.

[0383] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0384] Step 1:

[0385] The server reads electronic data from a specific directory. Specifically, the server accesses the " / data / books" folder and identifies the ".txt" files stored there. It opens each file and reads its contents into memory. Examples include files such as "LeadershipGuide.txt" and "InnovationInManagement.txt." In this step, the input is the electronic data file, and the output is the text data read into memory.

[0386] Step 2:

[0387] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed using Python's "re" module. Then, the "nltk" library is used to convert the text to lowercase and split it into tokens (words). For example, "Miyamoto Musashi is a Japanese samurai" is converted to "Miyamoto grapes are Japanese samurai." In this step, the input is the loaded text data, and the output is the preprocessed, clean text data.

[0388] Step 3:

[0389] The server passes the preprocessed text data to a generative AI model to extract key claims. Specifically, a generative AI model (e.g., a natural language processing model) is used to analyze the text content based on a prompt. The prompt used here is, "From the text below, please extract three key claims about business leadership." In this step, the input is the preprocessed text data and the prompt, and the output is the claim extraction results from the generative AI model.

[0390] Step 4:

[0391] The server quantifies the claims extracted from the generative AI model. Specifically, it uses the "scikit-learn" library to perform a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF). For example, the claim "The importance of leadership" is quantified to have a TF-IDF score of 0.85. In this step, the input is the extracted claim, and the output is the claim quantified by the TF-IDF score.

[0392] Step 5:

[0393] The server visually displays the quantified claims. Specifically, it uses Python's "matplotlib" and "plotly" libraries to convert the numerical data into graphs and charts. For example, it displays important claims and their importance as a bar graph. In this step, the input is the quantified claims, and the output is a visually displayed graph or chart. Users can use this to quickly grasp the important content.

[0394] (Application example 1)

[0395] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0396] Conventional information provision systems for business books have difficulty quickly and accurately extracting important points from vast amounts of text data and presenting them visually. Furthermore, it takes a great deal of time and effort for users to manually search for important information, making it impossible to efficiently gather information or acquire knowledge.

[0397] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0398] In this invention, the server includes means for storing book data, means for performing preprocessing of the book data, means for analyzing the book data using a natural language processing model, means for extracting and quantifying key claims, and means for converting the quantified key claims into visual display data, thereby enabling users to quickly and accurately grasp the important claims of the book data and effectively visually understand its contents.

[0399] "Information" means data that is collected, stored, and analyzed for a specific purpose.

[0400] "Generative artificial intelligence" refers to sophisticated algorithms that analyze specific input data and automatically generate important information or assertions.

[0401] A "main argument" is the most important, core information or opinion extracted from a text or data.

[0402] "Quantification" is the process of quantitatively evaluating the information value of text or data, and specifically refers to expressing importance and frequency numerically.

[0403] "Visually displaying" refers to the act of visually presenting quantified data or information in the form of graphs, charts, etc.

[0404] "Preprocessing" is the process of initially preparing book data and other information to prepare it in an analyzable format.

[0405] A "natural language processing model" refers to a machine learning model for analyzing, understanding, and generating human language.

[0406] A "summary" is a method of expressing the content of an original text concisely by abbreviating and presenting the main points of the text.

[0407] A "prompt" is text that is input to a generative AI model to cause it to generate a specific output.

[0408] A specific embodiment of the present invention will now be described. First, the server is equipped with a means for storing book data. Using this means, the server reads electronic book data from a specific directory and stores the contents in memory. The read electronic book data is saved in text file format.

[0409] The server then preprocesses the book data, removing unnecessary line breaks and special characters, converting the text to lower case, and splitting it into tokens (words). This process prepares the data in a format that is easy to analyze.

[0410] The server then analyzes the pre-processed text data using a generative AI that includes a natural language processing model. This analysis method uses the natural language processing model to extract key points or points from the text data. To do this, the server uses a generative AI model and inputs prompts such as the following into the model:

[0411] "Please extract key points about business leadership."

[0412] The server then quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This quantification method makes it possible to quantitatively indicate which claims are more important.

[0413] Finally, the server uses a means to visually display the quantified key points by converting the numerical data into graphs and charts and presenting them to the user on their device screen in a format that can be easily understood at a glance, such as bar graphs or pie charts.

[0414] For example, if a user wants to analyze a book on "Business Leadership," the server collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" and preprocesses them. It then uses a generative AI model to analyze the content, extracting key assertions such as "The Importance of Leadership," "Driving Innovation," and "Effective Communication," and quantifying them. It then creates graphs and charts and presents the results to the user on their device, allowing them to easily grasp the key points.

[0415] In this way, the system can quickly and accurately extract important points from business books and present them visually, allowing users to effectively gather information and acquire knowledge.

[0416] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0417] Step 1:

[0418] The server reads e-book data from a specific directory and stores it in memory. As input, the e-book data is given in the form of a text file. The server opens the file, reads its contents, and generates text data as output to store in memory.

[0419] Step 2:

[0420] The server performs preprocessing on the read text data. The text data obtained in step 1 is used as input. The server removes unnecessary line breaks and special characters, converts the text to lower case, and splits it into tokens (words). The output is the preprocessed tokenized text data.

[0421] Step 3:

[0422] The server uses a natural language processing model to parse the preprocessed text data, using as input the tokenized text data generated in step 2. The server inputs the generative AI model using the following prompt sentence:

[0423] "Please extract key points about business leadership."

[0424] The generative AI model extracts key points and summaries and outputs them in summary form.

[0425] Step 4:

[0426] The server then quantifies the extracted claims. The claims extracted in step 3 are used as input. The server then numerically evaluates the importance of each claim using TF-IDF (Term Frequency-Inverse Document Frequency). The output is a quantified importance score.

[0427] Step 5:

[0428] The server converts the quantified key claims into visual display data, using the quantified importance scores from step 4 as input. The server converts these scores into graphs and charts to generate visually displayable data. The output is the visual display data.

[0429] Step 6:

[0430] The terminal displays the visual display data provided by the server on its screen. The visual display data sent from the server is used as input. The terminal displays graphs and charts in a format that the user can understand at a glance and provides them to the user. As output, a display that the user can visually understand is obtained.

[0431] In this way, the specific operation has been explained while clarifying the input and output at each step.

[0432] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0433] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main arguments, and visually displays them, with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0434] 1. Loading book data

[0435] Subject: Server

[0436] The server loads the electronic data of business books from the specified directory. These are saved in text file format, and the server opens the files and stores their contents in memory. For example, a file such as "LeadershipGuide.txt" is loaded.

[0437] 2. Text Preprocessing

[0438] Subject: Server

[0439] The server preprocesses the book data it has loaded. This preprocessing removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[0440] 3. Content analysis and assertion extraction

[0441] Subject: Server

[0442] The server then passes the preprocessed text data to a generative AI system, which analyzes the content using a natural language processing model. This process extracts key points and key ideas from the text, such as "the importance of leadership" and "driving innovation."

[0443] 4. Quantifying your claims

[0444] Subject: Server

[0445] The server then quantifies the extracted key claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate how important each claim is. This results in an importance score being assigned to each claim.

[0446] 5. User Emotion Recognition

[0447] Subject: Server

[0448] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's face through a camera to determine the emotion.

[0449] 6. Providing and adjusting results

[0450] Subject: Server

[0451] The server visually displays the key points, quantified. At this stage, the display is dynamically adjusted based on the user's emotions, as recognized by the emotion engine. For example, if the user is excited, a colorful graph is used to emphasize the main points.

[0452] Specific examples

[0453] For example, if a user wishes to analyze several business books on "business leadership," the following process may be performed:

[0454] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the directory.

[0455] 2. The server preprocesses the book data, removing unnecessary characters and splitting the text into tokens.

[0456] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership" and "driving innovation."

[0457] 4. The server quantifies the claims and uses TF-IDF to evaluate the importance score of each claim.

[0458] 5. The server recognizes the user's emotions and determines their feelings based on facial expression analysis and text input.

[0459] 6. The server provides the results to the user, highlighting key points based on the user's emotions, for example, using colorful graphs if the user is excited.

[0460] This allows users to quickly understand important points from multiple business books, and since their emotions are also taken into consideration in the process, they can receive more personalized information.

[0461] The processing flow will be explained below.

[0462] Step 1:

[0463] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[0464] Step 2:

[0465] The server preprocesses the book data it has loaded. Specifically, it removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[0466] Step 3:

[0467] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[0468] Step 4:

[0469] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and assigns each claim an importance score.

[0470] Step 5:

[0471] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's facial expression through a camera to determine the emotion.

[0472] Step 6:

[0473] The server uses the emotional information obtained from the emotion engine to visually display the quantified claims. This process converts the numerical data into graphs and charts, providing them in a format that users can understand at a glance. The display method is dynamically adjusted based on the user's emotional state. For example, if the user is excited, a colorful graph will be used to emphasize the main points.

[0474] Step 7:

[0475] The user checks the results provided by the server. By viewing visualized data, the user can understand the main points and important arguments of multiple business books at a glance. Personalized information provided according to the user's emotional state allows the user to collect information more effectively and use it to make decisions.

[0476] Example 2

[0477] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0478] Conventional business book analysis systems can extract the main arguments from books and display them in numerical form, but they have the problem of not being able to provide personalized information without taking into account the user's emotions, making it difficult to improve user understanding and satisfaction.

[0479] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0480] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative model that analyzes the information, means for quantifying the main claims, means for visually displaying the quantified main claims, means including an emotion engine for recognizing a user's emotion, and means for dynamically adjusting the display method based on the recognized emotion. This makes it possible to effectively present the main claims of business books while taking the user's emotion into consideration.

[0481] "Information storage means" refers to a device or system that has the function of storing and managing electronic data of business books.

[0482] A "generative model" is a computational model that uses natural language processing to extract key points or insights from text data.

[0483] A "means for extracting key claims" is a device or system that has the functionality to use a generative model to find important claims and information from electronic data of business books.

[0484] The "means for quantifying key claims" is a device or system that has the function of quantitatively evaluating and scoring the importance of extracted claims.

[0485] A "visual display means" is a device or system capable of presenting a quantified assertion to a user in a visual format, such as a graph or chart.

[0486] The "emotion engine" is a calculation engine that recognizes and determines emotions through user text input and facial expression analysis.

[0487] A "dynamic adjustment means" is a device or system that has the capability to adapt the content and manner of display in real time based on the recognized user emotion.

[0488] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main points, and visually displays them, with an emotion engine that recognizes the user's emotions. The following describes how this system is specifically implemented.

[0489] Loading book data

[0490] Subject: Server

[0491] The server reads the electronic data of business books from a specified directory. This data is stored in text file format, and the server opens each file and stores its contents in memory. For example, it reads files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the " / data / books" directory. This process uses a file management system and a software library for input / output operations.

[0492] Text Preprocessing

[0493] Subject: Server

[0494] The server preprocesses the loaded book data. This preprocessing involves using regular expressions to remove unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). This prepares the text data in a format suitable for analysis. The software used includes natural language processing libraries (e.g., NLTK, SpaCy).

[0495] Content analysis and assertion extraction

[0496] Subject: Server

[0497] The server passes the preprocessed text data to a generative AI model for natural language processing. During this process, the generative AI model extracts key points and insights from the text. Specifically, models such as BERT and GPT-3 are used as generative AI models. For example, assertions such as "the importance of leadership" and "driving innovation" are extracted.

[0498] Quantifying claims

[0499] Subject: Server

[0500] The server then quantifies the extracted key claims. Specifically, it uses the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm to numerically evaluate the importance of each claim. For example, "importance of leadership" is assigned a score of 0.8, and "promotion of innovation" is assigned a score of 0.6.

[0501] User Emotion Recognition

[0502] Subject: Server

[0503] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. It analyzes the user's face through a camera to determine their emotion. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[0504] Providing and adjusting results

[0505] Subject: Server

[0506] The server visually displays the key points quantified. At this stage, the display method is dynamically adjusted based on the user's emotions, which are recognized by the emotion engine. For example, if the user is excited, colorful graphs are used to emphasize the main points. For this purpose, data visualization libraries (e.g., D3.js, Matplotlib) are used.

[0507] Specific examples

[0508] As a concrete example, consider a case where a user wants to analyze several business books on "Business Leadership." The following process is performed:

[0509] 1. The server reads the book data and scans "LeadershipGuide.txt", "InnovationInManagement.txt", etc. to obtain the contents.

[0510] 2. The server performs preprocessing, removing unnecessary characters and splitting the text into tokens.

[0511] 3. The server uses generative AI to extract key points, such as "The importance of leadership."

[0512] 4. The server quantifies the importance of the claims using TF-IDF and assigns an importance score to each claim.

[0513] 5. The server analyzes the user's emotions using the camera and microphone to determine their current emotions.

[0514] 6. The server adjusts the visual display based on emotion, highlighting key points with colorful graphs.

[0515] Prompt Sentence Examples

[0516] Use the following as an example prompt for the generative AI model:

[0517] "Summarize the contents of the following business books and extract the main points: LeadershipGuide.txt, InnovationInManagement.txt. Also, analyze user sentiment to highlight key points."

[0518] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0519] Step 1: Loading the book data

[0520] Subject: Server

[0521] The server reads the electronic data of the business book from the specified directory.

[0522] (Input): Directory path " / data / books"

[0523] (Specific behavior): Scan the " / data / books" directory and find files such as "LeadershipGuide.txt" and "InnovationInManagement.txt". Then, open each file one by one and store its contents in memory. If the contents of the text file are in Unicode format, check the encoding and decode it appropriately.

[0524] (Output): Text data stored in memory

[0525] Step 2: Preprocessing the text

[0526] Subject: Server

[0527] The server preprocesses the loaded book data.

[0528] (Input): Text data stored in memory

[0529] (Specific operation): As a preprocessing step, unnecessary line breaks and special characters are removed using regular expressions, and the text is converted to all lowercase. After that, the text is split into tokens by whitespace characters. For example, the sentence "The Leader is ..." is converted to lowercase "the leader is ..." and split into tokens. A natural language processing library (e.g., NLTK, SpaCy) is used for this process.

[0530] (Output): Tokenized word list

[0531] Step 3: Analyze content and extract claims

[0532] Subject: Server

[0533] The server passes the preprocessed data to the generative AI model for natural language processing.

[0534] (Input): Tokenized word list

[0535] (Specific operation): Pass the tokenized data to a generative AI model along with a prompt to extract the main claim. For example, use BERT or GPT-3 as the generative AI model. Provide the prompt "Extract the main claim from the following text: 'the leader is...'". The model will return claims such as "The importance of leadership" and "Promoting innovation".

[0536] (Output): List of extracted key claims

[0537] Step 4: Quantify your claims

[0538] Subject: Server

[0539] The server quantifies the extracted key assertions.

[0540] (Input): List of extracted key claims

[0541] (Specific behavior): Using the TF-IDF algorithm, the importance of each claim is evaluated. For example, "importance of leadership" is assigned a score of 0.8, and "driving innovation" is assigned a score of 0.6. This process is performed using machine learning libraries such as SciKit-Learn.

[0542] (Output): A list of claims and their TF-IDF scores

[0543] Step 5: Recognizing User Emotions

[0544] Subject: Server

[0545] The server uses an emotion engine to recognize the user's emotions.

[0546] (Input): Real-time video and audio data of the user

[0547] (Specific operation): Analyzes the user's facial expressions and voice in real time using a camera and microphone. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[0548] (Output): User's emotional data (e.g., "happy," "confused," etc.)

[0549] Step 6: Delivering and adjusting results

[0550] Subject: Server

[0551] The server visually displays the quantified claims and dynamically adjusts the display content based on the user's emotions.

[0552] (Input): A list of claims and their TF-IDF scores, and user sentiment data

[0553] (Specific Action): Present your main argument in a visual format such as a graph or chart. For example, if the user is excited, use a colorful graph to emphasize the point. Use a data visualization library (e.g., D3.js, Matplotlib) for this process.

[0554] (Output): A dynamically adjusted visual display presented to the user.

[0555] (Application example 2)

[0556] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0557] It is difficult to extract the main points from information-rich documents such as business books and to understand them efficiently. In addition, there is a need for technology that can provide more personalized information by adjusting the display method according to the emotional state of each individual user.

[0558] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0559] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative artificial intelligence that analyzes the information, means for quantifying the main claims, means for recognizing a user's emotions, means for dynamically adjusting the display method of the quantified main claims based on the user's emotions, and means for visually displaying the quantified main claims. This allows a user to quickly understand important points from multiple books and, in the process, receive more satisfying information through a display method that takes the user's emotional state into consideration.

[0560] "Means for storing information" is a function for saving text data such as business books in a storage device.

[0561] "Generative AI" is an AI technology that uses natural language processing to analyze text data and extract key points.

[0562] "Means for extracting key points" is a function for finding and extracting important points and points from text data.

[0563] The "means for quantifying the main claims" is a function for calculating the importance of the extracted claims and evaluating them numerically.

[0564] "Means for recognizing user emotions" refers to technology that uses a camera or text input to analyze and determine a user's emotional state.

[0565] The "means for dynamically adjusting the display method" is a function for changing the display method of an assertion in real time based on the recognized user sentiment.

[0566] "Visual display means" refers to techniques for presenting analyzed information and key arguments in a form that can be seen by the user, such as graphs, charts, or text.

[0567] This invention is a system that analyzes information from business books, extracts and quantifies key points, and dynamically adjusts the display method of the results by recognizing the user's emotions. This system is composed of a means for storing information, a generative artificial intelligence that analyzes the information, a means for quantifying key points, a means for recognizing the user's emotions, a means for dynamically adjusting the display method, and a means for visually displaying the quantified key points.

[0568] Program processing explanation

[0569] The server reads the digital data of business books from a specified directory and stores it in memory. The read text data is preprocessed to remove unnecessary line breaks and special characters and divide the text into tokens. This text data is then passed to a generative AI model for analysis and content extraction. The generative AI model uses natural language processing techniques to extract and quantify key points.

[0570] To recognize a user's emotions, the server analyzes the user's emotional state using a camera or text input. Image processing libraries such as OpenCV and dedicated emotion recognition models are used for emotion analysis. After the corresponding emotion is determined, the information is used to dynamically adjust the display method.

[0571] Specifically, if the user is "excited," the extracted assertions are emphasized using colorful graphs, etc. On the other hand, if the user is "neutral," the standard display method is applied. This allows the user to visually understand the information in a way that is appropriate for their emotions.

[0572] The device provides visually displayed assertions, which the user can receive through a display or head-mounted display, allowing the user to quickly understand important points from multiple business publications and receive personalized information according to emotional changes.

[0573] Specific examples

[0574] A user loads a book on "Business Leadership." Files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" are collected from the directory by the server. The server then preprocesses the data and passes it to a generative AI model to extract key assertions, such as "The Importance of Leadership" and "Driving Innovation." These assertions are then quantified using TF-IDF. Meanwhile, the user's emotions are analyzed from a photo (e.g., "user_image.jpg"), which is determined to indicate "excitement." Based on this information, the extracted assertions are highlighted in a colorful graph and presented to the user.

[0575] Prompt Sentence Examples

[0576] Prompt: "Extract the main idea from this text:\nText: XXXX"

[0577] This embodiment helps users quickly understand the main arguments of a business book in a manner that is responsive to their emotional state.

[0578] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0579] Step 1:

[0580] The server reads the digital data of a business book from the specified directory. Specifically, it opens a file such as "LeadershipGuide.txt" and stores its contents in memory. The input is the path to the e-book file, and the output is the read text data.

[0581] Step 2:

[0582] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed, all characters are converted to lowercase, and the data is split into tokens (words). The input is the loaded text data, and the output is the preprocessed text data.

[0583] Step 3:

[0584] The server passes the preprocessed text data to the generative AI model, which then uses natural language processing techniques to extract key claims. The input is the preprocessed text data, and the output is the extracted key claims (key phrases). Specifically, the system uses the Hugging Face Transformer model.

[0585] Step 4:

[0586] The server uses TF-IDF to quantify the extracted key claims. The input is the extracted key claims, and the output is the importance score of the key claims. Specifically, we use TfidfVectorizer to calculate the weight of each claim.

[0587] Step 5:

[0588] The server analyzes the user's face captured through a camera to recognize the user's emotions. The input is the user's facial image data, and the output is the determined user's emotional state. Specifically, OpenCV and an emotion recognition model are used.

[0589] Step 6:

[0590] The server dynamically adjusts the display of the quantified key claim based on the user's perceived emotion. The input is the key claim importance score and the user's emotional state, and the output is the adjusted display format. For example, if the user is excited, it is displayed as a colorful graph, and if the user is neutral, it is displayed as standard text.

[0591] Step 7:

[0592] The server visually displays the quantified key assertions in the adjusted display format. The input is the adjusted display format, and the output is the visual content displayed on the user's device. Specifically, it is presented to the user via a display or head-mounted display.

[0593] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0594] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0595] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0596] [Third embodiment]

[0597] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0598] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0599] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0600] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0601] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0602] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0603] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0604] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0605] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0606] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0607] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0608] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0609] This system stores information from business books, analyzes it to extract key points, and then quantifies and visually displays those points, allowing readers to quickly grasp important content. A specific embodiment of this system is described below.

[0610] 1. Loading book data

[0611] Subject: Server

[0612] The server reads the electronic data of business books from a specific directory. The electronic data is stored in text files, and the server opens these files and stores their contents in memory.

[0613] 2. Text Preprocessing

[0614] Subject: Server

[0615] The server preprocesses the book data it has loaded. This process removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format that is easy to analyze.

[0616] 3. Content analysis and assertion extraction

[0617] Subject: Server

[0618] The server passes the preprocessed text data to the generative AI, which analyzes its content. The generative AI uses a natural language processing model to extract key points and arguments from the text. This step makes it possible to automatically find summaries and key phrases from large amounts of text data.

[0619] 4. Quantifying your claims

[0620] Subject: Server

[0621] The server quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This allows us to quantitatively indicate which claims are more important.

[0622] 5. Providing results

[0623] Subject: Server

[0624] The server visually displays the key quantified claims. Specifically, it converts the numerical data into graphs and charts and provides them in a format that users can understand at a glance. Visual displays such as bar graphs and pie charts are used.

[0625] Specific examples

[0626] For example, if a user wishes to analyze several business books on "Business Leadership," the following process may be performed.

[0627] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt".

[0628] 2. The server preprocesses the book data, removing unnecessary line breaks and special characters and splitting the text into words.

[0629] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership," "driving innovation," and "effective communication."

[0630] 4. The server quantifies the claims and assigns a score to each claim to assess its importance.

[0631] 5. The server provides the results to the user and creates graphs and charts that visually show the scores of the extracted claims.

[0632] This allows users to see the main points of multiple books on "business leadership" at a glance, allowing them to acquire knowledge efficiently.

[0633] The processing flow will be explained below.

[0634] Step 1:

[0635] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[0636] Step 2:

[0637] The server preprocesses the book data it has loaded, removing unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). The text data for each book is then converted into a clean format, ready for analysis.

[0638] Step 3:

[0639] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[0640] Step 4:

[0641] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and calculates an importance score for each claim.

[0642] Step 5:

[0643] The server visually displays the quantified claims. This process uses the numerical data to generate graphs and charts. For example, a bar graph can be used to visually show the importance score of each claim.

[0644] Step 6:

[0645] The user checks the results provided by the server. By viewing the visualized data, the user can understand the main points and important arguments of multiple business books at a glance, which helps them gather information efficiently and make decisions.

[0646] Example 1

[0647] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0648] In recent years, with the increase in the amount of information, there has been a growing need to quickly extract important information from electronic data such as many books and papers and effectively understand it. However, conventional methods have had difficulty efficiently processing large amounts of information, extracting key points, and visually presenting them. Therefore, this invention provides a system that automatically and efficiently extracts important points from electronic data, quantifies them, and visualizes them, allowing users to quickly grasp important content.

[0649] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0650] In this invention, the server includes means for reading electronic data from a specific directory, means for preprocessing to remove unnecessary characters and divide the text into tokens, means for extracting key claims from the preprocessed data using a generative AI model, means for quantifying the key claims using TF-IDF, and means for visually displaying the quantified key claims. This allows important information to be efficiently extracted from electronic data, enabling users to quickly grasp the information.

[0651] The following definitions are provided for key terms contained in the claims:

[0652] A "specific directory" refers to a folder or path designated for the server to search for electronic data.

[0653] "Electronic data" refers to files containing written information stored in digital format, such as books, papers, and articles.

[0654] "Preprocessing" refers to a series of operations that remove unnecessary characters from text data and convert it into a format that is easy to analyze.

[0655] A "token" refers to a unit into which text data is divided into words or phrases when analyzing the data.

[0656] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate claims or summaries from text data.

[0657] "Key points" refers to phrases or sentences that indicate the most important information or points in electronic data.

[0658] "TF-IDF" stands for Term Frequency-Inverse Document Frequency and refers to a numerical method for evaluating the importance of terms in text data.

[0659] "Visual display" refers to presenting numerical data in a graphical format such as a graph or chart, so that the user can intuitively understand it.

[0660] This system is designed to efficiently analyze electronic data, extract important assertions, and visually display them. A specific embodiment of this system will be described below.

[0661] The server reads electronic data from a specific directory. For example, it identifies all text files in the " / data / books" folder, opens them, and reads their contents. A computing device with high I / O performance is recommended as the hardware used. The read contents are stored in memory for further processing.

[0662] Next, the server preprocesses the book data it has loaded. Specifically, it uses the Python "re" module to remove unnecessary line breaks and special characters, and then uses the "nltk" library to convert the text to lowercase and split it into tokens (words). This preprocessing prepares the text data in a format that is easy to analyze.

[0663] The preprocessed text data is passed to a generative AI model. The server uses the generative AI model to analyze the text data and extract key assertions. The prompt used is, "Please extract three key assertions about business leadership from the text below." A well-known natural language processing model is suitable as the AI ​​model to use.

[0664] The extracted claims are quantified. Specifically, a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF) is performed using the "scikit-learn" library. This gives a numerical value to the importance of each claim, allowing us to determine which claims are more important.

[0665] Finally, the server visually displays the quantified claims, using Python's matplotlib and plotly libraries to convert the numerical data into graphs and charts, which are displayed in an intuitive format for users to quickly grasp the key points.

[0666] For example, if a user wants to analyze several books on "business leadership," the process would proceed as follows: The server collects book data such as "LeadershipGuide.txt" and "InnovationInManagement.txt," performs preprocessing, and then uses a generative AI model to extract assertions such as "the importance of leadership," "driving innovation," and "effective communication." The extracted assertions are then quantified and displayed visually.

[0667] Example prompt sentence:

[0668] "Identify three key assertions about business leadership from the text below."

[0669] The above is a specific embodiment of this system.

[0670] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0671] Step 1:

[0672] The server reads electronic data from a specific directory. Specifically, the server accesses the " / data / books" folder and identifies the ".txt" files stored there. It opens each file and reads its contents into memory. Examples include files such as "LeadershipGuide.txt" and "InnovationInManagement.txt." In this step, the input is the electronic data file, and the output is the text data read into memory.

[0673] Step 2:

[0674] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed using Python's "re" module. Then, the "nltk" library is used to convert the text to lowercase and split it into tokens (words). For example, "Miyamoto Musashi is a Japanese samurai" is converted to "Miyamoto grapes are Japanese samurai." In this step, the input is the loaded text data, and the output is the preprocessed, clean text data.

[0675] Step 3:

[0676] The server passes the preprocessed text data to a generative AI model to extract key claims. Specifically, a generative AI model (e.g., a natural language processing model) is used to analyze the text content based on a prompt. The prompt used here is, "From the text below, please extract three key claims about business leadership." In this step, the input is the preprocessed text data and the prompt, and the output is the claim extraction results from the generative AI model.

[0677] Step 4:

[0678] The server quantifies the claims extracted from the generative AI model. Specifically, it uses the "scikit-learn" library to perform a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF). For example, the claim "The importance of leadership" is quantified to have a TF-IDF score of 0.85. In this step, the input is the extracted claim, and the output is the claim quantified by the TF-IDF score.

[0679] Step 5:

[0680] The server visually displays the quantified claims. Specifically, it uses Python's "matplotlib" and "plotly" libraries to convert the numerical data into graphs and charts. For example, it displays important claims and their importance as a bar graph. In this step, the input is the quantified claims, and the output is a visually displayed graph or chart. Users can use this to quickly grasp the important content.

[0681] (Application example 1)

[0682] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0683] Conventional information provision systems for business books have difficulty quickly and accurately extracting important points from vast amounts of text data and presenting them visually. Furthermore, it takes a great deal of time and effort for users to manually search for important information, making it impossible to efficiently gather information or acquire knowledge.

[0684] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0685] In this invention, the server includes means for storing book data, means for performing preprocessing of the book data, means for analyzing the book data using a natural language processing model, means for extracting and quantifying key claims, and means for converting the quantified key claims into visual display data, thereby enabling users to quickly and accurately grasp the important claims of the book data and effectively visually understand its contents.

[0686] "Information" means data that is collected, stored, and analyzed for a specific purpose.

[0687] "Generative artificial intelligence" refers to sophisticated algorithms that analyze specific input data and automatically generate important information or assertions.

[0688] A "main argument" is the most important, core information or opinion extracted from a text or data.

[0689] "Quantification" is the process of quantitatively evaluating the information value of text or data, and specifically refers to expressing importance and frequency numerically.

[0690] "Visually displaying" refers to the act of visually presenting quantified data or information in the form of graphs, charts, etc.

[0691] "Preprocessing" is the process of initially preparing book data and other information to prepare it in an analyzable format.

[0692] A "natural language processing model" refers to a machine learning model for analyzing, understanding, and generating human language.

[0693] A "summary" is a method of expressing the content of an original text concisely by abbreviating and presenting the main points of the text.

[0694] A "prompt" is text that is input to a generative AI model to cause it to generate a specific output.

[0695] A specific embodiment of the present invention will now be described. First, the server is equipped with a means for storing book data. Using this means, the server reads electronic book data from a specific directory and stores the contents in memory. The read electronic book data is saved in text file format.

[0696] The server then preprocesses the book data, removing unnecessary line breaks and special characters, converting the text to lower case, and splitting it into tokens (words). This process prepares the data in a format that is easy to analyze.

[0697] The server then analyzes the pre-processed text data using a generative AI that includes a natural language processing model. This analysis method uses the natural language processing model to extract key points or points from the text data. To do this, the server uses a generative AI model and inputs prompts such as the following into the model:

[0698] "Please extract key points about business leadership."

[0699] The server then quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This quantification method makes it possible to quantitatively indicate which claims are more important.

[0700] Finally, the server uses a means to visually display the quantified key points by converting the numerical data into graphs and charts and presenting them to the user on their device screen in a format that can be easily understood at a glance, such as bar graphs or pie charts.

[0701] For example, if a user wants to analyze a book on "Business Leadership," the server collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" and preprocesses them. It then uses a generative AI model to analyze the content, extracting key assertions such as "The Importance of Leadership," "Driving Innovation," and "Effective Communication," and quantifying them. It then creates graphs and charts and presents the results to the user on their device, allowing them to easily grasp the key points.

[0702] In this way, the system can quickly and accurately extract important points from business books and present them visually, allowing users to effectively gather information and acquire knowledge.

[0703] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0704] Step 1:

[0705] The server reads e-book data from a specific directory and stores it in memory. As input, the e-book data is given in the form of a text file. The server opens the file, reads its contents, and generates text data as output to store in memory.

[0706] Step 2:

[0707] The server performs preprocessing on the read text data. The text data obtained in step 1 is used as input. The server removes unnecessary line breaks and special characters, converts the text to lower case, and splits it into tokens (words). The output is the preprocessed tokenized text data.

[0708] Step 3:

[0709] The server uses a natural language processing model to parse the preprocessed text data, using as input the tokenized text data generated in step 2. The server inputs the generative AI model using the following prompt sentence:

[0710] "Please extract key points about business leadership."

[0711] The generative AI model extracts key points and summaries and outputs them in summary form.

[0712] Step 4:

[0713] The server then quantifies the extracted claims. The claims extracted in step 3 are used as input. The server then numerically evaluates the importance of each claim using TF-IDF (Term Frequency-Inverse Document Frequency). The output is a quantified importance score.

[0714] Step 5:

[0715] The server converts the quantified key claims into visual display data, using the quantified importance scores from step 4 as input. The server converts these scores into graphs and charts to generate visually displayable data. The output is the visual display data.

[0716] Step 6:

[0717] The terminal displays the visual display data provided by the server on its screen. The visual display data sent from the server is used as input. The terminal displays graphs and charts in a format that the user can understand at a glance and provides them to the user. As output, a display that the user can visually understand is obtained.

[0718] In this way, the specific operation has been explained while clarifying the input and output at each step.

[0719] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0720] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main arguments, and visually displays them, with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[0721] 1. Loading book data

[0722] Subject: Server

[0723] The server loads the electronic data of business books from the specified directory. These are saved in text file format, and the server opens the files and stores their contents in memory. For example, a file such as "LeadershipGuide.txt" is loaded.

[0724] 2. Text Preprocessing

[0725] Subject: Server

[0726] The server preprocesses the book data it has loaded. This preprocessing removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[0727] 3. Content analysis and assertion extraction

[0728] Subject: Server

[0729] The server then passes the preprocessed text data to a generative AI system, which analyzes the content using a natural language processing model. This process extracts key points and key ideas from the text, such as "the importance of leadership" and "driving innovation."

[0730] 4. Quantifying your claims

[0731] Subject: Server

[0732] The server then quantifies the extracted key claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate how important each claim is. This results in an importance score being assigned to each claim.

[0733] 5. User Emotion Recognition

[0734] Subject: Server

[0735] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's face through a camera to determine the emotion.

[0736] 6. Providing and adjusting results

[0737] Subject: Server

[0738] The server visually displays the key points, quantified. At this stage, the display is dynamically adjusted based on the user's emotions, as recognized by the emotion engine. For example, if the user is excited, a colorful graph is used to emphasize the main points.

[0739] Specific examples

[0740] For example, if a user wishes to analyze several business books on "business leadership," the following process may be performed:

[0741] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the directory.

[0742] 2. The server preprocesses the book data, removing unnecessary characters and splitting the text into tokens.

[0743] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership" and "driving innovation."

[0744] 4. The server quantifies the claims and uses TF-IDF to evaluate the importance score of each claim.

[0745] 5. The server recognizes the user's emotions and determines their feelings based on facial expression analysis and text input.

[0746] 6. The server provides the results to the user, highlighting key points based on the user's emotions, for example, using colorful graphs if the user is excited.

[0747] This allows users to quickly understand important points from multiple business books, and since their emotions are also taken into consideration in the process, they can receive more personalized information.

[0748] The processing flow will be explained below.

[0749] Step 1:

[0750] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[0751] Step 2:

[0752] The server preprocesses the book data it has loaded. Specifically, it removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[0753] Step 3:

[0754] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[0755] Step 4:

[0756] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and assigns each claim an importance score.

[0757] Step 5:

[0758] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's facial expression through a camera to determine the emotion.

[0759] Step 6:

[0760] The server uses the emotional information obtained from the emotion engine to visually display the quantified claims. This process converts the numerical data into graphs and charts, providing them in a format that users can understand at a glance. The display method is dynamically adjusted based on the user's emotional state. For example, if the user is excited, a colorful graph will be used to emphasize the main points.

[0761] Step 7:

[0762] The user checks the results provided by the server. By viewing visualized data, the user can understand the main points and important arguments of multiple business books at a glance. Personalized information provided according to the user's emotional state allows the user to collect information more effectively and use it to make decisions.

[0763] Example 2

[0764] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0765] Conventional business book analysis systems can extract the main arguments from books and display them in numerical form, but they have the problem of not being able to provide personalized information without taking into account the user's emotions, making it difficult to improve user understanding and satisfaction.

[0766] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0767] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative model that analyzes the information, means for quantifying the main claims, means for visually displaying the quantified main claims, means including an emotion engine for recognizing a user's emotion, and means for dynamically adjusting the display method based on the recognized emotion. This makes it possible to effectively present the main claims of business books while taking the user's emotion into consideration.

[0768] "Information storage means" refers to a device or system that has the function of storing and managing electronic data of business books.

[0769] A "generative model" is a computational model that uses natural language processing to extract key points or insights from text data.

[0770] A "means for extracting key claims" is a device or system that has the functionality to use a generative model to find important claims and information from electronic data of business books.

[0771] The "means for quantifying key claims" is a device or system that has the function of quantitatively evaluating and scoring the importance of extracted claims.

[0772] A "visual display means" is a device or system capable of presenting a quantified assertion to a user in a visual format, such as a graph or chart.

[0773] The "emotion engine" is a calculation engine that recognizes and determines emotions through user text input and facial expression analysis.

[0774] A "dynamic adjustment means" is a device or system that has the capability to adapt the content and manner of display in real time based on the recognized user emotion.

[0775] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main points, and visually displays them, with an emotion engine that recognizes the user's emotions. The following describes how this system is specifically implemented.

[0776] Loading book data

[0777] Subject: Server

[0778] The server reads the electronic data of business books from a specified directory. This data is stored in text file format, and the server opens each file and stores its contents in memory. For example, it reads files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the " / data / books" directory. This process uses a file management system and a software library for input / output operations.

[0779] Text Preprocessing

[0780] Subject: Server

[0781] The server preprocesses the loaded book data. This preprocessing involves using regular expressions to remove unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). This prepares the text data in a format suitable for analysis. The software used includes natural language processing libraries (e.g., NLTK, SpaCy).

[0782] Content analysis and assertion extraction

[0783] Subject: Server

[0784] The server passes the preprocessed text data to a generative AI model for natural language processing. During this process, the generative AI model extracts key points and insights from the text. Specifically, models such as BERT and GPT-3 are used as generative AI models. For example, assertions such as "the importance of leadership" and "driving innovation" are extracted.

[0785] Quantifying claims

[0786] Subject: Server

[0787] The server then quantifies the extracted key claims. Specifically, it uses the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm to numerically evaluate the importance of each claim. For example, "importance of leadership" is assigned a score of 0.8, and "promotion of innovation" is assigned a score of 0.6.

[0788] User Emotion Recognition

[0789] Subject: Server

[0790] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. It analyzes the user's face through a camera to determine their emotion. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[0791] Providing and adjusting results

[0792] Subject: Server

[0793] The server visually displays the key points quantified. At this stage, the display method is dynamically adjusted based on the user's emotions, which are recognized by the emotion engine. For example, if the user is excited, colorful graphs are used to emphasize the main points. For this purpose, data visualization libraries (e.g., D3.js, Matplotlib) are used.

[0794] Specific examples

[0795] As a concrete example, consider a case where a user wants to analyze several business books on "Business Leadership." The following process is performed:

[0796] 1. The server reads the book data and scans "LeadershipGuide.txt", "InnovationInManagement.txt", etc. to obtain the contents.

[0797] 2. The server performs preprocessing, removing unnecessary characters and splitting the text into tokens.

[0798] 3. The server uses generative AI to extract key points, such as "The importance of leadership."

[0799] 4. The server quantifies the importance of the claims using TF-IDF and assigns an importance score to each claim.

[0800] 5. The server analyzes the user's emotions using the camera and microphone to determine their current emotions.

[0801] 6. The server adjusts the visual display based on emotion, highlighting key points with colorful graphs.

[0802] Prompt Sentence Examples

[0803] Use the following as an example prompt for the generative AI model:

[0804] "Summarize the contents of the following business books and extract the main points: LeadershipGuide.txt, InnovationInManagement.txt. Also, analyze user sentiment to highlight key points."

[0805] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0806] Step 1: Loading the book data

[0807] Subject: Server

[0808] The server reads the electronic data of the business book from the specified directory.

[0809] (Input): Directory path " / data / books"

[0810] (Specific behavior): Scan the " / data / books" directory and find files such as "LeadershipGuide.txt" and "InnovationInManagement.txt". Then, open each file one by one and store its contents in memory. If the contents of the text file are in Unicode format, check the encoding and decode it appropriately.

[0811] (Output): Text data stored in memory

[0812] Step 2: Preprocessing the text

[0813] Subject: Server

[0814] The server preprocesses the loaded book data.

[0815] (Input): Text data stored in memory

[0816] (Specific operation): As a preprocessing step, unnecessary line breaks and special characters are removed using regular expressions, and the text is converted to all lowercase. After that, the text is split into tokens by whitespace characters. For example, the sentence "The Leader is ..." is converted to lowercase "the leader is ..." and split into tokens. A natural language processing library (e.g., NLTK, SpaCy) is used for this process.

[0817] (Output): Tokenized word list

[0818] Step 3: Analyze content and extract claims

[0819] Subject: Server

[0820] The server passes the preprocessed data to the generative AI model for natural language processing.

[0821] (Input): Tokenized word list

[0822] (Specific operation): Pass the tokenized data to a generative AI model along with a prompt to extract the main claim. For example, use BERT or GPT-3 as the generative AI model. Provide the prompt "Extract the main claim from the following text: 'the leader is...'". The model will return claims such as "The importance of leadership" and "Promoting innovation".

[0823] (Output): List of extracted key claims

[0824] Step 4: Quantify your claims

[0825] Subject: Server

[0826] The server quantifies the extracted key assertions.

[0827] (Input): List of extracted key claims

[0828] (Specific behavior): Using the TF-IDF algorithm, the importance of each claim is evaluated. For example, "importance of leadership" is assigned a score of 0.8, and "driving innovation" is assigned a score of 0.6. This process is performed using machine learning libraries such as SciKit-Learn.

[0829] (Output): A list of claims and their TF-IDF scores

[0830] Step 5: Recognizing User Emotions

[0831] Subject: Server

[0832] The server uses an emotion engine to recognize the user's emotions.

[0833] (Input): Real-time video and audio data of the user

[0834] (Specific operation): Analyzes the user's facial expressions and voice in real time using a camera and microphone. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[0835] (Output): User's emotional data (e.g., "happy," "confused," etc.)

[0836] Step 6: Delivering and adjusting results

[0837] Subject: Server

[0838] The server visually displays the quantified claims and dynamically adjusts the display content based on the user's emotions.

[0839] (Input): A list of claims and their TF-IDF scores, and user sentiment data

[0840] (Specific Action): Present your main argument in a visual format such as a graph or chart. For example, if the user is excited, use a colorful graph to emphasize the point. Use a data visualization library (e.g., D3.js, Matplotlib) for this process.

[0841] (Output): A dynamically adjusted visual display presented to the user.

[0842] (Application example 2)

[0843] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0844] It is difficult to extract the main points from information-rich documents such as business books and to understand them efficiently. In addition, there is a need for technology that can provide more personalized information by adjusting the display method according to the emotional state of each individual user.

[0845] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0846] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative artificial intelligence that analyzes the information, means for quantifying the main claims, means for recognizing a user's emotions, means for dynamically adjusting the display method of the quantified main claims based on the user's emotions, and means for visually displaying the quantified main claims. This allows a user to quickly understand important points from multiple books and, in the process, receive more satisfying information through a display method that takes the user's emotional state into consideration.

[0847] "Means for storing information" is a function for saving text data such as business books in a storage device.

[0848] "Generative AI" is an AI technology that uses natural language processing to analyze text data and extract key points.

[0849] "Means for extracting key points" is a function for finding and extracting important points and points from text data.

[0850] The "means for quantifying the main claims" is a function for calculating the importance of the extracted claims and evaluating them numerically.

[0851] "Means for recognizing user emotions" refers to technology that uses a camera or text input to analyze and determine a user's emotional state.

[0852] The "means for dynamically adjusting the display method" is a function for changing the display method of an assertion in real time based on the recognized user sentiment.

[0853] "Visual display means" refers to techniques for presenting analyzed information and key arguments in a form that can be seen by the user, such as graphs, charts, or text.

[0854] This invention is a system that analyzes information from business books, extracts and quantifies key points, and dynamically adjusts the display method of the results by recognizing the user's emotions. This system is composed of a means for storing information, a generative artificial intelligence that analyzes the information, a means for quantifying key points, a means for recognizing the user's emotions, a means for dynamically adjusting the display method, and a means for visually displaying the quantified key points.

[0855] Program processing explanation

[0856] The server reads the digital data of business books from a specified directory and stores it in memory. The read text data is preprocessed to remove unnecessary line breaks and special characters and divide the text into tokens. This text data is then passed to a generative AI model for analysis and content extraction. The generative AI model uses natural language processing techniques to extract and quantify key points.

[0857] To recognize a user's emotions, the server analyzes the user's emotional state using a camera or text input. Image processing libraries such as OpenCV and dedicated emotion recognition models are used for emotion analysis. After the corresponding emotion is determined, the information is used to dynamically adjust the display method.

[0858] Specifically, if the user is "excited," the extracted assertions are emphasized using colorful graphs, etc. On the other hand, if the user is "neutral," the standard display method is applied. This allows the user to visually understand the information in a way that is appropriate for their emotions.

[0859] The device provides visually displayed assertions, which the user can receive through a display or head-mounted display, allowing the user to quickly understand important points from multiple business publications and receive personalized information according to emotional changes.

[0860] Specific examples

[0861] A user loads a book on "Business Leadership." Files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" are collected from the directory by the server. The server then preprocesses the data and passes it to a generative AI model to extract key assertions, such as "The Importance of Leadership" and "Driving Innovation." These assertions are then quantified using TF-IDF. Meanwhile, the user's emotions are analyzed from a photo (e.g., "user_image.jpg"), which is determined to indicate "excitement." Based on this information, the extracted assertions are highlighted in a colorful graph and presented to the user.

[0862] Prompt Sentence Examples

[0863] Prompt: "Extract the main idea from this text:\nText: XXXX"

[0864] This embodiment helps users quickly understand the main arguments of a business book in a manner that is responsive to their emotional state.

[0865] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0866] Step 1:

[0867] The server reads the digital data of a business book from the specified directory. Specifically, it opens a file such as "LeadershipGuide.txt" and stores its contents in memory. The input is the path to the e-book file, and the output is the read text data.

[0868] Step 2:

[0869] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed, all characters are converted to lowercase, and the data is split into tokens (words). The input is the loaded text data, and the output is the preprocessed text data.

[0870] Step 3:

[0871] The server passes the preprocessed text data to the generative AI model, which then uses natural language processing techniques to extract key claims. The input is the preprocessed text data, and the output is the extracted key claims (key phrases). Specifically, the system uses the Hugging Face Transformer model.

[0872] Step 4:

[0873] The server uses TF-IDF to quantify the extracted key claims. The input is the extracted key claims, and the output is the importance score of the key claims. Specifically, we use TfidfVectorizer to calculate the weight of each claim.

[0874] Step 5:

[0875] The server analyzes the user's face captured through a camera to recognize the user's emotions. The input is the user's facial image data, and the output is the determined user's emotional state. Specifically, OpenCV and an emotion recognition model are used.

[0876] Step 6:

[0877] The server dynamically adjusts the display of the quantified key claim based on the user's perceived emotion. The input is the key claim importance score and the user's emotional state, and the output is the adjusted display format. For example, if the user is excited, it is displayed as a colorful graph, and if the user is neutral, it is displayed as standard text.

[0878] Step 7:

[0879] The server visually displays the quantified key assertions in the adjusted display format. The input is the adjusted display format, and the output is the visual content displayed on the user's device. Specifically, it is presented to the user via a display or head-mounted display.

[0880] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0881] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0882] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0883] [Fourth embodiment]

[0884] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0885] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0886] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0887] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0888] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0889] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0890] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0891] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0892] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0893] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0894] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0895] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0896] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0897] This system stores information from business books, analyzes it to extract key points, and then quantifies and visually displays those points, allowing readers to quickly grasp important content. A specific embodiment of this system is described below.

[0898] 1. Loading book data

[0899] Subject: Server

[0900] The server reads the electronic data of business books from a specific directory. The electronic data is stored in text files, and the server opens these files and stores their contents in memory.

[0901] 2. Text Preprocessing

[0902] Subject: Server

[0903] The server preprocesses the book data it has loaded. This process removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format that is easy to analyze.

[0904] 3. Content analysis and assertion extraction

[0905] Subject: Server

[0906] The server passes the preprocessed text data to the generative AI, which analyzes its content. The generative AI uses a natural language processing model to extract key points and arguments from the text. This step makes it possible to automatically find summaries and key phrases from large amounts of text data.

[0907] 4. Quantifying your claims

[0908] Subject: Server

[0909] The server quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This allows us to quantitatively indicate which claims are more important.

[0910] 5. Providing results

[0911] Subject: Server

[0912] The server visually displays the key quantified claims. Specifically, it converts the numerical data into graphs and charts and provides them in a format that users can understand at a glance. Visual displays such as bar graphs and pie charts are used.

[0913] Specific examples

[0914] For example, if a user wishes to analyze several business books on "Business Leadership," the following process may be performed.

[0915] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt".

[0916] 2. The server preprocesses the book data, removing unnecessary line breaks and special characters and splitting the text into words.

[0917] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership," "driving innovation," and "effective communication."

[0918] 4. The server quantifies the claims and assigns a score to each claim to assess its importance.

[0919] 5. The server provides the results to the user and creates graphs and charts that visually show the scores of the extracted claims.

[0920] This allows users to see the main points of multiple books on "business leadership" at a glance, allowing them to acquire knowledge efficiently.

[0921] The processing flow will be explained below.

[0922] Step 1:

[0923] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[0924] Step 2:

[0925] The server preprocesses the book data it has loaded, removing unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). The text data for each book is then converted into a clean format, ready for analysis.

[0926] Step 3:

[0927] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[0928] Step 4:

[0929] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and calculates an importance score for each claim.

[0930] Step 5:

[0931] The server visually displays the quantified claims. This process uses the numerical data to generate graphs and charts. For example, a bar graph can be used to visually show the importance score of each claim.

[0932] Step 6:

[0933] The user checks the results provided by the server. By viewing the visualized data, the user can understand the main points and important arguments of multiple business books at a glance, which helps them gather information efficiently and make decisions.

[0934] Example 1

[0935] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0936] In recent years, with the increase in the amount of information, there has been a growing need to quickly extract important information from electronic data such as many books and papers and effectively understand it. However, conventional methods have had difficulty efficiently processing large amounts of information, extracting key points, and visually presenting them. Therefore, this invention provides a system that automatically and efficiently extracts important points from electronic data, quantifies them, and visualizes them, allowing users to quickly grasp important content.

[0937] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0938] In this invention, the server includes means for reading electronic data from a specific directory, means for preprocessing to remove unnecessary characters and divide the text into tokens, means for extracting key claims from the preprocessed data using a generative AI model, means for quantifying the key claims using TF-IDF, and means for visually displaying the quantified key claims. This allows important information to be efficiently extracted from electronic data, enabling users to quickly grasp the information.

[0939] The following definitions are provided for key terms contained in the claims:

[0940] A "specific directory" refers to a folder or path designated for the server to search for electronic data.

[0941] "Electronic data" refers to files containing written information stored in digital format, such as books, papers, and articles.

[0942] "Preprocessing" refers to a series of operations that remove unnecessary characters from text data and convert it into a format that is easy to analyze.

[0943] A "token" refers to a unit into which text data is divided into words or phrases when analyzing the data.

[0944] A "generative AI model" refers to an algorithm or system that uses artificial intelligence to generate claims or summaries from text data.

[0945] "Key points" refers to phrases or sentences that indicate the most important information or points in electronic data.

[0946] "TF-IDF" stands for Term Frequency-Inverse Document Frequency and refers to a numerical method for evaluating the importance of terms in text data.

[0947] "Visual display" refers to presenting numerical data in a graphical format such as a graph or chart, so that the user can intuitively understand it.

[0948] This system is designed to efficiently analyze electronic data, extract important assertions, and visually display them. A specific embodiment of this system will be described below.

[0949] The server reads electronic data from a specific directory. For example, it identifies all text files in the " / data / books" folder, opens them, and reads their contents. A computing device with high I / O performance is recommended as the hardware used. The read contents are stored in memory for further processing.

[0950] Next, the server preprocesses the book data it has loaded. Specifically, it uses the Python "re" module to remove unnecessary line breaks and special characters, and then uses the "nltk" library to convert the text to lowercase and split it into tokens (words). This preprocessing prepares the text data in a format that is easy to analyze.

[0951] The preprocessed text data is passed to a generative AI model. The server uses the generative AI model to analyze the text data and extract key assertions. The prompt used is, "Please extract three key assertions about business leadership from the text below." A well-known natural language processing model is suitable as the AI ​​model to use.

[0952] The extracted claims are quantified. Specifically, a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF) is performed using the "scikit-learn" library. This gives a numerical value to the importance of each claim, allowing us to determine which claims are more important.

[0953] Finally, the server visually displays the quantified claims, using Python's matplotlib and plotly libraries to convert the numerical data into graphs and charts, which are displayed in an intuitive format for users to quickly grasp the key points.

[0954] For example, if a user wants to analyze several books on "business leadership," the process would proceed as follows: The server collects book data such as "LeadershipGuide.txt" and "InnovationInManagement.txt," performs preprocessing, and then uses a generative AI model to extract assertions such as "the importance of leadership," "driving innovation," and "effective communication." The extracted assertions are then quantified and displayed visually.

[0955] Example prompt sentence:

[0956] "Identify three key assertions about business leadership from the text below."

[0957] The above is a specific embodiment of this system.

[0958] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] The server reads electronic data from a specific directory. Specifically, the server accesses the " / data / books" folder and identifies the ".txt" files stored there. It opens each file and reads its contents into memory. Examples include files such as "LeadershipGuide.txt" and "InnovationInManagement.txt." In this step, the input is the electronic data file, and the output is the text data read into memory.

[0961] Step 2:

[0962] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed using Python's "re" module. Then, the "nltk" library is used to convert the text to lowercase and split it into tokens (words). For example, "Miyamoto Musashi is a Japanese samurai" is converted to "Miyamoto grapes are Japanese samurai." In this step, the input is the loaded text data, and the output is the preprocessed, clean text data.

[0963] Step 3:

[0964] The server passes the preprocessed text data to a generative AI model to extract key claims. Specifically, a generative AI model (e.g., a natural language processing model) is used to analyze the text content based on a prompt. The prompt used here is, "From the text below, please extract three key claims about business leadership." In this step, the input is the preprocessed text data and the prompt, and the output is the claim extraction results from the generative AI model.

[0965] Step 4:

[0966] The server quantifies the claims extracted from the generative AI model. Specifically, it uses the "scikit-learn" library to perform a numerical evaluation based on Term Frequency-Inverse Document Frequency (TF-IDF). For example, the claim "The importance of leadership" is quantified to have a TF-IDF score of 0.85. In this step, the input is the extracted claim, and the output is the claim quantified by the TF-IDF score.

[0967] Step 5:

[0968] The server visually displays the quantified claims. Specifically, it uses Python's "matplotlib" and "plotly" libraries to convert the numerical data into graphs and charts. For example, it displays important claims and their importance as a bar graph. In this step, the input is the quantified claims, and the output is a visually displayed graph or chart. Users can use this to quickly grasp the important content.

[0969] (Application example 1)

[0970] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0971] Conventional information provision systems for business books have difficulty quickly and accurately extracting important points from vast amounts of text data and presenting them visually. Furthermore, it takes a great deal of time and effort for users to manually search for important information, making it impossible to efficiently gather information or acquire knowledge.

[0972] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0973] In this invention, the server includes means for storing book data, means for performing preprocessing of the book data, means for analyzing the book data using a natural language processing model, means for extracting and quantifying key claims, and means for converting the quantified key claims into visual display data, thereby enabling users to quickly and accurately grasp the important claims of the book data and effectively visually understand its contents.

[0974] "Information" means data that is collected, stored, and analyzed for a specific purpose.

[0975] "Generative artificial intelligence" refers to sophisticated algorithms that analyze specific input data and automatically generate important information or assertions.

[0976] A "main argument" is the most important, core information or opinion extracted from a text or data.

[0977] "Quantification" is the process of quantitatively evaluating the information value of text or data, and specifically refers to expressing importance and frequency numerically.

[0978] "Visually displaying" refers to the act of visually presenting quantified data or information in the form of graphs, charts, etc.

[0979] "Preprocessing" is the process of initially preparing book data and other information to prepare it in an analyzable format.

[0980] A "natural language processing model" refers to a machine learning model for analyzing, understanding, and generating human language.

[0981] A "summary" is a method of expressing the content of an original text concisely by abbreviating and presenting the main points of the text.

[0982] A "prompt" is text that is input to a generative AI model to cause it to generate a specific output.

[0983] A specific embodiment of the present invention will now be described. First, the server is equipped with a means for storing book data. Using this means, the server reads electronic book data from a specific directory and stores the contents in memory. The read electronic book data is saved in text file format.

[0984] The server then preprocesses the book data, removing unnecessary line breaks and special characters, converting the text to lower case, and splitting it into tokens (words). This process prepares the data in a format that is easy to analyze.

[0985] The server then analyzes the pre-processed text data using a generative AI that includes a natural language processing model. This analysis method uses the natural language processing model to extract key points or points from the text data. To do this, the server uses a generative AI model and inputs prompts such as the following into the model:

[0986] "Please extract key points about business leadership."

[0987] The server then quantifies the extracted claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate the importance of each claim. This quantification method makes it possible to quantitatively indicate which claims are more important.

[0988] Finally, the server uses a means to visually display the quantified key points by converting the numerical data into graphs and charts and presenting them to the user on their device screen in a format that can be easily understood at a glance, such as bar graphs or pie charts.

[0989] For example, if a user wants to analyze a book on "Business Leadership," the server collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" and preprocesses them. It then uses a generative AI model to analyze the content, extracting key assertions such as "The Importance of Leadership," "Driving Innovation," and "Effective Communication," and quantifying them. It then creates graphs and charts and presents the results to the user on their device, allowing them to easily grasp the key points.

[0990] In this way, the system can quickly and accurately extract important points from business books and present them visually, allowing users to effectively gather information and acquire knowledge.

[0991] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0992] Step 1:

[0993] The server reads e-book data from a specific directory and stores it in memory. As input, the e-book data is given in the form of a text file. The server opens the file, reads its contents, and generates text data as output to store in memory.

[0994] Step 2:

[0995] The server performs preprocessing on the read text data. The text data obtained in step 1 is used as input. The server removes unnecessary line breaks and special characters, converts the text to lower case, and splits it into tokens (words). The output is the preprocessed tokenized text data.

[0996] Step 3:

[0997] The server uses a natural language processing model to parse the preprocessed text data, using as input the tokenized text data generated in step 2. The server inputs the generative AI model using the following prompt sentence:

[0998] "Please extract key points about business leadership."

[0999] The generative AI model extracts key points and summaries and outputs them in summary form.

[1000] Step 4:

[1001] The server then quantifies the extracted claims. The claims extracted in step 3 are used as input. The server then numerically evaluates the importance of each claim using TF-IDF (Term Frequency-Inverse Document Frequency). The output is a quantified importance score.

[1002] Step 5:

[1003] The server converts the quantified key claims into visual display data, using the quantified importance scores from step 4 as input. The server converts these scores into graphs and charts to generate visually displayable data. The output is the visual display data.

[1004] Step 6:

[1005] The terminal displays the visual display data provided by the server on its screen. The visual display data sent from the server is used as input. The terminal displays graphs and charts in a format that the user can understand at a glance and provides them to the user. As output, a display that the user can visually understand is obtained.

[1006] In this way, the specific operation has been explained while clarifying the input and output at each step.

[1007] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1008] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main arguments, and visually displays them, with an emotion engine that recognizes the user's emotions. Specific embodiments of this system are described below.

[1009] 1. Loading book data

[1010] Subject: Server

[1011] The server loads the electronic data of business books from the specified directory. These are saved in text file format, and the server opens the files and stores their contents in memory. For example, a file such as "LeadershipGuide.txt" is loaded.

[1012] 2. Text Preprocessing

[1013] Subject: Server

[1014] The server preprocesses the book data it has loaded. This preprocessing removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[1015] 3. Content analysis and assertion extraction

[1016] Subject: Server

[1017] The server then passes the preprocessed text data to a generative AI system, which analyzes the content using a natural language processing model. This process extracts key points and key ideas from the text, such as "the importance of leadership" and "driving innovation."

[1018] 4. Quantifying your claims

[1019] Subject: Server

[1020] The server then quantifies the extracted key claims. Specifically, it uses TF-IDF (Term Frequency-Inverse Document Frequency) to numerically evaluate how important each claim is. This results in an importance score being assigned to each claim.

[1021] 5. User Emotion Recognition

[1022] Subject: Server

[1023] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's face through a camera to determine the emotion.

[1024] 6. Providing and adjusting results

[1025] Subject: Server

[1026] The server visually displays the key points, quantified. At this stage, the display is dynamically adjusted based on the user's emotions, as recognized by the emotion engine. For example, if the user is excited, a colorful graph is used to emphasize the main points.

[1027] Specific examples

[1028] For example, if a user wishes to analyze several business books on "business leadership," the following process may be performed:

[1029] 1. The server reads the book data and collects files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the directory.

[1030] 2. The server preprocesses the book data, removing unnecessary characters and splitting the text into tokens.

[1031] 3. The server uses generative AI to analyze the content and extract key assertions such as "the importance of leadership" and "driving innovation."

[1032] 4. The server quantifies the claims and uses TF-IDF to evaluate the importance score of each claim.

[1033] 5. The server recognizes the user's emotions and determines their feelings based on facial expression analysis and text input.

[1034] 6. The server provides the results to the user, highlighting key points based on the user's emotions, for example, using colorful graphs if the user is excited.

[1035] This allows users to quickly understand important points from multiple business books, and since their emotions are also taken into consideration in the process, they can receive more personalized information.

[1036] The processing flow will be explained below.

[1037] Step 1:

[1038] The server reads the book data from the directory. The server finds all text files in the specified directory, opens them, and stores their contents in memory. For example, files like "LeadershipGuide.txt" and "InnovationInManagement.txt" are read.

[1039] Step 2:

[1040] The server preprocesses the book data it has loaded. Specifically, it removes unnecessary line breaks and special characters, converts the text to lowercase, and splits it into tokens (words). This prepares the text data in a format suitable for analysis.

[1041] Step 3:

[1042] The server then passes the preprocessed text data to a generative AI for content analysis. The generative AI uses natural language processing models to extract key points and key points from the text. For example, key phrases such as "the importance of leadership" and "driving innovation" are extracted.

[1043] Step 4:

[1044] The server then quantifies the extracted key claims, using a technique called Term Frequency-Inverse Document Frequency (TF-IDF) to numerically evaluate the importance of each claim, and assigns each claim an importance score.

[1045] Step 5:

[1046] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. For example, it analyzes the user's facial expression through a camera to determine the emotion.

[1047] Step 6:

[1048] The server uses the emotional information obtained from the emotion engine to visually display the quantified claims. This process converts the numerical data into graphs and charts, providing them in a format that users can understand at a glance. The display method is dynamically adjusted based on the user's emotional state. For example, if the user is excited, a colorful graph will be used to emphasize the main points.

[1049] Step 7:

[1050] The user checks the results provided by the server. By viewing visualized data, the user can understand the main points and important arguments of multiple business books at a glance. Personalized information provided according to the user's emotional state allows the user to collect information more effectively and use it to make decisions.

[1051] Example 2

[1052] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1053] Conventional business book analysis systems can extract the main arguments from books and display them in numerical form, but they have the problem of not being able to provide personalized information without taking into account the user's emotions, making it difficult to improve user understanding and satisfaction.

[1054] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1055] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative model that analyzes the information, means for quantifying the main claims, means for visually displaying the quantified main claims, means including an emotion engine for recognizing a user's emotion, and means for dynamically adjusting the display method based on the recognized emotion. This makes it possible to effectively present the main claims of business books while taking the user's emotion into consideration.

[1056] "Information storage means" refers to a device or system that has the function of storing and managing electronic data of business books.

[1057] A "generative model" is a computational model that uses natural language processing to extract key points or insights from text data.

[1058] A "means for extracting key claims" is a device or system that has the functionality to use a generative model to find important claims and information from electronic data of business books.

[1059] The "means for quantifying key claims" is a device or system that has the function of quantitatively evaluating and scoring the importance of extracted claims.

[1060] A "visual display means" is a device or system capable of presenting a quantified assertion to a user in a visual format, such as a graph or chart.

[1061] The "emotion engine" is a calculation engine that recognizes and determines emotions through user text input and facial expression analysis.

[1062] A "dynamic adjustment means" is a device or system that has the capability to adapt the content and manner of display in real time based on the recognized user emotion.

[1063] This invention combines a conventional system that stores and analyzes information from business books, extracts and quantifies the main points, and visually displays them, with an emotion engine that recognizes the user's emotions. The following describes how this system is specifically implemented.

[1064] Loading book data

[1065] Subject: Server

[1066] The server reads the electronic data of business books from a specified directory. This data is stored in text file format, and the server opens each file and stores its contents in memory. For example, it reads files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" from the " / data / books" directory. This process uses a file management system and a software library for input / output operations.

[1067] Text Preprocessing

[1068] Subject: Server

[1069] The server preprocesses the loaded book data. This preprocessing involves using regular expressions to remove unnecessary line breaks and special characters, converting the text to lowercase, and splitting it into tokens (words). This prepares the text data in a format suitable for analysis. The software used includes natural language processing libraries (e.g., NLTK, SpaCy).

[1070] Content analysis and assertion extraction

[1071] Subject: Server

[1072] The server passes the preprocessed text data to a generative AI model for natural language processing. During this process, the generative AI model extracts key points and insights from the text. Specifically, models such as BERT and GPT-3 are used as generative AI models. For example, assertions such as "the importance of leadership" and "driving innovation" are extracted.

[1073] Quantifying claims

[1074] Subject: Server

[1075] The server then quantifies the extracted key claims. Specifically, it uses the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm to numerically evaluate the importance of each claim. For example, "importance of leadership" is assigned a score of 0.8, and "promotion of innovation" is assigned a score of 0.6.

[1076] User Emotion Recognition

[1077] Subject: Server

[1078] The server uses an emotion engine to recognize the user's emotions. This engine recognizes emotions through the user's text input and facial expression analysis. It analyzes the user's face through a camera to determine their emotion. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[1079] Providing and adjusting results

[1080] Subject: Server

[1081] The server visually displays the key points quantified. At this stage, the display method is dynamically adjusted based on the user's emotions, which are recognized by the emotion engine. For example, if the user is excited, colorful graphs are used to emphasize the main points. For this purpose, data visualization libraries (e.g., D3.js, Matplotlib) are used.

[1082] Specific examples

[1083] As a concrete example, consider a case where a user wants to analyze several business books on "Business Leadership." The following process is performed:

[1084] 1. The server reads the book data and scans "LeadershipGuide.txt", "InnovationInManagement.txt", etc. to obtain the contents.

[1085] 2. The server performs preprocessing, removing unnecessary characters and splitting the text into tokens.

[1086] 3. The server uses generative AI to extract key points, such as "The importance of leadership."

[1087] 4. The server quantifies the importance of the claims using TF-IDF and assigns an importance score to each claim.

[1088] 5. The server analyzes the user's emotions using the camera and microphone to determine their current emotions.

[1089] 6. The server adjusts the visual display based on emotion, highlighting key points with colorful graphs.

[1090] Prompt Sentence Examples

[1091] Use the following as an example prompt for the generative AI model:

[1092] "Summarize the contents of the following business books and extract the main points: LeadershipGuide.txt, InnovationInManagement.txt. Also, analyze user sentiment to highlight key points."

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Step 1: Loading the book data

[1095] Subject: Server

[1096] The server reads the electronic data of the business book from the specified directory.

[1097] (Input): Directory path " / data / books"

[1098] (Specific behavior): Scan the " / data / books" directory and find files such as "LeadershipGuide.txt" and "InnovationInManagement.txt". Then, open each file one by one and store its contents in memory. If the contents of the text file are in Unicode format, check the encoding and decode it appropriately.

[1099] (Output): Text data stored in memory

[1100] Step 2: Preprocessing the text

[1101] Subject: Server

[1102] The server preprocesses the loaded book data.

[1103] (Input): Text data stored in memory

[1104] (Specific operation): As a preprocessing step, unnecessary line breaks and special characters are removed using regular expressions, and the text is converted to all lowercase. After that, the text is split into tokens by whitespace characters. For example, the sentence "The Leader is ..." is converted to lowercase "the leader is ..." and split into tokens. A natural language processing library (e.g., NLTK, SpaCy) is used for this process.

[1105] (Output): Tokenized word list

[1106] Step 3: Analyze content and extract claims

[1107] Subject: Server

[1108] The server passes the preprocessed data to the generative AI model for natural language processing.

[1109] (Input): Tokenized word list

[1110] (Specific operation): Pass the tokenized data to a generative AI model along with a prompt to extract the main claim. For example, use BERT or GPT-3 as the generative AI model. Provide the prompt "Extract the main claim from the following text: 'the leader is...'". The model will return claims such as "The importance of leadership" and "Promoting innovation".

[1111] (Output): List of extracted key claims

[1112] Step 4: Quantify your claims

[1113] Subject: Server

[1114] The server quantifies the extracted key assertions.

[1115] (Input): List of extracted key claims

[1116] (Specific behavior): Using the TF-IDF algorithm, the importance of each claim is evaluated. For example, "importance of leadership" is assigned a score of 0.8, and "driving innovation" is assigned a score of 0.6. This process is performed using machine learning libraries such as SciKit-Learn.

[1117] (Output): A list of claims and their TF-IDF scores

[1118] Step 5: Recognizing User Emotions

[1119] Subject: Server

[1120] The server uses an emotion engine to recognize the user's emotions.

[1121] (Input): Real-time video and audio data of the user

[1122] (Specific operation): Analyzes the user's facial expressions and voice in real time using a camera and microphone. For example, if the user is smiling, it is determined to be "happy," and if they are frowning, it is determined to be "confused." Facial expression analysis uses computer vision libraries (e.g., OpenCV) and machine learning models.

[1123] (Output): User's emotional data (e.g., "happy," "confused," etc.)

[1124] Step 6: Delivering and adjusting results

[1125] Subject: Server

[1126] The server visually displays the quantified claims and dynamically adjusts the display content based on the user's emotions.

[1127] (Input): A list of claims and their TF-IDF scores, and user sentiment data

[1128] (Specific Action): Present your main argument in a visual format such as a graph or chart. For example, if the user is excited, use a colorful graph to emphasize the point. Use a data visualization library (e.g., D3.js, Matplotlib) for this process.

[1129] (Output): A dynamically adjusted visual display presented to the user.

[1130] (Application example 2)

[1131] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1132] It is difficult to extract the main points from information-rich documents such as business books and to understand them efficiently. In addition, there is a need for technology that can provide more personalized information by adjusting the display method according to the emotional state of each individual user.

[1133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1134] In this invention, the server includes means for storing information, means for extracting main claims from the information using a generative artificial intelligence that analyzes the information, means for quantifying the main claims, means for recognizing a user's emotions, means for dynamically adjusting the display method of the quantified main claims based on the user's emotions, and means for visually displaying the quantified main claims. This allows a user to quickly understand important points from multiple books and, in the process, receive more satisfying information through a display method that takes the user's emotional state into consideration.

[1135] "Means for storing information" is a function for saving text data such as business books in a storage device.

[1136] "Generative AI" is an AI technology that uses natural language processing to analyze text data and extract key points.

[1137] "Means for extracting key points" is a function for finding and extracting important points and points from text data.

[1138] The "means for quantifying the main claims" is a function for calculating the importance of the extracted claims and evaluating them numerically.

[1139] "Means for recognizing user emotions" refers to technology that uses a camera or text input to analyze and determine a user's emotional state.

[1140] The "means for dynamically adjusting the display method" is a function for changing the display method of an assertion in real time based on the recognized user sentiment.

[1141] "Visual display means" refers to techniques for presenting analyzed information and key arguments in a form that can be seen by the user, such as graphs, charts, or text.

[1142] This invention is a system that analyzes information from business books, extracts and quantifies key points, and dynamically adjusts the display method of the results by recognizing the user's emotions. This system is composed of a means for storing information, a generative artificial intelligence that analyzes the information, a means for quantifying key points, a means for recognizing the user's emotions, a means for dynamically adjusting the display method, and a means for visually displaying the quantified key points.

[1143] Program processing explanation

[1144] The server reads the digital data of business books from a specified directory and stores it in memory. The read text data is preprocessed to remove unnecessary line breaks and special characters and divide the text into tokens. This text data is then passed to a generative AI model for analysis and content extraction. The generative AI model uses natural language processing techniques to extract and quantify key points.

[1145] To recognize a user's emotions, the server analyzes the user's emotional state using a camera or text input. Image processing libraries such as OpenCV and dedicated emotion recognition models are used for emotion analysis. After the corresponding emotion is determined, the information is used to dynamically adjust the display method.

[1146] Specifically, if the user is "excited," the extracted assertions are emphasized using colorful graphs, etc. On the other hand, if the user is "neutral," the standard display method is applied. This allows the user to visually understand the information in a way that is appropriate for their emotions.

[1147] The device provides visually displayed assertions, which the user can receive through a display or head-mounted display, allowing the user to quickly understand important points from multiple business publications and receive personalized information according to emotional changes.

[1148] Specific examples

[1149] A user loads a book on "Business Leadership." Files such as "LeadershipGuide.txt" and "InnovationInManagement.txt" are collected from the directory by the server. The server then preprocesses the data and passes it to a generative AI model to extract key assertions, such as "The Importance of Leadership" and "Driving Innovation." These assertions are then quantified using TF-IDF. Meanwhile, the user's emotions are analyzed from a photo (e.g., "user_image.jpg"), which is determined to indicate "excitement." Based on this information, the extracted assertions are highlighted in a colorful graph and presented to the user.

[1150] Prompt Sentence Examples

[1151] Prompt: "Extract the main idea from this text:\nText: XXXX"

[1152] This embodiment helps users quickly understand the main arguments of a business book in a manner that is responsive to their emotional state.

[1153] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1154] Step 1:

[1155] The server reads the digital data of a business book from the specified directory. Specifically, it opens a file such as "LeadershipGuide.txt" and stores its contents in memory. The input is the path to the e-book file, and the output is the read text data.

[1156] Step 2:

[1157] The book data loaded by the server is preprocessed. Specifically, unnecessary line breaks and special characters are removed, all characters are converted to lowercase, and the data is split into tokens (words). The input is the loaded text data, and the output is the preprocessed text data.

[1158] Step 3:

[1159] The server passes the preprocessed text data to the generative AI model, which then uses natural language processing techniques to extract key claims. The input is the preprocessed text data, and the output is the extracted key claims (key phrases). Specifically, the system uses the Hugging Face Transformer model.

[1160] Step 4:

[1161] The server uses TF-IDF to quantify the extracted key claims. The input is the extracted key claims, and the output is the importance score of the key claims. Specifically, we use TfidfVectorizer to calculate the weight of each claim.

[1162] Step 5:

[1163] The server analyzes the user's face captured through a camera to recognize the user's emotions. The input is the user's facial image data, and the output is the determined user's emotional state. Specifically, OpenCV and an emotion recognition model are used.

[1164] Step 6:

[1165] The server dynamically adjusts the display of the quantified key claim based on the user's perceived emotion. The input is the key claim importance score and the user's emotional state, and the output is the adjusted display format. For example, if the user is excited, it is displayed as a colorful graph, and if the user is neutral, it is displayed as standard text.

[1166] Step 7:

[1167] The server visually displays the quantified key assertions in the adjusted display format. The input is the adjusted display format, and the output is the visual content displayed on the user's device. Specifically, it is presented to the user via a display or head-mounted display.

[1168] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1169] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1170] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1171] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1172] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1173] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1174] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1175] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1176] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1177] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1178] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1179] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1180] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1181] 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.

[1182] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1183] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1184] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1185] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1186] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1187] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1188] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1189] The following is further disclosed regarding the above embodiment.

[1190] (Claim 1)

[1191] means for storing said information;

[1192] means for extracting key claims from said information using generative artificial intelligence to analyze said information;

[1193] a means for quantifying said key assertions;

[1194] a means for visually displaying said quantified key assertions;

[1195] A system including:

[1196] (Claim 2)

[1197] The system of claim 1 , wherein the information is electronic book data.

[1198] (Claim 3)

[1199] The system of claim 1 , wherein the generative artificial intelligence includes a natural language processing model.

[1200] (Claim 4)

[1201] 2. The system of claim 1, wherein the digitizing means uses TF-IDF (Term Frequency-Inverse Document Frequency).

[1202] (Claim 5)

[1203] 10. The system of claim 1, wherein said visual display means uses a graph.

[1204] "Example 1"

[1205] (Claim 1)

[1206] means for reading electronic data from a particular directory;

[1207] A means for preprocessing the text to remove unnecessary characters and to divide the text into tokens;

[1208] A means for extracting key assertions from the pre-processed data using a generative AI model; and

[1209] A means for quantifying the main assertions using TF-IDF;

[1210] a means for visually displaying said quantified key assertions;

[1211] A system including:

[1212] (Claim 2)

[1213] 2. The system of claim 1, wherein the information is electronic data.

[1214] (Claim 3)

[1215] 10. The system of claim 1, wherein the generative AI model comprises a natural language processing model.

[1216] "Application Example 1"

[1217] (Claim 1)

[1218] means for storing said information;

[1219] means for extracting key claims from said information using generative artificial intelligence to analyze said information;

[1220] a means for quantifying said key assertions;

[1221] a means for visually displaying said quantified key assertions;

[1222] means for performing preprocessing of the information on book data;

[1223] means for analyzing the information using a natural language processing model;

[1224] means for converting the summarized assertions into visual display data;

[1225] A system including:

[1226] (Claim 2)

[1227] The system of claim 1 , wherein the information is electronic book data, and the electronic book data is divided into tokens.

[1228] (Claim 3)

[1229] 2. The system of claim 1, wherein the generative artificial intelligence includes a natural language processing model, and the summarization is performed using prompt sentences based on the generative AI model.

[1230] "Example 2: Combining Emotion Engines"

[1231] (Claim 1)

[1232] means for storing said information;

[1233] means for extracting key assertions from the information using a generative model that analyzes the information;

[1234] a means for quantifying said key assertions;

[1235] a means for visually displaying said quantified key assertions;

[1236] means including an emotion engine for recognizing an emotion of a user;

[1237] means for dynamically adjusting the display method based on the recognized emotion;

[1238] A system including:

[1239] (Claim 2)

[1240] The system of claim 1 , wherein the information is electronic book data.

[1241] (Claim 3)

[1242] The system of claim 1 , wherein the generative model uses natural language processing.

[1243] "Application example 2 when combining emotion engines"

[1244] (Claim 1)

[1245] means for storing said information;

[1246] means for extracting key claims from said information using generative artificial intelligence to analyze said information;

[1247] a means for quantifying said key assertions;

[1248] means for recognizing the emotion of the user;

[1249] means for dynamically adjusting the display of the quantified key claims based on the user's sentiment;

[1250] a means for visually displaying said quantified key assertions;

[1251] A system including:

[1252] (Claim 2)

[1253] The system of claim 1 , wherein the information is electronic book data.

[1254] (Claim 3)

[1255] The system of claim 1 , wherein the generative artificial intelligence includes a natural language processing model. [Explanation of symbols]

[1256] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for storing said information; means for extracting key claims from said information using generative artificial intelligence to analyze said information; a means for quantifying said key assertions; a means for visually displaying said quantified key assertions; A system including:

2. The system of claim 1 , wherein the information is electronic book data.

3. The system of claim 1 , wherein the generative artificial intelligence comprises a natural language processing model.

4. The system of claim 1, wherein the means for quantifying uses TF-IDF (Term Frequency-Inverse Document Frequency).

5. 2. The system of claim 1, wherein said visual display means uses a graph.

Images