system

Abstract

We provide the system. [Solution] A means for obtaining identification information of information items displayed on the user terminal, means for obtaining detailed information of an information item from an information processing device based on the aforementioned identification information, A means for analyzing the aforementioned detailed information using a language model and generating summary information, Means for displaying the summary information on a display screen, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the rapid increase of information in modern society, it has become difficult for users to grasp important information for themselves in a short time. Especially in news articles, a huge amount of information is updated daily, and understanding all of this is a high burden for users. In such a situation, there is a need for a method that allows users to efficiently and comprehensively understand news and information in a summarized manner.

Means for Solving the Problems

[0005] This invention provides a system in which a user terminal displaying news articles automatically summarizes the articles with simple operation from the user. This system acquires identification information for information items displayed on the user terminal and obtains detailed information for those items from an information processing device based on that identification information. The acquired detailed information is analyzed by a language model trained using a machine learning algorithm to generate summary information. The generated summary information is displayed in multiple formats according to the user's needs, allowing the user to quickly and efficiently obtain important information.

[0006] A "user terminal" refers to an electronic device used by users to display news articles and information items and to operate them.

[0007] "Identifying information for displayed information items" refers to data used to uniquely identify a specific news article or information item.

[0008] An "information processing device" refers to a central system that stores detailed information about information items and provides that information in response to requests from terminals.

[0009] "Detailed information" refers to the complete content of a specific piece of information, including news articles.

[0010] A "language model" refers to a machine learning algorithm trained to analyze text and summarize it.

[0011] "Summary information" refers to information that concisely expresses the main points extracted from detailed information.

[0012] "Display screen" refers to an interface used to visually display summary information on a user's terminal.

[0013] A "machine learning algorithm" refers to a method of learning rules and patterns from large amounts of data, and is used to train language models. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

[0017] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Also, the 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), an APU (Accelerated Processing Unit), and the like.

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

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

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention provides an automated summarization system for users to efficiently understand web news. Specifically, a "Generate AI Summary" button is displayed on the web news page on the user's terminal. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article to the server. Based on the received identification information, the server retrieves detailed information about the news article from its database.

[0036] The acquired detailed information is automatically analyzed using a language model. This language model is trained on a large amount of news data using machine learning algorithms and has the ability to extract the main points and key aspects of an article. The analyzed information is generated as a summary and sent from the server to the terminal.

[0037] The terminal displays the received summary information on the user interface, allowing users to quickly grasp the news summary. This system enables users to quickly understand vast amounts of news information and access detailed information as needed.

[0038] As a concrete example, when a user accesses an economic news article, the server analyzes the article's content and generates summary information such as "Major companies report better-than-expected quarterly earnings." This summary information is displayed on the user's device, allowing them to immediately grasp the main points of the article. This enables users to efficiently gather information and, if necessary, quickly access detailed article content.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] When a user views an article on a news website, their device will display a "Generate AI Summary" button on the page.

[0042] Step 2:

[0043] When a user clicks the "Generate AI Summarize" button, the device sends the article's identification information to the server. This identification information allows the server to determine which articles should be summarized.

[0044] Step 3:

[0045] The server uses the received identification information to retrieve detailed information about the relevant news article from the database.

[0046] Step 4:

[0047] The server passes detailed information from retrieved news articles to a language model for analysis to perform summarization. This language model uses a trained machine learning algorithm to extract the main points of the article and generate summary information.

[0048] Step 5:

[0049] The server sends the generated summary information to the terminal.

[0050] Step 6:

[0051] The device displays the received summary information on the user interface. By viewing this summary information, the user can quickly understand the key points of the article.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] In today's information society, users are surrounded by vast amounts of information and are required to efficiently acquire the information they need. However, traditional methods require manually selecting important information from a massive dataset, which is time-consuming and laborious. Therefore, there is a need for automated systems that allow users to quickly grasp information and access details as needed.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes means for acquiring identification information of an article displayed on the user's terminal, means for acquiring detailed information of the article from an information processing device based on the identification information, and means for analyzing the detailed information using a natural language processing model and generating summary information. This enables the user to understand the main points of the article in a short time and to efficiently collect information.

[0057] A "user terminal" is an electronic device used to acquire and display information, and which can be directly operated by the user.

[0058] "Article identification information" refers to unique information used to identify a particular article, and is usually represented as a URL or identifier code.

[0059] An "information processing device" is a computer device that acquires, analyzes, and generates data, and functions as a server.

[0060] A "natural language processing model" is an algorithm that uses machine learning techniques to analyze human language, and has the function of extracting important information from text and generating a summary.

[0061] "Summary information" is a concise summary of key information extracted from a longer article, used to help users understand the main points of the article in a short amount of time.

[0062] This invention provides an automated summarization system that enables users to efficiently understand news articles. The system consists of a user terminal, a server, and a trained natural language processing model.

[0063] The user's device provides a "Generate AI Summary" button on the webpage displaying the news article. When the user clicks this button, the device sends identification information to the server to uniquely identify the article. The client's browser plays a crucial role in sending this identification information.

[0064] Based on the received identification information, the server uses an information processing device and a database to retrieve detailed information about the article. This includes the article's title and the entire body of the text. Next, the server uses a natural language processing model (for example, a model using machine learning techniques such as BERT or GPT) to analyze the retrieved article. This model is used to analyze the article's content, extract important information, and generate a summary.

[0065] The generated summary information is sent from the server to the user's terminal. The terminal displays this summary information on its user interface, allowing the user to quickly grasp the main points of the article. This process enables users to efficiently obtain important information from a large amount of article data.

[0066] For example, when a user accesses an economic news article and presses the "Generate AI Summary" button, the server generates a summary such as "Major companies report better-than-expected quarterly earnings," which is immediately displayed on the user's device. This allows the user to access important information while saving time reading the entire article. As an example of a prompt, the system can be asked to generate a specific summary by using "Generate a summary of this article. Article ID: 12345."

[0067] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0068] Step 1:

[0069] The user clicks the "Generate AI Summary" button displayed on the web news page on their device. This action retrieves the identifying information of the currently displayed news article (e.g., URL and article ID). The input is the user's click operation, and the output is the article's identifying information.

[0070] Step 2:

[0071] The terminal sends the identification information of the retrieved article to the server. The server receives this identification information as input and queries the database to retrieve detailed information about the article. At this point, the output is the specific details of the article (title, body, etc.). Retrieval from the database is performed using an SQL query.

[0072] Step 3:

[0073] The server inputs the detailed information of the obtained article into a natural language processing model. This model is used to analyze the article content and generate a summary. This analysis includes processes such as tokenization, extraction of key sentences, and identification of main points. The input is the detailed information of the article, and the output is the summary.

[0074] Step 4:

[0075] The server sends the generated summary information to the terminal. The terminal displays the summary information received from the server on a portion of the web page to present it to the user in an easy-to-understand manner. The input is the summary information, and the output is the display on the user interface. This allows the user to understand the core of the article in a short amount of time.

[0076] (Application Example 1)

[0077] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0078] In today's information-saturated world, users are required to quickly acquire necessary information and understand it efficiently. Furthermore, there is a lack of means to flexibly utilize information in various aspects of work and daily life. In particular, information visualization devices require simple operation via voice commands and the instantaneous presentation of summarized information.

[0079] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0080] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for receiving user instructions using a speech recognition device. As a result, the user can efficiently acquire information by giving voice instructions and instantly grasp the summarized information on a visualization device.

[0081] A "user terminal" is a device that displays information items and serves as an interface with the user.

[0082] "Identification information" refers to information used to uniquely identify an information item.

[0083] An "information processing device" is a device that stores detailed information and provides information based on identification information.

[0084] "Detailed information" refers to information that includes specific details related to the information item.

[0085] A "language model" is a model trained using natural language processing algorithms, and is used to analyze information and extract key points.

[0086] "Summary information" refers to concise information that includes the main points and key takeaways extracted from detailed information.

[0087] A "visual output device" is a device for displaying summarized information, and its role is to provide information to users visually.

[0088] A "voice recognition device" is a device that identifies the user's voice commands and activates the appropriate function.

[0089] The system for carrying out this invention consists of a visual output device (e.g., smart glasses) worn by the user and a voice recognition device. This system acquires identification information of information items, retrieves detailed information from an information processing device, and then generates summary information using a language model. The summary information is provided to the user by the visual output device. Furthermore, this system includes a voice recognition device that simplifies user operation through voice instructions.

[0090] When a user wears smart glasses and gives voice commands regarding specific news or product information, the visual output device acquires identification information for the information item. The device sends this information to a server, which retrieves detailed information from the information processing device. This detailed information is analyzed using a language model that applies natural language processing technology (e.g., BERT) and generated as summary information. The generated summary information is sent from the server to the visual output device and displayed in the user's field of vision. This allows the user to grasp the information instantly.

[0091] The server functions as the backend environment for this information processing, utilizing hardware and software suitable for information gathering and analysis. For example, it might use a server machine with powerful processing capabilities or a state-of-the-art software environment to run natural language processing libraries.

[0092] For example, if a store staff member needs to explain a new product, they can give a voice command such as "Summarize the features of the new product," and the smart glasses will display summary information such as "This product features a next-generation processor and an extended battery." This allows staff to quickly and accurately convey product information to customers. An example of a prompt would be, "Please summarize the technical details of the new product."

[0093] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0094] Step 1:

[0095] The user wears a visual output device (smart glasses) and gives voice commands to the object for which they want to know information. The input here is the user's voice command. The voice recognition device converts this voice command into text data and sends it to the terminal.

[0096] Step 2:

[0097] The terminal analyzes the received text data and identifies the identification information related to the information items. This identification information serves as a key to retrieve detailed information from the information processing device. The output after processing is the identified identification information.

[0098] Step 3:

[0099] The server uses the identification information received from the terminal to access the information processing device and retrieve the relevant detailed information. The retrieved detailed information includes datasets of news articles and product descriptions. The output is a dataset of detailed information.

[0100] Step 4:

[0101] The server analyzes the acquired detailed information using a language model (e.g., BERT). This analysis extracts key points from the detailed information and generates a summary. The input is a dataset of detailed information, and the output is the summary.

[0102] Step 5:

[0103] The server sends the generated summary information to the terminal. The terminal provides this information to a visual output device, allowing the user to immediately visually confirm the summary content. Here, the input is the summary information, and the output is a visually presented summary text.

[0104] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0105] This invention combines an automated summarization system for users to efficiently understand web news with an emotion engine that recognizes the user's emotions. The user's terminal is equipped with a "Generate AI Summarize" button when displaying web news articles. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article and data that infers the user's emotions to the server.

[0106] The server retrieves detailed information about news articles from a database based on identification information and analyzes that information using a language model. The language model, trained by machine learning algorithms, extracts the main points and key aspects of the article to generate a summary. Simultaneously, an emotion engine recognizes the user's emotions and influences how the generated summary is presented.

[0107] Specifically, the emotion engine analyzes the tone, speed, and selected words of the user's voice and text input to recognize their emotions. Based on this recognition, it provides a detailed summary if the user is relaxed, and a concise summary highlighting only the key points if they are in a hurry. Furthermore, it may guide users to additional relevant information if their interest or curiosity is heightened. This system allows users to efficiently process news in a way that suits their emotional state and needs, improving the quality of information gathering.

[0108] For example, when a user is reading a sports article, if the device's emotion engine recognizes that the user is enjoying it, the summary information will highlight more memorable moments from the game, keeping the user engaged. This allows users to experience the news more than just as a stream of information.

[0109] The following describes the processing flow.

[0110] Step 1:

[0111] While a user is viewing a news article, the device displays a "Generate AI Summary" button. This button serves as an interface for users to click if they want to view a summary of the article.

[0112] Step 2:

[0113] When a user clicks the "Generate AI Summarize" button, the device collects the article's identification information and the user's input data (voice or text).

[0114] Step 3:

[0115] The device sends the collected identification information and input data to the server. At this point, the server prepares to both identify the news article and infer the user's sentiment.

[0116] Step 4:

[0117] The server uses identification information to retrieve detailed information about the target news article from the database. Simultaneously, it analyzes the user's input data using an emotion engine to determine their emotions.

[0118] Step 5:

[0119] The language model analyzes the acquired news articles, extracts the main points, and generates summary information. This process is supported by machine learning algorithms.

[0120] Step 6:

[0121] The emotion engine recognizes the user's emotions and adjusts the presentation format of the summary information based on that. For example, if it determines that the user is in a hurry, it selects a short and concise summary.

[0122] Step 7:

[0123] The server sends the adjusted summary information to the terminal.

[0124] Step 8:

[0125] The device displays the received summary information on the user interface. Users can view summaries that are relevant to their situation and efficiently grasp the information.

[0126] (Example 2)

[0127] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0128] In today's information-saturated world, users are required to quickly and efficiently access and understand a wide variety of news articles. However, news articles can be time-consuming to read and often lack information tailored to the user's emotions and circumstances. As a result, information may be missed or misunderstood.

[0129] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0130] In this invention, the server includes means for acquiring identification information of news articles, means for inferring emotional states, and means for generating summaries using a generative AI model and providing them in a format appropriate to the emotional state. This enables users to quickly and efficiently understand news articles in accordance with their emotional state and circumstances.

[0131] A "user terminal" is an electronic device that a user operates to display and manipulate information.

[0132] "Identification information" refers to data used to uniquely recognize specific information items.

[0133] An "information item" is a unit of digital content provided to users, such as a news article.

[0134] An "information processing device" is a computer system used for managing and processing data.

[0135] A "generative AI model" is an artificial intelligence program that is trained based on machine learning algorithms to analyze text and generate summaries.

[0136] "Emotional state" refers to the state of a user's emotional situation or reaction.

[0137] "Audio or text data" refers to input signals or textual information used to analyze a user's emotions.

[0138] "Summary information" is text that concisely expresses the main points and important aspects of an information item.

[0139] This invention is an automated summarization system designed to help users efficiently understand web news, and includes a function to recognize the user's emotions and adjust the summary accordingly. The user's terminal displays the news article and is equipped with an "Generate AI Summary" button. By pressing this button, the user requests a summary of the news article.

[0140] When a user clicks the "Generate AI Summarize" button, the device obtains identification information to uniquely identify the news article and also collects and sends data to the server to infer the user's sentiment. This sentiment data includes the tone and speed of voice and text input, as well as selected words.

[0141] The server uses identification information to retrieve detailed news article information from the database and analyzes it using a generative AI model. The generative AI model is trained using machine learning algorithms and extracts the main points and key aspects of the article to generate a summary. The server also uses an emotion engine to analyze the user's emotional state and adjusts how the generated summary is presented based on that emotion.

[0142] Specifically, the server provides a detailed summary based on the user's emotional state; if the user is relaxed, it provides a concise summary highlighting only the main points; if the user is in a hurry, it provides a brief summary emphasizing only the key points. Furthermore, if the server determines that the user is interested, it can also guide them to additional relevant information.

[0143] For example, if a user is enjoying sports news, the emotion engine recognizes this and provides a summary that keeps the user engaged by detailing memorable moments from the game. In this way, news articles become experiential content that goes beyond mere information dissemination.

[0144] An example of a prompt message is, "Please summarize this news. Also, if the user is in a hurry, please highlight only the key points." This allows the AI ​​to generate output that meets the specified conditions.

[0145] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0146] Step 1:

[0147] The user first views a web news article displayed on their device. If the user decides they want to summarize a particular news article, they click the "Generate AI Summarize" button on their device. This action causes the device to obtain identifying information such as the URL and article ID of the news article as input. Next, along with this identifying information, the device also collects sentiment inference data obtained from voice and text input, and sends these to the server.

[0148] Step 2:

[0149] The server uses the identification information received from the terminal to retrieve detailed information about the corresponding news article from the database. This data retrieval yields the article's text and related metadata as output. This prepares the server for the subsequent text analysis.

[0150] Step 3:

[0151] The server inputs the retrieved news article into a generative AI model. The prompt used is "Please summarize this news." The generative AI model, trained with machine learning algorithms, analyzes the input data of the news article and generates a summary. This process outputs summary information that extracts the main points and key aspects of the article.

[0152] Step 4:

[0153] The server activates its emotion engine and analyzes the emotion prediction data transmitted from the terminal. Specifically, it analyzes factors such as voice tone, text content, and input speed to predict the user's emotional state. Based on this prediction, it determines whether the user is relaxed, in a hurry, or highly interested.

[0154] Step 5:

[0155] The server adjusts the generated summary information based on the emotional state. For example, if the user is relaxed, it generates a summary with detailed explanations; if they are in a hurry, it generates a concise summary that highlights the key points. If the server determines that the user is agitated, it includes relevant additional information in the summary. This adjusted summary information becomes the output.

[0156] Step 6:

[0157] Ultimately, the server sends the adjusted summary information to the terminal. The terminal then displays this summary information to the user. This allows the user to view a summary of the news article in a format that best suits their emotional state in real time.

[0158] (Application Example 2)

[0159] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0160] It is difficult to accurately grasp users' emotions and interests while they are viewing content, and to present relevant information appropriately and efficiently. In particular, there is a lack of means to enhance the richness of the information users gain from the content and to provide information that meets their individual needs.

[0161] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0162] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for adjusting the generated summary information with an emotion recognition device that recognizes the user's emotions. This enables flexible information provision in response to the user's emotions.

[0163] A "user terminal" is a device capable of displaying and inputting information, and provides an interface for users to view content.

[0164] An "information item" is an individual unit of information related to specific content or data, and possesses identifying information.

[0165] "Identification information" refers to data used to uniquely identify an information item, and is used for communication with databases and information processing devices.

[0166] "Detailed information" refers to additional explanations or data related to an information item that are necessary for users to understand the information.

[0167] An "information processing device" is a device or system for processing and providing data, including databases and servers.

[0168] A "language model" is an algorithm used for natural language processing, specifically for analyzing and summarizing text data.

[0169] An "emotion recognition device" is a device that recognizes a user's emotions from voice, text, and visual characteristics, and is used to identify the user's emotional state.

[0170] A "visualization display device" is a device for visually displaying information and presenting generated summary information to the user.

[0171] "Emotion" refers to a state related to a user's feelings or mood, and is a concept used to analyze and understand the user's response to a system.

[0172] "Additional information" refers to relevant data provided according to the user's interests and emotions, and includes supplementary content to satisfy the user's information needs.

[0173] This invention is a system that identifies information items displayed on a user terminal, detects the user's emotions, and then provides a summary of the information and additional information. The server receives identification information from the user terminal and obtains detailed information through an information processing device. Then, it analyzes this detailed information using a language model as a generating AI model and generates a summary.

[0174] In this process, the user's device uses an emotion recognition device to detect the user's emotions through voice input and visual data. This emotion data is processed by a server, and the generated summary information is adjusted according to the emotion. For example, if the user is relaxed, more detailed content is displayed, while if they are in a hurry, a concise summary focusing on the key points is presented. Furthermore, if the system wants to keep the user interested, it presents relevant news and trivia as additional information.

[0175] When users are watching movies or video content, the smart glasses use an emotion engine to analyze their reactions based on the visual and audio data they capture. For example, if the system detects increased excitement or interest while watching a sports match, it will display the latest news and player information related to the match as additional information. In this way, users can gain a deeper understanding of and enjoyment of what they are watching.

[0176] For example, if a user is watching a "specific movie," the emotion engine will sense the user's level of interest and provide additional information about that movie. An example of an input prompt for the generative AI model would be: "The user is currently watching a specific movie. The emotion engine is showing high interest. Please generate additional relevant information."

[0177] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0178] Step 1:

[0179] The user selects and starts playback of content they are watching on their device. At this time, the device obtains identification information related to the content and sends it to the server. The input is the content's identification information, and the output is the transmission of this identification information to the server. Specifically, when a user selects a movie or program using a visual device such as smart glasses, that information is transmitted to the system.

[0180] Step 2:

[0181] The server retrieves detailed information from the information processing device based on the received identification information. This provides the relevant data for the content. The input is the content's identification information, and the output is the detailed information. Specifically, the server queries the database to collect detailed content information.

[0182] Step 3:

[0183] The server analyzes the acquired detailed information using a language model, which is a generating AI model, and generates summary information. The input is detailed information, and the output is the generated summary information. Specifically, the generating AI processes text data, extracts important points, and generates a summary.

[0184] Step 4:

[0185] The device uses an emotion recognition device to recognize the user's emotions from audio and visual data. The input is data related to the user's emotions, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to capture the user's facial expressions and vocalizations, and analyzes them with an emotion engine.

[0186] Step 5:

[0187] The server adjusts the generated summary information based on the recognized sentiment data and sends it to the user's terminal. The input is the recognized sentiment data and summary information, and the output is the adjusted summary information. Specifically, the server provides detailed information if the user is calm, and shortened content if the user is in a hurry.

[0188] Step 6:

[0189] The device presents the user with adjusted summary information and displays additional relevant information based on the sentiment recognition results. The input is the adjusted summary information, and the output is the displayed content. Specifically, the device displays summary information and interesting trivia on its display. For example, if the user shows interest in a particular scene, background knowledge related to that scene is added.

[0190] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0191] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0192] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0193] [Second Embodiment]

[0194] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0195] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0196] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0197] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0198] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0199] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0200] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0201] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0202] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0203] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0204] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0205] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0206] This invention provides an automated summarization system for users to efficiently understand web news. Specifically, a "Generate AI Summary" button is displayed on the web news page on the user's terminal. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article to the server. Based on the received identification information, the server retrieves detailed information about the news article from its database.

[0207] The acquired detailed information is automatically analyzed using a language model. This language model is trained on a large amount of news data using machine learning algorithms and has the ability to extract the main points and key aspects of an article. The analyzed information is generated as a summary and sent from the server to the terminal.

[0208] The terminal displays the received summary information on the user interface, allowing users to quickly grasp the news summary. This system enables users to quickly understand vast amounts of news information and access detailed information as needed.

[0209] As a concrete example, when a user accesses an economic news article, the server analyzes the article's content and generates summary information such as "Major companies report better-than-expected quarterly earnings." This summary information is displayed on the user's device, allowing them to immediately grasp the main points of the article. This enables users to efficiently gather information and, if necessary, quickly access detailed article content.

[0210] The following describes the processing flow.

[0211] Step 1:

[0212] When a user views an article on a news website, their device will display a "Generate AI Summary" button on the page.

[0213] Step 2:

[0214] When a user clicks the "Generate AI Summarize" button, the device sends the article's identification information to the server. This identification information allows the server to determine which articles should be summarized.

[0215] Step 3:

[0216] The server uses the received identification information to retrieve detailed information about the relevant news article from the database.

[0217] Step 4:

[0218] The server passes detailed information from retrieved news articles to a language model for analysis to perform summarization. This language model uses a trained machine learning algorithm to extract the main points of the article and generate summary information.

[0219] Step 5:

[0220] The server sends the generated summary information to the terminal.

[0221] Step 6:

[0222] The device displays the received summary information on the user interface. By viewing this summary information, the user can quickly understand the key points of the article.

[0223] (Example 1)

[0224] Next, we will describe Example 1. 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."

[0225] In today's information society, users are surrounded by vast amounts of information and are required to efficiently acquire the information they need. However, traditional methods require manually selecting important information from a massive dataset, which is time-consuming and laborious. Therefore, there is a need for automated systems that allow users to quickly grasp information and access details as needed.

[0226] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0227] In this invention, the server includes means for acquiring identification information of an article displayed on the user's terminal, means for acquiring detailed information of the article from an information processing device based on the identification information, and means for analyzing the detailed information using a natural language processing model and generating summary information. This enables the user to understand the main points of the article in a short time and to efficiently collect information.

[0228] A "user terminal" is an electronic device used to acquire and display information, and which can be directly operated by the user.

[0229] "Article identification information" refers to unique information used to identify a particular article, and is usually represented as a URL or identifier code.

[0230] An "information processing device" is a computer device that acquires, analyzes, and generates data, and functions as a server.

[0231] A "natural language processing model" is an algorithm that uses machine learning techniques to analyze human language, and has the function of extracting important information from text and generating a summary.

[0232] "Summary information" is a concise summary of key information extracted from a longer article, used to help users understand the main points of the article in a short amount of time.

[0233] This invention provides an automated summarization system that enables users to efficiently understand news articles. The system consists of a user terminal, a server, and a trained natural language processing model.

[0234] The user's device provides a "Generate AI Summary" button on the webpage displaying the news article. When the user clicks this button, the device sends identification information to the server to uniquely identify the article. The client's browser plays a crucial role in sending this identification information.

[0235] Based on the received identification information, the server uses an information processing device and a database to retrieve detailed information about the article. This includes the article's title and the entire body of the text. Next, the server uses a natural language processing model (for example, a model using machine learning techniques such as BERT or GPT) to analyze the retrieved article. This model is used to analyze the article's content, extract important information, and generate a summary.

[0236] The generated summary information is sent from the server to the user's terminal. The terminal displays this summary information on its user interface, allowing the user to quickly grasp the main points of the article. This process enables users to efficiently obtain important information from a large amount of article data.

[0237] For example, when a user accesses an economic news article and presses the "Generate AI Summary" button, the server generates a summary such as "Major companies report better-than-expected quarterly earnings," which is immediately displayed on the user's device. This allows the user to access important information while saving time reading the entire article. As an example of a prompt, the system can be asked to generate a specific summary by using "Generate a summary of this article. Article ID: 12345."

[0238] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0239] Step 1:

[0240] The user clicks the "Generate AI Summary" button displayed on the web news page on their device. This action retrieves the identifying information of the currently displayed news article (e.g., URL and article ID). The input is the user's click operation, and the output is the article's identifying information.

[0241] Step 2:

[0242] The terminal sends the identification information of the retrieved article to the server. The server receives this identification information as input and queries the database to retrieve detailed information about the article. At this point, the output is the specific details of the article (title, body, etc.). Retrieval from the database is performed using an SQL query.

[0243] Step 3:

[0244] The server inputs the detailed information of the obtained article into a natural language processing model. This model is used to analyze the article content and generate a summary. This analysis includes processes such as tokenization, extraction of key sentences, and identification of main points. The input is the detailed information of the article, and the output is the summary.

[0245] Step 4:

[0246] The server sends the generated summary information to the terminal. The terminal displays the summary information received from the server on a portion of the web page to present it to the user in an easy-to-understand manner. The input is the summary information, and the output is the display on the user interface. This allows the user to understand the core of the article in a short amount of time.

[0247] (Application Example 1)

[0248] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0249] In today's information-saturated world, users are required to quickly acquire necessary information and understand it efficiently. Furthermore, there is a lack of means to flexibly utilize information in various aspects of work and daily life. In particular, information visualization devices require simple operation via voice commands and the instantaneous presentation of summarized information.

[0250] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0251] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for receiving user instructions using a speech recognition device. As a result, the user can efficiently acquire information by giving voice instructions and instantly grasp the summarized information on a visualization device.

[0252] A "user terminal" is a device that displays information items and serves as an interface with the user.

[0253] "Identification information" refers to information used to uniquely identify an information item.

[0254] An "information processing device" is a device that stores detailed information and provides information based on identification information.

[0255] "Detailed information" refers to information that includes specific details related to the information item.

[0256] A "language model" is a model trained using natural language processing algorithms, and is used to analyze information and extract key points.

[0257] "Summary information" refers to concise information that includes the main points and key takeaways extracted from detailed information.

[0258] A "visual output device" is a device for displaying summarized information, and its role is to provide information to users visually.

[0259] A "voice recognition device" is a device that identifies the user's voice commands and activates the appropriate function.

[0260] The system for carrying out this invention consists of a visual output device (e.g., smart glasses) worn by the user and a voice recognition device. This system acquires identification information of information items, retrieves detailed information from an information processing device, and then generates summary information using a language model. The summary information is provided to the user by the visual output device. Furthermore, this system includes a voice recognition device that simplifies user operation through voice instructions.

[0261] When a user wears smart glasses and gives voice commands regarding specific news or product information, the visual output device acquires identification information for the information item. The device sends this information to a server, which retrieves detailed information from the information processing device. This detailed information is analyzed using a language model that applies natural language processing technology (e.g., BERT) and generated as summary information. The generated summary information is sent from the server to the visual output device and displayed in the user's field of vision. This allows the user to grasp the information instantly.

[0262] The server functions as the backend environment for this information processing, utilizing hardware and software suitable for information gathering and analysis. For example, it might use a server machine with powerful processing capabilities or a state-of-the-art software environment to run natural language processing libraries.

[0263] For example, if a store staff member needs to explain a new product, they can give a voice command such as "Summarize the features of the new product," and the smart glasses will display summary information such as "This product features a next-generation processor and an extended battery." This allows staff to quickly and accurately convey product information to customers. An example of a prompt would be, "Please summarize the technical details of the new product."

[0264] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0265] Step 1:

[0266] The user wears a visual output device (smart glasses) and gives voice commands to the object for which they want to know information. The input here is the user's voice command. The voice recognition device converts this voice command into text data and sends it to the terminal.

[0267] Step 2:

[0268] The terminal analyzes the received text data and identifies the identification information related to the information items. This identification information serves as a key to retrieve detailed information from the information processing device. The output after processing is the identified identification information.

[0269] Step 3:

[0270] The server uses the identification information received from the terminal to access the information processing device and retrieve the relevant detailed information. The retrieved detailed information includes datasets of news articles and product descriptions. The output is a dataset of detailed information.

[0271] Step 4:

[0272] The server analyzes the acquired detailed information using a language model (e.g., BERT). This analysis extracts key points from the detailed information and generates a summary. The input is a dataset of detailed information, and the output is the summary.

[0273] Step 5:

[0274] The server sends the generated summary information to the terminal. The terminal provides this information to a visual output device, allowing the user to immediately visually confirm the summary content. Here, the input is the summary information, and the output is a visually presented summary text.

[0275] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0276] This invention combines an automated summarization system for users to efficiently understand web news with an emotion engine that recognizes the user's emotions. The user's terminal is equipped with a "Generate AI Summarize" button when displaying web news articles. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article and data that infers the user's emotions to the server.

[0277] The server retrieves detailed information about news articles from a database based on identification information and analyzes that information using a language model. The language model, trained by machine learning algorithms, extracts the main points and key aspects of the article to generate a summary. Simultaneously, an emotion engine recognizes the user's emotions and influences how the generated summary is presented.

[0278] Specifically, the emotion engine analyzes the tone, speed, and selected words of the user's voice and text input to recognize their emotions. Based on this recognition, it provides a detailed summary if the user is relaxed, and a concise summary highlighting only the key points if they are in a hurry. Furthermore, it may guide users to additional relevant information if their interest or curiosity is heightened. This system allows users to efficiently process news in a way that suits their emotional state and needs, improving the quality of information gathering.

[0279] For example, when a user is reading a sports article, if the device's emotion engine recognizes that the user is enjoying it, the summary information will highlight more memorable moments from the game, keeping the user engaged. This allows users to experience the news more than just as a stream of information.

[0280] The following describes the processing flow.

[0281] Step 1:

[0282] While the user is viewing a news article, the terminal displays a "Generate AI Summary" button. This button functions as an interface for the user to click when they want to view a summary of the article.

[0283] Step 2:

[0284] When the user clicks the "Generate AI Summary" button, the terminal collects the article's identification information and the user's input data (voice or text).

[0285] Step 3:

[0286] The terminal sends the collected identification information and input data to the server. At this point, the server prepares to perform both the identification of the news article and the inference of the user's sentiment.

[0287] Step 4:

[0288] The server uses the identification information to obtain detailed information about the target news article from the database. At the same time, the sentiment is analyzed by the sentiment engine from the user's input data.

[0289] Step 5:

[0290] The language model analyzes the obtained news article, extracts the main idea, and generates summary information. This process is supported by machine learning algorithms.

[0291] Step 6:

[0292] The sentiment engine recognizes the user's sentiment and adjusts the presentation format of the summary information based on the result. For example, if it is determined that the user is in a hurry, a short and concise summary is selected.

[0293] Step 7:

[0294] The server sends the adjusted summary information to the terminal.

[0295] Step 8:

[0296] The device displays the received summary information on the user interface. Users can view summaries that are relevant to their situation and efficiently grasp the information.

[0297] (Example 2)

[0298] Next, we will describe Example 2. 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".

[0299] In today's information-saturated world, users are required to quickly and efficiently access and understand a wide variety of news articles. However, news articles can be time-consuming to read and often lack information tailored to the user's emotions and circumstances. As a result, information may be missed or misunderstood.

[0300] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0301] In this invention, the server includes means for acquiring identification information of news articles, means for inferring emotional states, and means for generating summaries using a generative AI model and providing them in a format appropriate to the emotional state. This enables users to quickly and efficiently understand news articles in accordance with their emotional state and circumstances.

[0302] A "user terminal" is an electronic device that a user operates to display and manipulate information.

[0303] "Identification information" refers to data used to uniquely recognize specific information items.

[0304] An "information item" is a unit of digital content provided to users, such as a news article.

[0305] An "information processing device" is a computer system used for managing and processing data.

[0306] The "Generative AI Model" is an artificial intelligence program trained based on machine learning algorithms that analyzes text and generates summaries.

[0307] The "Emotional State" is a state indicating the emotional situation and reactions of the user.

[0308] The "Voice or Text Data" is an input signal or character information used to analyze the user's emotions.

[0309] The "Summary Information" is text that concisely expresses the main idea and important points of information items. [[ID=1...​​​​​​​​​​​​​Specifically, the server provides a detailed summary based on the user's emotional state; if the user is relaxed, it provides a concise summary highlighting only the main points; if the user is in a hurry, it provides a brief summary emphasizing only the key points. Furthermore, if the server determines that the user is interested, it can also guide them to additional relevant information.

[0314] For example, if a user is enjoying sports news, the emotion engine recognizes this and provides a summary that keeps the user engaged by detailing memorable moments from the game. In this way, news articles become experiential content that goes beyond mere information dissemination.

[0315] An example of a prompt message is, "Please summarize this news. Also, if the user is in a hurry, please highlight only the key points." This allows the AI ​​to generate output that meets the specified conditions.

[0316] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0317] Step 1:

[0318] The user first views a web news article displayed on their device. If the user decides they want to summarize a particular news article, they click the "Generate AI Summarize" button on their device. This action causes the device to obtain identifying information such as the URL and article ID of the news article as input. Next, along with this identifying information, the device also collects sentiment inference data obtained from voice and text input, and sends these to the server.

[0319] Step 2:

[0320] The server uses the identification information received from the terminal to retrieve detailed information about the corresponding news article from the database. This data retrieval yields the article's text and related metadata as output. This prepares the server for the subsequent text analysis.

[0321] Step 3:

[0322] The server inputs the retrieved news article into a generative AI model. The prompt used is "Please summarize this news." The generative AI model, trained with machine learning algorithms, analyzes the input data of the news article and generates a summary. This process outputs summary information that extracts the main points and key aspects of the article.

[0323] Step 4:

[0324] The server activates its emotion engine and analyzes the emotion prediction data transmitted from the terminal. Specifically, it analyzes factors such as voice tone, text content, and input speed to predict the user's emotional state. Based on this prediction, it determines whether the user is relaxed, in a hurry, or highly interested.

[0325] Step 5:

[0326] The server adjusts the generated summary information based on the emotional state. For example, if the user is relaxed, it generates a summary with detailed explanations; if they are in a hurry, it generates a concise summary that highlights the key points. If the server determines that the user is agitated, it includes relevant additional information in the summary. This adjusted summary information becomes the output.

[0327] Step 6:

[0328] Ultimately, the server sends the adjusted summary information to the terminal. The terminal then displays this summary information to the user. This allows the user to view a summary of the news article in a format that best suits their emotional state in real time.

[0329] (Application Example 2)

[0330] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0331] It is difficult to accurately grasp users' emotions and interests while they are viewing content, and to present relevant information appropriately and efficiently. In particular, there is a lack of means to enhance the richness of the information users gain from the content and to provide information that meets their individual needs.

[0332] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0333] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for adjusting the generated summary information with an emotion recognition device that recognizes the user's emotions. This enables flexible information provision in response to the user's emotions.

[0334] A "user terminal" is a device capable of displaying and inputting information, and provides an interface for users to view content.

[0335] An "information item" is an individual unit of information related to specific content or data, and possesses identifying information.

[0336] "Identification information" refers to data used to uniquely identify an information item, and is used for communication with databases and information processing devices.

[0337] "Detailed information" refers to additional explanations or data related to an information item that are necessary for users to understand the information.

[0338] An "information processing device" is a device or system for processing and providing data, including databases and servers.

[0339] A "language model" is an algorithm used for natural language processing, specifically for analyzing and summarizing text data.

[0340] An "emotion recognition device" is a device that recognizes a user's emotions from voice, text, and visual characteristics, and is used to identify the user's emotional state.

[0341] A "visualization display device" is a device for visually displaying information and presenting generated summary information to the user.

[0342] "Emotion" refers to a state related to a user's feelings or mood, and is a concept used to analyze and understand the user's response to a system.

[0343] "Additional information" refers to relevant data provided according to the user's interests and emotions, and includes supplementary content to satisfy the user's information needs.

[0344] This invention is a system that identifies information items displayed on a user terminal, detects the user's emotions, and then provides a summary of the information and additional information. The server receives identification information from the user terminal and obtains detailed information through an information processing device. Then, it analyzes this detailed information using a language model as a generating AI model and generates a summary.

[0345] In this process, the user's device uses an emotion recognition device to detect the user's emotions through voice input and visual data. This emotion data is processed by a server, and the generated summary information is adjusted according to the emotion. For example, if the user is relaxed, more detailed content is displayed, while if they are in a hurry, a concise summary focusing on the key points is presented. Furthermore, if the system wants to keep the user interested, it presents relevant news and trivia as additional information.

[0346] When users are watching movies or video content, the smart glasses use an emotion engine to analyze their reactions based on the visual and audio data they capture. For example, if the system detects increased excitement or interest while watching a sports match, it will display the latest news and player information related to the match as additional information. In this way, users can gain a deeper understanding of and enjoyment of what they are watching.

[0347] For example, if a user is watching a "specific movie," the emotion engine will sense the user's level of interest and provide additional information about that movie. An example of an input prompt for the generative AI model would be: "The user is currently watching a specific movie. The emotion engine is showing high interest. Please generate additional relevant information."

[0348] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0349] Step 1:

[0350] The user selects and starts playback of content they are watching on their device. At this time, the device obtains identification information related to the content and sends it to the server. The input is the content's identification information, and the output is the transmission of this identification information to the server. Specifically, when a user selects a movie or program using a visual device such as smart glasses, that information is transmitted to the system.

[0351] Step 2:

[0352] The server retrieves detailed information from the information processing device based on the received identification information. This provides the relevant data for the content. The input is the content's identification information, and the output is the detailed information. Specifically, the server queries the database to collect detailed content information.

[0353] Step 3:

[0354] The server analyzes the acquired detailed information using a language model, which is a generating AI model, and generates summary information. The input is detailed information, and the output is the generated summary information. Specifically, the generating AI processes text data, extracts important points, and generates a summary.

[0355] Step 4:

[0356] The device uses an emotion recognition device to recognize the user's emotions from audio and visual data. The input is data related to the user's emotions, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to capture the user's facial expressions and vocalizations, and analyzes them with an emotion engine.

[0357] Step 5:

[0358] The server adjusts the generated summary information based on the recognized sentiment data and sends it to the user's terminal. The input is the recognized sentiment data and summary information, and the output is the adjusted summary information. Specifically, the server provides detailed information if the user is calm, and shortened content if the user is in a hurry.

[0359] Step 6:

[0360] The device presents the user with adjusted summary information and displays additional relevant information based on the sentiment recognition results. The input is the adjusted summary information, and the output is the displayed content. Specifically, the device displays summary information and interesting trivia on its display. For example, if the user shows interest in a particular scene, background knowledge related to that scene is added.

[0361] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0362] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0363] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0364] [Third Embodiment]

[0365] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0366] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0367] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0368] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0369] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0370] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0371] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0372] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0373] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0374] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0375] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0376] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0377] This invention provides an automated summarization system for users to efficiently understand web news. Specifically, a "Generate AI Summary" button is displayed on the web news page on the user's terminal. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article to the server. Based on the received identification information, the server retrieves detailed information about the news article from its database.

[0378] The acquired detailed information is automatically analyzed using a language model. This language model is trained on a large amount of news data using machine learning algorithms and has the ability to extract the main points and key aspects of an article. The analyzed information is generated as a summary and sent from the server to the terminal.

[0379] The terminal displays the received summary information on the user interface, allowing users to quickly grasp the news summary. This system enables users to quickly understand vast amounts of news information and access detailed information as needed.

[0380] As a concrete example, when a user accesses an economic news article, the server analyzes the article's content and generates summary information such as "Major companies report better-than-expected quarterly earnings." This summary information is displayed on the user's device, allowing them to immediately grasp the main points of the article. This enables users to efficiently gather information and, if necessary, quickly access detailed article content.

[0381] The following describes the processing flow.

[0382] Step 1:

[0383] When a user views an article on a news website, their device will display a "Generate AI Summary" button on the page.

[0384] Step 2:

[0385] When a user clicks the "Generate AI Summarize" button, the device sends the article's identification information to the server. This identification information allows the server to determine which articles should be summarized.

[0386] Step 3:

[0387] The server uses the received identification information to retrieve detailed information about the relevant news article from the database.

[0388] Step 4:

[0389] The server passes detailed information from retrieved news articles to a language model for analysis to perform summarization. This language model uses a trained machine learning algorithm to extract the main points of the article and generate summary information.

[0390] Step 5:

[0391] The server sends the generated summary information to the terminal.

[0392] Step 6:

[0393] The device displays the received summary information on the user interface. By viewing this summary information, the user can quickly understand the key points of the article.

[0394] (Example 1)

[0395] Next, we will describe Example 1. 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."

[0396] In today's information society, users are surrounded by vast amounts of information and are required to efficiently acquire the information they need. However, traditional methods require manually selecting important information from a massive dataset, which is time-consuming and laborious. Therefore, there is a need for automated systems that allow users to quickly grasp information and access details as needed.

[0397] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0398] In this invention, the server includes means for acquiring identification information of an article displayed on the user's terminal, means for acquiring detailed information of the article from an information processing device based on the identification information, and means for analyzing the detailed information using a natural language processing model and generating summary information. This enables the user to understand the main points of the article in a short time and to efficiently collect information.

[0399] A "user terminal" is an electronic device used to acquire and display information, and which can be directly operated by the user.

[0400] "Article identification information" refers to unique information used to identify a particular article, and is usually represented as a URL or identifier code.

[0401] An "information processing device" is a computer device that acquires, analyzes, and generates data, and functions as a server.

[0402] A "natural language processing model" is an algorithm that uses machine learning techniques to analyze human language, and has the function of extracting important information from text and generating a summary.

[0403] "Summary information" is a concise summary of key information extracted from a longer article, used to help users understand the main points of the article in a short amount of time.

[0404] This invention provides an automated summarization system that enables users to efficiently understand news articles. The system consists of a user terminal, a server, and a trained natural language processing model.

[0405] The user's device provides a "Generate AI Summary" button on the webpage displaying the news article. When the user clicks this button, the device sends identification information to the server to uniquely identify the article. The client's browser plays a crucial role in sending this identification information.

[0406] Based on the received identification information, the server uses an information processing device and a database to retrieve detailed information about the article. This includes the article's title and the entire body of the text. Next, the server uses a natural language processing model (for example, a model using machine learning techniques such as BERT or GPT) to analyze the retrieved article. This model is used to analyze the article's content, extract important information, and generate a summary.

[0407] The generated summary information is sent from the server to the user's terminal. The terminal displays this summary information on its user interface, allowing the user to quickly grasp the main points of the article. This process enables users to efficiently obtain important information from a large amount of article data.

[0408] For example, when a user accesses an economic news article and presses the "Generate AI Summary" button, the server generates a summary such as "Major companies report better-than-expected quarterly earnings," which is immediately displayed on the user's device. This allows the user to access important information while saving time reading the entire article. As an example of a prompt, the system can be asked to generate a specific summary by using "Generate a summary of this article. Article ID: 12345."

[0409] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0410] Step 1:

[0411] The user clicks the "Generate AI Summary" button displayed on the web news page on their device. This action retrieves the identifying information of the currently displayed news article (e.g., URL and article ID). The input is the user's click operation, and the output is the article's identifying information.

[0412] Step 2:

[0413] The terminal sends the identification information of the retrieved article to the server. The server receives this identification information as input and queries the database to retrieve detailed information about the article. At this point, the output is the specific details of the article (title, body, etc.). Retrieval from the database is performed using an SQL query.

[0414] Step 3:

[0415] The server inputs the detailed information of the obtained article into a natural language processing model. This model is used to analyze the article content and generate a summary. This analysis includes processes such as tokenization, extraction of key sentences, and identification of main points. The input is the detailed information of the article, and the output is the summary.

[0416] Step 4:

[0417] The server sends the generated summary information to the terminal. The terminal displays the summary information received from the server on a portion of the web page to present it to the user in an easy-to-understand manner. The input is the summary information, and the output is the display on the user interface. This allows the user to understand the core of the article in a short amount of time.

[0418] (Application Example 1)

[0419] Next, we will explain Application Example 1. In the following explanation, 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."

[0420] In today's information-saturated world, users are required to quickly acquire necessary information and understand it efficiently. Furthermore, there is a lack of means to flexibly utilize information in various aspects of work and daily life. In particular, information visualization devices require simple operation via voice commands and the instantaneous presentation of summarized information.

[0421] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0422] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for receiving user instructions using a speech recognition device. As a result, the user can efficiently acquire information by giving voice instructions and instantly grasp the summarized information on a visualization device.

[0423] A "user terminal" is a device that displays information items and serves as an interface with the user.

[0424] "Identification information" refers to information used to uniquely identify an information item.

[0425] An "information processing device" is a device that stores detailed information and provides information based on identification information.

[0426] "Detailed information" refers to information that includes specific details related to the information item.

[0427] A "language model" is a model trained using natural language processing algorithms, and is used to analyze information and extract key points.

[0428] "Summary information" refers to concise information that includes the main points and key takeaways extracted from detailed information.

[0429] A "visual output device" is a device for displaying summarized information, and its role is to provide information to users visually.

[0430] A "voice recognition device" is a device that identifies the user's voice commands and activates the appropriate function.

[0431] The system for carrying out this invention consists of a visual output device (e.g., smart glasses) worn by the user and a voice recognition device. This system acquires identification information of information items, retrieves detailed information from an information processing device, and then generates summary information using a language model. The summary information is provided to the user by the visual output device. Furthermore, this system includes a voice recognition device that simplifies user operation through voice instructions.

[0432] When a user wears smart glasses and gives voice commands regarding specific news or product information, the visual output device acquires identification information for the information item. The device sends this information to a server, which retrieves detailed information from the information processing device. This detailed information is analyzed using a language model that applies natural language processing technology (e.g., BERT) and generated as summary information. The generated summary information is sent from the server to the visual output device and displayed in the user's field of vision. This allows the user to grasp the information instantly.

[0433] The server functions as the backend environment for this information processing, utilizing hardware and software suitable for information gathering and analysis. For example, it might use a server machine with powerful processing capabilities or a state-of-the-art software environment to run natural language processing libraries.

[0434] For example, if a store staff member needs to explain a new product, they can give a voice command such as "Summarize the features of the new product," and the smart glasses will display summary information such as "This product features a next-generation processor and an extended battery." This allows staff to quickly and accurately convey product information to customers. An example of a prompt would be, "Please summarize the technical details of the new product."

[0435] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0436] Step 1:

[0437] The user wears a visual output device (smart glasses) and gives voice commands to the object for which they want to know information. The input here is the user's voice command. The voice recognition device converts this voice command into text data and sends it to the terminal.

[0438] Step 2:

[0439] The terminal analyzes the received text data and identifies the identification information related to the information items. This identification information serves as a key to retrieve detailed information from the information processing device. The output after processing is the identified identification information.

[0440] Step 3:

[0441] The server uses the identification information received from the terminal to access the information processing device and retrieve the relevant detailed information. The retrieved detailed information includes datasets of news articles and product descriptions. The output is a dataset of detailed information.

[0442] Step 4:

[0443] The server analyzes the acquired detailed information using a language model (e.g., BERT). This analysis extracts key points from the detailed information and generates a summary. The input is a dataset of detailed information, and the output is the summary.

[0444] Step 5:

[0445] The server sends the generated summary information to the terminal. The terminal provides this information to a visual output device, allowing the user to immediately visually confirm the summary content. Here, the input is the summary information, and the output is a visually presented summary text.

[0446] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0447] This invention combines an automated summarization system for users to efficiently understand web news with an emotion engine that recognizes the user's emotions. The user's terminal is equipped with a "Generate AI Summarize" button when displaying web news articles. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article and data that infers the user's emotions to the server.

[0448] The server retrieves detailed information about news articles from a database based on identification information and analyzes that information using a language model. The language model, trained by machine learning algorithms, extracts the main points and key aspects of the article to generate a summary. Simultaneously, an emotion engine recognizes the user's emotions and influences how the generated summary is presented.

[0449] Specifically, the emotion engine analyzes the tone, speed, and selected words of the user's voice and text input to recognize their emotions. Based on this recognition, it provides a detailed summary if the user is relaxed, and a concise summary highlighting only the key points if they are in a hurry. Furthermore, it may guide users to additional relevant information if their interest or curiosity is heightened. This system allows users to efficiently process news in a way that suits their emotional state and needs, improving the quality of information gathering.

[0450] For example, when a user is reading a sports article, if the device's emotion engine recognizes that the user is enjoying it, the summary information will highlight more memorable moments from the game, keeping the user engaged. This allows users to experience the news more than just as a stream of information.

[0451] The following describes the processing flow.

[0452] Step 1:

[0453] While a user is viewing a news article, the device displays a "Generate AI Summary" button. This button serves as an interface for users to click if they want to view a summary of the article.

[0454] Step 2:

[0455] When a user clicks the "Generate AI Summarize" button, the device collects the article's identification information and the user's input data (voice or text).

[0456] Step 3:

[0457] The device sends the collected identification information and input data to the server. At this point, the server prepares to both identify the news article and infer the user's sentiment.

[0458] Step 4:

[0459] The server uses identification information to retrieve detailed information about the target news article from the database. Simultaneously, it analyzes the user's input data using an emotion engine to determine their emotions.

[0460] Step 5:

[0461] The language model analyzes the acquired news articles, extracts the main points, and generates summary information. This process is supported by machine learning algorithms.

[0462] Step 6:

[0463] The emotion engine recognizes the user's emotions and adjusts the presentation format of the summary information based on that. For example, if it determines that the user is in a hurry, it selects a short and concise summary.

[0464] Step 7:

[0465] The server sends the adjusted summary information to the terminal.

[0466] Step 8:

[0467] The device displays the received summary information on the user interface. Users can view summaries that are relevant to their situation and efficiently grasp the information.

[0468] (Example 2)

[0469] Next, we will describe Example 2. 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."

[0470] In today's information-saturated world, users are required to quickly and efficiently access and understand a wide variety of news articles. However, news articles can be time-consuming to read and often lack information tailored to the user's emotions and circumstances. As a result, information may be missed or misunderstood.

[0471] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0472] In this invention, the server includes means for acquiring identification information of news articles, means for inferring emotional states, and means for generating summaries using a generative AI model and providing them in a format appropriate to the emotional state. This enables users to quickly and efficiently understand news articles in accordance with their emotional state and circumstances.

[0473] A "user terminal" is an electronic device that a user operates to display and manipulate information.

[0474] "Identification information" refers to data used to uniquely recognize specific information items.

[0475] An "information item" is a unit of digital content provided to users, such as a news article.

[0476] An "information processing device" is a computer system used for managing and processing data.

[0477] A "generative AI model" is an artificial intelligence program that is trained based on machine learning algorithms to analyze text and generate summaries.

[0478] "Emotional state" refers to the state of a user's emotional situation or reaction.

[0479] "Audio or text data" refers to input signals or textual information used to analyze a user's emotions.

[0480] "Summary information" is text that concisely expresses the main points and important aspects of an information item.

[0481] This invention is an automated summarization system designed to help users efficiently understand web news, and includes a function to recognize the user's emotions and adjust the summary accordingly. The user's terminal displays the news article and is equipped with an "Generate AI Summary" button. By pressing this button, the user requests a summary of the news article.

[0482] When a user clicks the "Generate AI Summarize" button, the device obtains identification information to uniquely identify the news article and also collects and sends data to the server to infer the user's sentiment. This sentiment data includes the tone and speed of voice and text input, as well as selected words.

[0483] The server uses identification information to retrieve detailed news article information from the database and analyzes it using a generative AI model. The generative AI model is trained using machine learning algorithms and extracts the main points and key aspects of the article to generate a summary. The server also uses an emotion engine to analyze the user's emotional state and adjusts how the generated summary is presented based on that emotion.

[0484] Specifically, the server provides a detailed summary based on the user's emotional state; if the user is relaxed, it provides a concise summary highlighting only the main points; if the user is in a hurry, it provides a brief summary emphasizing only the key points. Furthermore, if the server determines that the user is interested, it can also guide them to additional relevant information.

[0485] For example, if a user is enjoying sports news, the emotion engine recognizes this and provides a summary that keeps the user engaged by detailing memorable moments from the game. In this way, news articles become experiential content that goes beyond mere information dissemination.

[0486] An example of a prompt message is, "Please summarize this news. Also, if the user is in a hurry, please highlight only the key points." This allows the AI ​​to generate output that meets the specified conditions.

[0487] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0488] Step 1:

[0489] The user first views a web news article displayed on their device. If the user decides they want to summarize a particular news article, they click the "Generate AI Summarize" button on their device. This action causes the device to obtain identifying information such as the URL and article ID of the news article as input. Next, along with this identifying information, the device also collects sentiment inference data obtained from voice and text input, and sends these to the server.

[0490] Step 2:

[0491] The server uses the identification information received from the terminal to retrieve detailed information about the corresponding news article from the database. This data retrieval yields the article's text and related metadata as output. This prepares the server for the subsequent text analysis.

[0492] Step 3:

[0493] The server inputs the retrieved news article into a generative AI model. The prompt used is "Please summarize this news." The generative AI model, trained with machine learning algorithms, analyzes the input data of the news article and generates a summary. This process outputs summary information that extracts the main points and key aspects of the article.

[0494] Step 4:

[0495] The server activates its emotion engine and analyzes the emotion prediction data transmitted from the terminal. Specifically, it analyzes factors such as voice tone, text content, and input speed to predict the user's emotional state. Based on this prediction, it determines whether the user is relaxed, in a hurry, or highly interested.

[0496] Step 5:

[0497] The server adjusts the generated summary information based on the emotional state. For example, if the user is relaxed, it generates a summary with detailed explanations; if they are in a hurry, it generates a concise summary that highlights the key points. If the server determines that the user is agitated, it includes relevant additional information in the summary. This adjusted summary information becomes the output.

[0498] Step 6:

[0499] Ultimately, the server sends the adjusted summary information to the terminal. The terminal then displays this summary information to the user. This allows the user to view a summary of the news article in a format that best suits their emotional state in real time.

[0500] (Application Example 2)

[0501] Next, we will explain application example 2. In the following explanation, 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."

[0502] It is difficult to accurately grasp users' emotions and interests while they are viewing content, and to present relevant information appropriately and efficiently. In particular, there is a lack of means to enhance the richness of the information users gain from the content and to provide information that meets their individual needs.

[0503] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0504] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for adjusting the generated summary information with an emotion recognition device that recognizes the user's emotions. This enables flexible information provision in response to the user's emotions.

[0505] A "user terminal" is a device capable of displaying and inputting information, and provides an interface for users to view content.

[0506] An "information item" is an individual unit of information related to specific content or data, and possesses identifying information.

[0507] "Identification information" refers to data used to uniquely identify an information item, and is used for communication with databases and information processing devices.

[0508] "Detailed information" refers to additional explanations or data related to an information item that are necessary for users to understand the information.

[0509] An "information processing device" is a device or system for processing and providing data, including databases and servers.

[0510] A "language model" is an algorithm used for natural language processing, specifically for analyzing and summarizing text data.

[0511] An "emotion recognition device" is a device that recognizes a user's emotions from voice, text, and visual characteristics, and is used to identify the user's emotional state.

[0512] A "visualization display device" is a device for visually displaying information and presenting generated summary information to the user.

[0513] "Emotion" refers to a state related to a user's feelings or mood, and is a concept used to analyze and understand the user's response to a system.

[0514] "Additional information" refers to relevant data provided according to the user's interests and emotions, and includes supplementary content to satisfy the user's information needs.

[0515] This invention is a system that identifies information items displayed on a user terminal, detects the user's emotions, and then provides a summary of the information and additional information. The server receives identification information from the user terminal and obtains detailed information through an information processing device. Then, it analyzes this detailed information using a language model as a generating AI model and generates a summary.

[0516] In this process, the user's device uses an emotion recognition device to detect the user's emotions through voice input and visual data. This emotion data is processed by a server, and the generated summary information is adjusted according to the emotion. For example, if the user is relaxed, more detailed content is displayed, while if they are in a hurry, a concise summary focusing on the key points is presented. Furthermore, if the system wants to keep the user interested, it presents relevant news and trivia as additional information.

[0517] When users are watching movies or video content, the smart glasses use an emotion engine to analyze their reactions based on the visual and audio data they capture. For example, if the system detects increased excitement or interest while watching a sports match, it will display the latest news and player information related to the match as additional information. In this way, users can gain a deeper understanding of and enjoyment of what they are watching.

[0518] For example, if a user is watching a "specific movie," the emotion engine will sense the user's level of interest and provide additional information about that movie. An example of an input prompt for the generative AI model would be: "The user is currently watching a specific movie. The emotion engine is showing high interest. Please generate additional relevant information."

[0519] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0520] Step 1:

[0521] The user selects and starts playback of content they are watching on their device. At this time, the device obtains identification information related to the content and sends it to the server. The input is the content's identification information, and the output is the transmission of this identification information to the server. Specifically, when a user selects a movie or program using a visual device such as smart glasses, that information is transmitted to the system.

[0522] Step 2:

[0523] The server retrieves detailed information from the information processing device based on the received identification information. This provides the relevant data for the content. The input is the content's identification information, and the output is the detailed information. Specifically, the server queries the database to collect detailed content information.

[0524] Step 3:

[0525] The server analyzes the acquired detailed information using a language model, which is a generating AI model, and generates summary information. The input is detailed information, and the output is the generated summary information. Specifically, the generating AI processes text data, extracts important points, and generates a summary.

[0526] Step 4:

[0527] The device uses an emotion recognition device to recognize the user's emotions from audio and visual data. The input is data related to the user's emotions, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to capture the user's facial expressions and vocalizations, and analyzes them with an emotion engine.

[0528] Step 5:

[0529] The server adjusts the generated summary information based on the recognized sentiment data and sends it to the user's terminal. The input is the recognized sentiment data and summary information, and the output is the adjusted summary information. Specifically, the server provides detailed information if the user is calm, and shortened content if the user is in a hurry.

[0530] Step 6:

[0531] The device presents the user with adjusted summary information and displays additional relevant information based on the sentiment recognition results. The input is the adjusted summary information, and the output is the displayed content. Specifically, the device displays summary information and interesting trivia on its display. For example, if the user shows interest in a particular scene, background knowledge related to that scene is added.

[0532] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0533] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0534] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0535] [Fourth Embodiment]

[0536] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0537] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0538] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0539] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0540] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0541] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0542] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0543] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0544] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0545] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0546] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0547] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0548] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0549] This invention provides an automated summarization system for users to efficiently understand web news. Specifically, a "Generate AI Summary" button is displayed on the web news page on the user's terminal. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article to the server. Based on the received identification information, the server retrieves detailed information about the news article from its database.

[0550] The acquired detailed information is automatically analyzed using a language model. This language model is trained on a large amount of news data using machine learning algorithms and has the ability to extract the main points and key aspects of an article. The analyzed information is generated as a summary and sent from the server to the terminal.

[0551] The terminal displays the received summary information on the user interface, allowing users to quickly grasp the news summary. This system enables users to quickly understand vast amounts of news information and access detailed information as needed.

[0552] As a concrete example, when a user accesses an economic news article, the server analyzes the article's content and generates summary information such as "Major companies report better-than-expected quarterly earnings." This summary information is displayed on the user's device, allowing them to immediately grasp the main points of the article. This enables users to efficiently gather information and, if necessary, quickly access detailed article content.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] When a user views an article on a news website, their device will display a "Generate AI Summary" button on the page.

[0556] Step 2:

[0557] When a user clicks the "Generate AI Summarize" button, the device sends the article's identification information to the server. This identification information allows the server to determine which articles should be summarized.

[0558] Step 3:

[0559] The server uses the received identification information to retrieve detailed information about the relevant news article from the database.

[0560] Step 4:

[0561] The server passes detailed information from retrieved news articles to a language model for analysis to perform summarization. This language model uses a trained machine learning algorithm to extract the main points of the article and generate summary information.

[0562] Step 5:

[0563] The server sends the generated summary information to the terminal.

[0564] Step 6:

[0565] The device displays the received summary information on the user interface. By viewing this summary information, the user can quickly understand the key points of the article.

[0566] (Example 1)

[0567] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0568] In today's information society, users are surrounded by vast amounts of information and are required to efficiently acquire the information they need. However, traditional methods require manually selecting important information from a massive dataset, which is time-consuming and laborious. Therefore, there is a need for automated systems that allow users to quickly grasp information and access details as needed.

[0569] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0570] In this invention, the server includes means for acquiring identification information of an article displayed on the user's terminal, means for acquiring detailed information of the article from an information processing device based on the identification information, and means for analyzing the detailed information using a natural language processing model and generating summary information. This enables the user to understand the main points of the article in a short time and to efficiently collect information.

[0571] A "user terminal" is an electronic device used to acquire and display information, and which can be directly operated by the user.

[0572] "Article identification information" refers to unique information used to identify a particular article, and is usually represented as a URL or identifier code.

[0573] An "information processing device" is a computer device that acquires, analyzes, and generates data, and functions as a server.

[0574] A "natural language processing model" is an algorithm that uses machine learning techniques to analyze human language, and has the function of extracting important information from text and generating a summary.

[0575] "Summary information" is a concise summary of key information extracted from a longer article, used to help users understand the main points of the article in a short amount of time.

[0576] This invention provides an automated summarization system that enables users to efficiently understand news articles. The system consists of a user terminal, a server, and a trained natural language processing model.

[0577] The user's device provides a "Generate AI Summary" button on the webpage displaying the news article. When the user clicks this button, the device sends identification information to the server to uniquely identify the article. The client's browser plays a crucial role in sending this identification information.

[0578] Based on the received identification information, the server uses an information processing device and a database to retrieve detailed information about the article. This includes the article's title and the entire body of the text. Next, the server uses a natural language processing model (for example, a model using machine learning techniques such as BERT or GPT) to analyze the retrieved article. This model is used to analyze the article's content, extract important information, and generate a summary.

[0579] The generated summary information is sent from the server to the user's terminal. The terminal displays this summary information on its user interface, allowing the user to quickly grasp the main points of the article. This process enables users to efficiently obtain important information from a large amount of article data.

[0580] For example, when a user accesses an economic news article and presses the "Generate AI Summary" button, the server generates a summary such as "Major companies report better-than-expected quarterly earnings," which is immediately displayed on the user's device. This allows the user to access important information while saving time reading the entire article. As an example of a prompt, the system can be asked to generate a specific summary by using "Generate a summary of this article. Article ID: 12345."

[0581] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0582] Step 1:

[0583] The user clicks the "Generate AI Summary" button displayed on the web news page on their device. This action retrieves the identifying information of the currently displayed news article (e.g., URL and article ID). The input is the user's click operation, and the output is the article's identifying information.

[0584] Step 2:

[0585] The terminal sends the identification information of the retrieved article to the server. The server receives this identification information as input and queries the database to retrieve detailed information about the article. At this point, the output is the specific details of the article (title, body, etc.). Retrieval from the database is performed using an SQL query.

[0586] Step 3:

[0587] The server inputs the detailed information of the obtained article into a natural language processing model. This model is used to analyze the article content and generate a summary. This analysis includes processes such as tokenization, extraction of key sentences, and identification of main points. The input is the detailed information of the article, and the output is the summary.

[0588] Step 4:

[0589] The server sends the generated summary information to the terminal. The terminal displays the summary information received from the server on a portion of the web page to present it to the user in an easy-to-understand manner. The input is the summary information, and the output is the display on the user interface. This allows the user to understand the core of the article in a short amount of time.

[0590] (Application Example 1)

[0591] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0592] In today's information-saturated world, users are required to quickly acquire necessary information and understand it efficiently. Furthermore, there is a lack of means to flexibly utilize information in various aspects of work and daily life. In particular, information visualization devices require simple operation via voice commands and the instantaneous presentation of summarized information.

[0593] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0594] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for receiving user instructions using a speech recognition device. As a result, the user can efficiently acquire information by giving voice instructions and instantly grasp the summarized information on a visualization device.

[0595] A "user terminal" is a device that displays information items and serves as an interface with the user.

[0596] "Identification information" refers to information used to uniquely identify an information item.

[0597] An "information processing device" is a device that stores detailed information and provides information based on identification information.

[0598] "Detailed information" refers to information that includes specific details related to the information item.

[0599] A "language model" is a model trained using natural language processing algorithms, and is used to analyze information and extract key points.

[0600] "Summary information" refers to concise information that includes the main points and key takeaways extracted from detailed information.

[0601] A "visual output device" is a device for displaying summarized information, and its role is to provide information to users visually.

[0602] A "voice recognition device" is a device that identifies the user's voice commands and activates the appropriate function.

[0603] The system for carrying out this invention consists of a visual output device (e.g., smart glasses) worn by the user and a voice recognition device. This system acquires identification information of information items, retrieves detailed information from an information processing device, and then generates summary information using a language model. The summary information is provided to the user by the visual output device. Furthermore, this system includes a voice recognition device that simplifies user operation through voice instructions.

[0604] When a user wears smart glasses and gives voice commands regarding specific news or product information, the visual output device acquires identification information for the information item. The device sends this information to a server, which retrieves detailed information from the information processing device. This detailed information is analyzed using a language model that applies natural language processing technology (e.g., BERT) and generated as summary information. The generated summary information is sent from the server to the visual output device and displayed in the user's field of vision. This allows the user to grasp the information instantly.

[0605] The server functions as the backend environment for this information processing, utilizing hardware and software suitable for information gathering and analysis. For example, it might use a server machine with powerful processing capabilities or a state-of-the-art software environment to run natural language processing libraries.

[0606] For example, if a store staff member needs to explain a new product, they can give a voice command such as "Summarize the features of the new product," and the smart glasses will display summary information such as "This product features a next-generation processor and an extended battery." This allows staff to quickly and accurately convey product information to customers. An example of a prompt would be, "Please summarize the technical details of the new product."

[0607] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0608] Step 1:

[0609] The user wears a visual output device (smart glasses) and gives voice commands to the object for which they want to know information. The input here is the user's voice command. The voice recognition device converts this voice command into text data and sends it to the terminal.

[0610] Step 2:

[0611] The terminal analyzes the received text data and identifies the identification information related to the information items. This identification information serves as a key to retrieve detailed information from the information processing device. The output after processing is the identified identification information.

[0612] Step 3:

[0613] The server uses the identification information received from the terminal to access the information processing device and retrieve the relevant detailed information. The retrieved detailed information includes datasets of news articles and product descriptions. The output is a dataset of detailed information.

[0614] Step 4:

[0615] The server analyzes the acquired detailed information using a language model (e.g., BERT). This analysis extracts key points from the detailed information and generates a summary. The input is a dataset of detailed information, and the output is the summary.

[0616] Step 5:

[0617] The server sends the generated summary information to the terminal. The terminal provides this information to a visual output device, allowing the user to immediately visually confirm the summary content. Here, the input is the summary information, and the output is a visually presented summary text.

[0618] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0619] This invention combines an automated summarization system for users to efficiently understand web news with an emotion engine that recognizes the user's emotions. The user's terminal is equipped with a "Generate AI Summarize" button when displaying web news articles. When the user clicks this button, the terminal sends identification information that uniquely identifies the news article and data that infers the user's emotions to the server.

[0620] The server retrieves detailed information about news articles from a database based on identification information and analyzes that information using a language model. The language model, trained by machine learning algorithms, extracts the main points and key aspects of the article to generate a summary. Simultaneously, an emotion engine recognizes the user's emotions and influences how the generated summary is presented.

[0621] Specifically, the emotion engine analyzes the tone, speed, and selected words of the user's voice and text input to recognize their emotions. Based on this recognition, it provides a detailed summary if the user is relaxed, and a concise summary highlighting only the key points if they are in a hurry. Furthermore, it may guide users to additional relevant information if their interest or curiosity is heightened. This system allows users to efficiently process news in a way that suits their emotional state and needs, improving the quality of information gathering.

[0622] For example, when a user is reading a sports article, if the device's emotion engine recognizes that the user is enjoying it, the summary information will highlight more memorable moments from the game, keeping the user engaged. This allows users to experience the news more than just as a stream of information.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] While a user is viewing a news article, the device displays a "Generate AI Summary" button. This button serves as an interface for users to click if they want to view a summary of the article.

[0626] Step 2:

[0627] When a user clicks the "Generate AI Summarize" button, the device collects the article's identification information and the user's input data (voice or text).

[0628] Step 3:

[0629] The device sends the collected identification information and input data to the server. At this point, the server prepares to both identify the news article and infer the user's sentiment.

[0630] Step 4:

[0631] The server uses identification information to retrieve detailed information about the target news article from the database. Simultaneously, it analyzes the user's input data using an emotion engine to determine their emotions.

[0632] Step 5:

[0633] The language model analyzes the acquired news articles, extracts the main points, and generates summary information. This process is supported by machine learning algorithms.

[0634] Step 6:

[0635] The emotion engine recognizes the user's emotions and adjusts the presentation format of the summary information based on that. For example, if it determines that the user is in a hurry, it selects a short and concise summary.

[0636] Step 7:

[0637] The server sends the adjusted summary information to the terminal.

[0638] Step 8:

[0639] The device displays the received summary information on the user interface. Users can view summaries that are relevant to their situation and efficiently grasp the information.

[0640] (Example 2)

[0641] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] In today's information-saturated world, users are required to quickly and efficiently access and understand a wide variety of news articles. However, news articles can be time-consuming to read and often lack information tailored to the user's emotions and circumstances. As a result, information may be missed or misunderstood.

[0643] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0644] In this invention, the server includes means for acquiring identification information of news articles, means for inferring emotional states, and means for generating summaries using a generative AI model and providing them in a format appropriate to the emotional state. This enables users to quickly and efficiently understand news articles in accordance with their emotional state and circumstances.

[0645] A "user terminal" is an electronic device that a user operates to display and manipulate information.

[0646] "Identification information" refers to data used to uniquely recognize specific information items.

[0647] An "information item" is a unit of digital content provided to users, such as a news article.

[0648] An "information processing device" is a computer system used for managing and processing data.

[0649] A "generative AI model" is an artificial intelligence program that is trained based on machine learning algorithms to analyze text and generate summaries.

[0650] "Emotional state" refers to the state of a user's emotional situation or reaction.

[0651] "Audio or text data" refers to input signals or textual information used to analyze a user's emotions.

[0652] "Summary information" is text that concisely expresses the main points and important aspects of an information item.

[0653] This invention is an automated summarization system designed to help users efficiently understand web news, and includes a function to recognize the user's emotions and adjust the summary accordingly. The user's terminal displays the news article and is equipped with an "Generate AI Summary" button. By pressing this button, the user requests a summary of the news article.

[0654] When a user clicks the "Generate AI Summarize" button, the device obtains identification information to uniquely identify the news article and also collects and sends data to the server to infer the user's sentiment. This sentiment data includes the tone and speed of voice and text input, as well as selected words.

[0655] The server uses identification information to retrieve detailed news article information from the database and analyzes it using a generative AI model. The generative AI model is trained using machine learning algorithms and extracts the main points and key aspects of the article to generate a summary. The server also uses an emotion engine to analyze the user's emotional state and adjusts how the generated summary is presented based on that emotion.

[0656] Specifically, the server provides a detailed summary based on the user's emotional state; if the user is relaxed, it provides a concise summary highlighting only the main points; if the user is in a hurry, it provides a brief summary emphasizing only the key points. Furthermore, if the server determines that the user is interested, it can also guide them to additional relevant information.

[0657] For example, if a user is enjoying sports news, the emotion engine recognizes this and provides a summary that keeps the user engaged by detailing memorable moments from the game. In this way, news articles become experiential content that goes beyond mere information dissemination.

[0658] An example of a prompt message is, "Please summarize this news. Also, if the user is in a hurry, please highlight only the key points." This allows the AI ​​to generate output that meets the specified conditions.

[0659] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0660] Step 1:

[0661] The user first views a web news article displayed on their device. If the user decides they want to summarize a particular news article, they click the "Generate AI Summarize" button on their device. This action causes the device to obtain identifying information such as the URL and article ID of the news article as input. Next, along with this identifying information, the device also collects sentiment inference data obtained from voice and text input, and sends these to the server.

[0662] Step 2:

[0663] The server uses the identification information received from the terminal to retrieve detailed information about the corresponding news article from the database. This data retrieval yields the article's text and related metadata as output. This prepares the server for the subsequent text analysis.

[0664] Step 3:

[0665] The server inputs the retrieved news article into a generative AI model. The prompt used is "Please summarize this news." The generative AI model, trained with machine learning algorithms, analyzes the input data of the news article and generates a summary. This process outputs summary information that extracts the main points and key aspects of the article.

[0666] Step 4:

[0667] The server activates its emotion engine and analyzes the emotion prediction data transmitted from the terminal. Specifically, it analyzes factors such as voice tone, text content, and input speed to predict the user's emotional state. Based on this prediction, it determines whether the user is relaxed, in a hurry, or highly interested.

[0668] Step 5:

[0669] The server adjusts the generated summary information based on the emotional state. For example, if the user is relaxed, it generates a summary with detailed explanations; if they are in a hurry, it generates a concise summary that highlights the key points. If the server determines that the user is agitated, it includes relevant additional information in the summary. This adjusted summary information becomes the output.

[0670] Step 6:

[0671] Ultimately, the server sends the adjusted summary information to the terminal. The terminal then displays this summary information to the user. This allows the user to view a summary of the news article in a format that best suits their emotional state in real time.

[0672] (Application Example 2)

[0673] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] It is difficult to accurately grasp users' emotions and interests while they are viewing content, and to present relevant information appropriately and efficiently. In particular, there is a lack of means to enhance the richness of the information users gain from the content and to provide information that meets their individual needs.

[0675] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0676] In this invention, the server includes means for acquiring identification information of information items displayed on the user terminal, means for acquiring detailed information of the information items from an information processing device based on the identification information, means for analyzing the detailed information using a language model and generating summary information, and means for adjusting the generated summary information with an emotion recognition device that recognizes the user's emotions. This enables flexible information provision in response to the user's emotions.

[0677] A "user terminal" is a device capable of displaying and inputting information, and provides an interface for users to view content.

[0678] An "information item" is an individual unit of information related to specific content or data, and possesses identifying information.

[0679] "Identification information" refers to data used to uniquely identify an information item, and is used for communication with databases and information processing devices.

[0680] "Detailed information" refers to additional explanations or data related to an information item that are necessary for users to understand the information.

[0681] An "information processing device" is a device or system for processing and providing data, including databases and servers.

[0682] A "language model" is an algorithm used for natural language processing, specifically for analyzing and summarizing text data.

[0683] An "emotion recognition device" is a device that recognizes a user's emotions from voice, text, and visual characteristics, and is used to identify the user's emotional state.

[0684] A "visualization display device" is a device for visually displaying information and presenting generated summary information to the user.

[0685] "Emotion" refers to a state related to a user's feelings or mood, and is a concept used to analyze and understand the user's response to a system.

[0686] "Additional information" refers to relevant data provided according to the user's interests and emotions, and includes supplementary content to satisfy the user's information needs.

[0687] This invention is a system that identifies information items displayed on a user terminal, detects the user's emotions, and then provides a summary of the information and additional information. The server receives identification information from the user terminal and obtains detailed information through an information processing device. Then, it analyzes this detailed information using a language model as a generating AI model and generates a summary.

[0688] In this process, the user's device uses an emotion recognition device to detect the user's emotions through voice input and visual data. This emotion data is processed by a server, and the generated summary information is adjusted according to the emotion. For example, if the user is relaxed, more detailed content is displayed, while if they are in a hurry, a concise summary focusing on the key points is presented. Furthermore, if the system wants to keep the user interested, it presents relevant news and trivia as additional information.

[0689] When users are watching movies or video content, the smart glasses use an emotion engine to analyze their reactions based on the visual and audio data they capture. For example, if the system detects increased excitement or interest while watching a sports match, it will display the latest news and player information related to the match as additional information. In this way, users can gain a deeper understanding of and enjoyment of what they are watching.

[0690] For example, if a user is watching a "specific movie," the emotion engine will sense the user's level of interest and provide additional information about that movie. An example of an input prompt for the generative AI model would be: "The user is currently watching a specific movie. The emotion engine is showing high interest. Please generate additional relevant information."

[0691] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0692] Step 1:

[0693] The user selects and starts playback of content they are watching on their device. At this time, the device obtains identification information related to the content and sends it to the server. The input is the content's identification information, and the output is the transmission of this identification information to the server. Specifically, when a user selects a movie or program using a visual device such as smart glasses, that information is transmitted to the system.

[0694] Step 2:

[0695] The server retrieves detailed information from the information processing device based on the received identification information. This provides the relevant data for the content. The input is the content's identification information, and the output is the detailed information. Specifically, the server queries the database to collect detailed content information.

[0696] Step 3:

[0697] The server analyzes the acquired detailed information using a language model, which is a generating AI model, and generates summary information. The input is detailed information, and the output is the generated summary information. Specifically, the generating AI processes text data, extracts important points, and generates a summary.

[0698] Step 4:

[0699] The device uses an emotion recognition device to recognize the user's emotions from audio and visual data. The input is data related to the user's emotions, and the output is the recognized emotion data. Specifically, the device uses a camera and microphone to capture the user's facial expressions and vocalizations, and analyzes them with an emotion engine.

[0700] Step 5:

[0701] The server adjusts the generated summary information based on the recognized sentiment data and sends it to the user's terminal. The input is the recognized sentiment data and summary information, and the output is the adjusted summary information. Specifically, the server provides detailed information if the user is calm, and shortened content if the user is in a hurry.

[0702] Step 6:

[0703] The device presents the user with adjusted summary information and displays additional relevant information based on the sentiment recognition results. The input is the adjusted summary information, and the output is the displayed content. Specifically, the device displays summary information and interesting trivia on its display. For example, if the user shows interest in a particular scene, background knowledge related to that scene is added.

[0704] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0705] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0706] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0707] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0708] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0709] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0710] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0711] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0712] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0713] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0714] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0715] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0716] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0717] 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.

[0718] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0719] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0720] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0721] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0722] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0723] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0724] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0725] The following is further disclosed regarding the embodiments described above.

[0726] (Claim 1)

[0727] A means for obtaining identification information of information items displayed on the user terminal,

[0728] means for obtaining detailed information of an information item from an information processing device based on the aforementioned identification information,

[0729] A means for analyzing the aforementioned detailed information using a language model and generating summary information,

[0730] Means for displaying the summary information on a display screen,

[0731] A system that includes this.

[0732] (Claim 2)

[0733] The system according to claim 1, wherein the language model is trained by a machine learning algorithm.

[0734] (Claim 3)

[0735] The system according to claim 1, wherein the summary information is provided in multiple summary formats according to the user's selection.

[0736] "Example 1"

[0737] (Claim 1)

[0738] A means for obtaining identification information of an article displayed on the user's terminal,

[0739] A means for obtaining detailed information about an article from an information processing device based on the aforementioned identification information,

[0740] The means for analyzing the aforementioned detailed information using a natural language processing model and generating summary information,

[0741] A means for presenting the aforementioned summary information to the user,

[0742] Means for the user to operate an input device for obtaining identification information of an article,

[0743] A system that includes this.

[0744] (Claim 2)

[0745] The system according to claim 1, wherein the natural language processing model is trained by machine learning techniques.

[0746] (Claim 3)

[0747] The system according to claim 1, wherein the summary information is provided upon request from the user.

[0748] "Application Example 1"

[0749] (Claim 1)

[0750] A means for obtaining identification information of information items displayed on the user terminal,

[0751] means for obtaining detailed information of an information item from an information processing device based on the aforementioned identification information,

[0752] A means for analyzing the aforementioned detailed information using a language model and generating summary information,

[0753] A means for providing the aforementioned summary information to the user through a visual output device,

[0754] A means of receiving user instructions using a voice recognition device,

[0755] A system that includes this.

[0756] (Claim 2)

[0757] The system according to claim 1, wherein the language model is trained by a machine learning algorithm and presents a summary of information items in response to the user's voice instructions.

[0758] (Claim 3)

[0759] The system according to claim 1, wherein the summary information is presented to a visual output device in multiple formats according to the user's selection.

[0760] "Example 2 of combining an emotion engine"

[0761] (Claim 1)

[0762] A means for obtaining identification information of information items displayed on the user terminal,

[0763] means for obtaining detailed information of an information item from an information processing device based on the aforementioned identification information,

[0764] A means for analyzing the aforementioned detailed information using a generation AI model and generating summary information,

[0765] In order to recognize the user's emotional state, a means of analyzing voice or text data to infer emotions,

[0766] A means for adjusting and providing summary information in a format corresponding to the aforementioned emotional state,

[0767] Means for displaying the summary information on a display screen,

[0768] A system that includes this.

[0769] (Claim 2)

[0770] The system according to claim 1, wherein the generating AI model is trained by a machine learning algorithm and provides summary information that reflects the user's emotional state.

[0771] (Claim 3)

[0772] The system according to claim 1, wherein the summary information is provided in multiple summary formats according to the user's emotional state.

[0773] "Application example 2 when combining with an emotional engine"

[0774] (Claim 1)

[0775] A means for obtaining identification information of information items displayed on the user terminal,

[0776] means for obtaining detailed information of an information item from an information processing device based on the aforementioned identification information,

[0777] A means for analyzing the aforementioned detailed information using a language model and generating summary information,

[0778] A means by which the generated summary information is adjusted by an emotion recognition device that recognizes the user's emotions,

[0779] Means for presenting the summary information on a visualization display device,

[0780] Means of providing additional information related to the user's emotions,

[0781] A system that includes this.

[0782] (Claim 2)

[0783] The system according to claim 1, wherein the language model is a model trained by a machine learning algorithm, and the generated summary information is adjusted according to changes in the user's emotions.

[0784] (Claim 3)

[0785] The system according to claim 1, wherein the summary information is provided in multiple variable formats based on the user's selection or emotional recognition. [Explanation of Symbols]

[0786] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for obtaining identification information of information items displayed on the user terminal, means for obtaining detailed information of an information item from an information processing device based on the aforementioned identification information, A means for analyzing the aforementioned detailed information using a language model and generating summary information, Means for displaying the summary information on a display screen, A system that includes this.

2. The system according to claim 1, wherein the language model is trained by a machine learning algorithm.

3. The system according to claim 1, wherein the summary information is provided in multiple summary formats according to the user's selection.

Images